View Article

Abstract

Microbiology might undergo a revolution because to artificial intelligence (AI), which could improve our knowledge and management of microbial system. Explore the revolutionary effects of Artificial intelligence (AI) and machine learning (ML) on the filed of microbiology in this mini-review. The paper gives a quick summary of several fields, including as clinical diagnostic, medication and vaccination development, and management of public health, where Artificial intelligence (AI) is changing practices. Our conversation focuses on the evolution of novel antimicrobial to combat strains that are resistant, the Using neural networks with convolutions for improved Identification of pathogens, and improvements at the point of care diagnostic The use of AI in forensic microbiology, microbial ecology, and epidemiology is also described, highlighting its ability to interpret intricate microbiological interaction and predicting disease epidemics. Highlight the need for interpretable artificial intelligence (AI) models that adhere to ethical and medical standards while critically examining the difficulties in applying AI, like as guaranteeing quality of the data and getting over algorithm-based limitation. We discuss the complexities of digitalizing microbiology diagnosis, highlighting the necessity of effective data management in clinical and laboratory setting. We outlined important future possibilities for artificial intelligence in microbiology, with an emphasis on creating flexible, self-updating AI models and integrating them into clinical setting. AI has the potential to transform infection control and microbiology diagnosis, greatly impacting patient care and public health.

Keywords

AI in microbiology, Machine learning diagnostic, AI drug discovery, AI infectious diseases and bacterial infections, AI clinical microbiology.

Introduction

Microbiology, the study of microorganisms such bacterial, viruses, fungi and parasites, has long been important in understanding diseases, environmental processes, and biotechnological applications [1]. The launch of artificial AI is a type of intelligence. breakthrough phase in the always evolving filed of microbes, altering the foundation of its application and study. As we enter this era, a change in perspective toward computational methodologies for meaningful interpretation of data is required due to the unprecedented influx of biological data obtained from high-throughput technologies. Form identifying microbial interactions and resistance mechanism to forecasting pharmacological targets and infectious disease diagnosis , artificial intelligence (AI), and in particular machine learning (ML), emerges as a crucial tool in tackling complicated microbiological difficulties [2]. (AI) is being incorporated into a variety of fields within microbiology, including bacteriology, mycology, parasitology, and virology. The effective use of AI in microbiology has been accelerated by its combination with sophisticated data gathering tools increased processing strength, and globally network, which are exemplified by Moore's law, the internet, and big data [2,3]. This combination is especially apparent in the files of drug design, where AI-powered techniques are leading the manner in The production of new antimicrobials 

artificial intelligence (AI) has an equally transformative role In the field of clinical microbiology, improving accuracy of diagnosis and streamlining data processing. AI-enabled methods such as matrix-assisted laser ionization/desorption duration - flight MALDI-TOF mass spectrometry is transforming antibiotic opposition profiling as well as microbiological identification by offering prompt, accurate, efficient and reasonably priced fixes [5,6]. AI’s ability to process vast datasets—like genomic information and digital images generated through modern diagnostic tools— is essential to enhancing laboratory findings and speeding up diagnostic workflows. [7,8]. Ai in Microbiology can be used to health with health of the public issue including sepsis and infection disease management, where it can help with diagnosis prognosis, and individualized treatment plans. AI’s use in infection avoidance and management is also Notable because of its capacity to evaluate massive health datasets, which helps with infection control plans and epidemic identification [1,9]. Our goal in this study its to examine the various facets of artificial intelligence’s function in medical microbiology, with a focus on how it affects both clinical and research applications. We will talk about how AI is substantially advancing health care and public health by not just that changing current methods, but furthermore opening the door for new findings and advancements inside the filed of microbiology Consequently making a substantial contribution to the development of  healthcare and public health. This investigation into the intersection of AI and microbiology will shed light on the cutting edge, difficulties, and the future of this multidisciplinary partnership.

1.1 Fundamentals of AI in microbiology

1.1.1 Machine learning (ML)

Microbiology is changing as a result of machine learning, a key element of artificial intelligence (AI). From microbial identification to antibiotic resistance prediction, this technology provides reliable techniques for data analysis.  Making use of a dataset of more than The support vector machine (SVM) and 1500 genomes technique has been utilized to find both well-known and new Genes in Mycobacterium tuberculosis that resist antibiotics  [10].       Figure 1 provides a schematic representation of machine learning applications in microbiology.

1.1.2 Basics of machine learning

Computers may get knowledge from data and make judgments on their own thanks to machine learning.  In microbiology, this is especially advantageous since it opens up new avenues for microbial investigation and greatly improves our comprehension of microbial behavior and disease outcomes [10].

1.1.3 Supervised learning.

Using labelled datasets to train algorithms is known as supervised learning.  This approach works well in microbiology for objectives like forecasting the behaviour of microorganisms or the course of diseases. To detect antibiotic resistance in different bacterial species, adaptive boosting classifiers are created [11,12].

Figure 1. General Workflow And Example For Machine Learning Applications In Microbiology.

1.1.4 Unsupervised learning.

Analyse unlabelled data to find hidden patterns in intricate microbial is known as unsupervised learning. datasets Our comprehension of various microbial communities and their interactions can be greatly improved by using this technique [13–17]. The original dataset is symbolized by the specimens on a pink background.  A wide range of molecular characteristics, including DNA, RNA, and proteins, as well as phenotypic characteristics, such as cellular shape, motility, and acidity levels, are noted from every specimen. These characteristics, represented by F1 through make up a comprehensive collection of traits.  The machine learning model will try to predict certain goal outcomes that are identified concurrently with feature gathering.  These targets, which have a blue backdrop and are connected to the features by bidirectional black arrows, are created from extra data that is correlated with the specimen. The training stage, which follows, is characterized through a violet colour and entails analysing the input data, which comprises parameters such gene activity patterns, metabolic product quantification, and the relative abundance of microbial communities. This crucial stage involves a number of systematic actions, including choosing a suitable model for machine learning, adjusting its conditions to improve precision, and creating the finished model as it identifying most important characteristics.  Following During training, the model is ready for the forecast. stage, during which it comes into contact with fresh, unlabelled biological samples that have been identified by a yellow backdrop. The same features that were utilized in the training phase are extracted from these data through processing.  Lastly, the model predicts the unknown goal outcomes—which are still marked as question marks—by applying its learnt patterns to these features.  This predictive ability advances our knowledge of microbial interactions and behaviour by allowing the extrapolation of important findings from new biological data. Microbiological research and public health both heavily rely on microbial behaviour or disease transmission [18, 19].

1.1.5 The role of deep learning.

Neural networks are used in deep learning, an advanced subfield of machine learning, to analyse large datasets.  Models for deep learning such as ARGs (deep antibiotic resistance genes) [18], which are utilized in microbiology to predict antibiotic resistance genes, which helps with environmental monitoring [30].

1.1.6 ML in Microbial data analysis and Predictive Modelling.

Significant quantities of microbiological Data processing is possible.  and analyse a machine learning. Its application to predictive modelling, specifically for predicting patterns microbial behaviour or the transmission of illness, is essential to microbiological research and public health. [18,22].

1.1.7 Challenges in ML for microbiology.

There are difficulties when using machine learning in microbiology, especially when it comes to The amount and calibers of information. Large, varied Datasets are necessary for reliable instruction and prediction of effective machine learning models [11]. Predictive machine learning models can also have certain disadvantages. For example, because training data may contain bias that influences outcomes, it may be challenging to identify and minimize bise in AI models used for microbiological applications, Inadequately structure detraining data may contain bias that influences outcomes, it may be challenging to identify and minimize bias in AI models used for microbiological applications. Inadequately structured datasets for training machine learning models and the availability of low quality microbiological data [23]. with data management arise form the digitization of microbial diagnostic processes and include collecting, guaranteeing quality, storing, and safeguarding data. Future developments in AI and ML in microbiology will likely include more in-depth conversation and potentially new regulations pertaining to patient authorization, data protection, and ethical concerns. [24]. Furthermore, laws and regulations are lagging behind scientific advancements in area like genome editing and synthetic biology, which poses risks and uncertainties.  in addition to the few case studies, several among these technologies require an external data source in order to validate their specific algorithms in a medical scenario [25].

2. CURRENT DEVELOPMENTS AND APPLICATIONS OF AI IN MICROBIOLOGY.

2.1 Developments in Clinical Diagnosis and Illness Identification.

A revolution in medical microbiology is being brought about by artificial machine learning (ML) and artificial intelligence (AI), which offer quick and accurate diagnosis as well as treatments For contagious diseases. Machine learning (ML), for example approaches similar to convolutional neural network (CNNs) significantly increase the accuracy of computer-aided diagnostics (CADX) software. Identifying cells afflicted by malaria [26,27]. Similar techniques have improved the sensitivity of parasite detection in samples, outperforming convention human slide testing [28]. The capability of automated tools to analyses laboratory examples that are shows as images has transformed the identification of species and genera of bacteria. These technologies, they are crucial in a number of industries, including the food, veterinary, and medical sectors, identify bacterial based on their form, colour, and colony patterns [29,30].

2.2.1 Epidemiology and disease prognosis.

In epidemiology, machine learning (ML) models such as logistic regression (LR) as well as artificial ANNs, or neural networks, are utilized to forecast patient results for illnesses like Ebola is a viral illness. Instruments such as the Ebola Care app analyse test data and clinical symptoms to give medical professionals vital information for treatment decisions. [31]

2.2.2 Point-of-care (POC) diagnostics.

ML has a revolutionary effect on point-of-care (POC) diagnostics.  ML algorithms use routine test findings, such urine, to distinguish between positive and negative instances for diagnosing sexually transmitted illnesses like trichomoniasis [32]. This method works very well in environments with limited resources. Additionally, the creation of mobile microbiological laboratories has been made possible by advancements in smartphone technology, increasing accessibility to diagnoses. [33,35] Artificial intelligence (AI)-enabled diagnostic tools are being created more frequently In order to be utilized in the hospital, offering prompt outcomes that guide therapy choices without requiring a lot of laboratory processing.  These gadgets are especially useful in places with limited access to centralized lab facilities, including isolated or resource-constrained locations. For instance, at the bedside or in the field, AI-powered devices can do quick diagnostic tests for infectious diseases like COVID-19, TB, or malaria.  Healthcare professionals can start therapy right away because to these gadgets' ability to test samples, such blood or sputum, and offer precise results in a matter of minutes. By delivering top-notch ability to diagnose straight to patients, eliminating the need of referrals to specialist laboratories, and enhancing Gaining access to prompt Take care, AI-powered Diagnostics at the point of care have the ability to revolutionize the way medical care is delivered. [36]

2.2.3 Drug and vaccine discovery.

Finding novel chemicals and potential vaccines is made much easier with machine learning.  Its ability to speed up drug discovery has been demonstrated by its usage to examine data from open databases such as the Opportunistic Infection and Tuberculosis Therapeutics Database (Chem DB) for possible antiviral compounds against the human immunodeficiency virus (HIV) [37,38]. For Apicomplexan pathogens, silico vaccine candidate selection with ML classifiers has shown promise [39,41].

2.2.4 Antimicrobial resistance and outbreak prediction.

In order to comprehend and address antimicrobial resistance (AMR), ML, or machine learning is essential. This has been crucial detecting medication resistance in diseases like HIV and tuberculosis (TB), creating new opportunity for managing and predicting resistance [42,48]. Furthermore, ML has demonstrated its potential in real-time infection disease tracking by being used to forecast disease outbreak utilizing data form unconventional sources like social media and search engines [49,52].

2.2.5 Microbial ecology and forensics.

ML is used in microbial ecology to help comprehend the dynamics and interaction of microbial population. Ecosystem interaction have been predicted using methods such as random forest (RF) [53,54]. ML helps forensic microbiology analyse post-mortem microbiomes, which greatly advance both public health diagnostic and forensic science [51]

Figure 2 is a schematic picture that shows how deep learning algorithms are used to analyse microscopic photographs of microorganisms, with an emphasis on evaluating their geometric qualities and macroscopic similarities.

2.2.6 improving medical microbiology's efficiency and accuracy.

The contribution of AI to improving accuracy and productivity in medical microbiology is significant. Automatic susceptibility examinations and the pathogen identification simplify lab procedures while tackling the difficulties associated with manual processing of intricate data, such as pictures, spectra, and DNA-RNA sequences, particularly when staff members are present. shortage and complex analyses [55,56].

Applications of AI in microbiology are many and include:

  • Automatic blood culture interpretation of convolutional neural network (CNNs) is used to analyse gram stains [57].
  • Automation of culture plate image analysis increases time efficiency and sensitivity [58,60].
  • Developments in MALDI-TOF MS for AMR detection direct sample identification [61,65].
  • Predicting AMR by DNA sequence analysis using WGS and ML [66,67].

3. AI IN HEALTHCARE AND MICROBIAL DIAGNOSIS.

Through Natural language processing (NLP), deep learning, and machine learning (ML),  artificial intelligence (AI) plays a varied role in healthcare, including microbial diagnosis. It works especially well for onco-radiology and structure data processing form hospital labs [68]. NLP makes it easier to create and maintain electronic medical records (EMRs) and allows for the analysis of voice and text diagnose a variety of illnesses [69].Creating sophisticated algorithms for culture identification and improving the effectiveness of microbial culture analysis are two example of AI used in culture interpretation [70,71]. Methicillin-resistant staphylococcus aures (MRSA) identification and sophisticated culture analysis in urine samples are made possible by automated methods such as the independence and PhenoMatrix automated plate assessment system (APAS) [72,73]. Helps identify and treat drug-resistant infections early forecasting patterns of antimicrobial susceptibility [74]. AI’s incorporation into extensive laboratory operations is exemplified by solutions for complete laboratory automation, such as WASP Lab and Kiestra Total Laboratory Automation (TLA) [75].

3.3.1 Sepsis management.

models in which anticipate the start of sepsis in advance, outperforming traditional scoring techniques, demonstrate AI's critical role in sepsis early warning systems [76]. Regular clinical factors have been added to these models, enhancing the viability of predicting sepsis in a variety of contexts [77,80]. By using machine learning and big data- based on screening techniques that incorporate unstructured textual data for greater accuracy, AI has also improved the detection of sepsis [81,82]. Clinical research links early warning systems to lower mortality and shorter hospital stays, confirming AI's efficacy in managing sepsis [83]. AI also helps in subtyping sepsis by classifying several phenotypes with various clinical traits [84]. AI systems swiftly identify typical bacteria and fungi in pathogen identification and antimicrobial susceptibility testing, improving empirical antibiotic therapy [85]. With prediction models for urine production upon resuscitation and fluid reactivity, artificial intelligence (AI) models direct fluid resuscitation and management in the treatment of sepsis [86,87]. Frameworks for causal inference calculate the effects of treatments, enabling more individualized healthcare [88]. In the prediction of sepsis, AI models have dramatically decreased hospital stays and increased in-hospital death rates [89,90]. To validate these models and incorporate them into clinical practice, more study is necessary [91].

3.3.2 Advancing infection surveillance and control.

AI is enhancing the prevention and management of infections (IPC) By altering the monitoring of healthcare-associated infections (HAIs).  Its use in deciphering intricate datasets from electronic health records (EHRs) is essential for tracking infection patterns and assessing intervention tactics [92]. The application of deep learning to chest radiography for tuberculosis diagnosis exemplifies AI's role in identifying infections with implications for IPC [93]. In laboratories, improved microscopy and machine learning algorithms are used for targeted antimicrobial treatment and quick diagnosis [94,95] Even with AI’s revolutionary potential, finding high-quality datasets for model building continues to be difficult [96]. However, AI promises to have a significant effect on patient treatment plans as well as public health management, well as increase the effectiveness of infection surveillance.

3.3.3 AI in antibiotic discovery against MRSA.

The development of novel antibiotic to combat MRSA has been greatly aided by AI and ML applications in microbiology [97]. The identification of possible antibiotic candidates has hastened due to AI’s capacity to process and analyse large data sets (figure-3) using features calculated by RDKIT [98,99]. The study technique entails training, validating, and evaluating ML models. Performance is assessed using AUPRC [99]. AI's capacity to analyse and show the chemical space of a molecule, which aids in differentiating between antibiotic that are effective and those that are not [100,101] certain structural classes that show how antibiotics work are identified Using algorithms for deep learning and monte and searches [102,103]. The synergy between computational predications and conventional experimental approaches is highlighted by the rigorous experimental confirmation of AI-driven forecast. AI-guided research sheds light on the pharmacological characteristics, resistance mechanisms, and general effectiveness of the substance [104,109].

(Figure 3) Large databases are used in computer-aided drug design to sort through and find important pharmacological characteristics that affect a compound's functioning and effectiveness.

Regardless of the methods utilized, the collected data constitute the cornerstone for designing a suite of new chemicals. These new substances are put through a thorough testing process, and the findings give new information about their pharmacological characteristics. The compounds are refined through a series of steps in this recurrent cycle until a reliable scoring system produces potential antibiotic medicines. Following optimization, these candidates are critically assessed to look at their safety and effectiveness characteristics in vivo. then put through a rigorous assessment that looks at their safety and effectiveness characteristics in vivo.

4. ISSUES, DEVELOPMENTS, AND PATHS FOR MICROBIOLOGICAL APPLICATIONS OF AI AND ML.

A new era in prevention and management of infections (IPC) and diagnostic capacities is ushered in by the application of AI and ML in microbiology.  Nevertheless, in order to fully utilize their potential, these limits and difficulties must be resolved.

4.4.1 Data quality and algorithm challenges.

The effectiveness of training data determines how well ML algorithms work in microbiology.  Due to data sources' frequent imperfections and potential for noise introduction, obtaining high-quality data is a constant struggle. It is anticipated that sophisticated data cleaning and normalization methods will lessen problems associated with noisy and imbalanced data.  Future developments will probably concentrate on creating strategies to raise the effectiveness of training information and increase the algorithms' capacity to be generalized. Furthermore, XAI, or explainable AI initiatives seek To develop additional visible and interpretable models of in order to increase user trust [110].

4.4.2 AI in IPC: Challenges and Prospective Evaluation.

AI has several benefits for IPC, including the ability to handle big datasets and produce reliable results.  However, there are issues with AI's reliance on high-quality data and the lack of strong reference standards in IPC.  In order to guarantee clinical relevance and sensitivity to the subtleties of healthcare data, future directions include carrying out more prospective investigations in clinical settings and establishing strong frameworks for collaboration between AI developers and IPC specialists [111,113].

4.4.3 AI models' clinical integration and universal application.

A hurdle is The restricted adoption of Medical AI experts because of Its intricate reasoning and incompatibility with traditional medical logic. The upcoming trends include creating AI simulations that can oneself -update along with adjust to various medical care settings, increasing their applicability and efficiency.  Through education and alignment with medical thinking, efforts will be made to increase healthcare professionals' adoption of AI [114,120].

4.4.4 Digitalization in diagnostic processes.

The digitization of microbiology diagnostic procedures presents data management issues with regard to security, storage, quality assurance, and collection.  With a growing emphasis on handling the deluge of data using cutting-edge analytics tools and complex data visualization strategies, the trend toward digitalization will continue.  Another important trend is the training of laboratory staff in digital skills for efficient management and analysis of this data [121,128].

Figure 4: Management of infectious illnesses and AI.

4.4.5 Legal and ethical considerations.

Microbiology data must be collected, analysed, and shared in accordance Considering legal and regulatory regulations, such as Europe's General Data Protection Regulation, or GDPR. More in-depth conversations and possibly new laws pertaining to patient consent, ethical issues, and data protection With relation to AI and ML in microbiology will be discussed in the future.  It is crucial to define universal standards for data exchange and usage, informed by ideas like FAIR, and to harmonize legal frameworks [129,132].

4.4.6 uses of machine learning in microbiological labs.

In microbiology labs, Machine learning is able to greatly improve The diagnostic procedure.  Algorithm integration across From pre-analytics to post-analytics, the diagnostic procedure will be the main focus of future developments in machine learning applications.  The focus will be on developing algorithms capable of deciphering intricate interactions within bacterial networks and offering subtle insights on pathogenicity and microbial resistance [133,140].

4.4.7 Artificial neural network (ANN) and Deep learning (DL).

The algorithmic system known as artificial neural networks (ANN) functions similarly to organic neurons.  It consists of an output-generating function (similar to an axon), an activation function applied to the sum of weighted input vectors (similar to a cell body), and an input vector of numerical values multiplied by weights (similar to dendrites in a neuron).  Multiple hidden layers are added to the neural network model in order to handle a complex problem [141]. Growing or lowering how many nodes there are in the intermediate levels (also known as concealed layers) may increase or decrease the data size.  Therefore, huge data can be subjected to classification analysis.  The use of a multi-layered neural network modelling technique is known as deep learning (DL). When gathering and disseminating data, there are crucial factors to take into account; Data developers are required to make sure patients are informed and that their consent is acquired. consider the numerous national and international regulations that safeguard the confidentiality of medical records [142].

5. INFECTION DISEASE DIAGNOSIS AND DISEASE PREVENTION.

Clinicians use artificial intelligence to help them make clinical decisions.  It is possible to predict Using data, determine which hematological patients with febrile neutropenia will develop infections caused by multidrug-resistant Gram-negative bacteria (MDR-GNB). gathered from electronic health records (EHRs).  EHR benefits include quicker access to test findings and medical care, as well as central storage of all patient data.  Numerous factors, including the patient's microbiota state, hospital environment, and history of antibiotic treatment, are linked to the likelihood of acquiring a multidrug-resistant infection (143). Artificial AI initiatives for infectious illness early detection.

Figure 5. AI and infectious diseases management.

Figure.6 Potential future advancements of AI in Microbiology

Figure 7. Guide Artificial Intelligence (AI) against Automation: Although automation increases productivity, it necessitates modifications to the laboratory's infrastructure and a change in the requirements for employee training.

New diagnostic and prognostic models will be created by applying AI to huge clinical datasets produced by increased automation. The move to individualized medicine will be made possible by automation and artificial intelligence.

6. Digital Microbiology

As Topol said in 2019, the arrival of digitalization and AI has raised expectation in the healthcare business [141]. Theses expectations are mostly driven by the increased focus on cost reduction and quality optimization. But it’s important to understand that the full advantages of digitization will only be achieved by significantly improving healthcare procedure, especially with regard to quality improvement. As highlighted by Dolen et al. in 2017 this cells for an increased need for high quality digital laboratory data, including microbiological information in diagnoses [142].

Figure: 9. Mencacci A, De Socio GV, Pirelli E, Bondi P, Cenci E. Laboratory automation, informatics, and artificial intelligence: present and future views in clinical microbiology. Effects of automation on laboratory, patient, and hospital administration. Microbiol Front Cell Infection. PMID: 37441239; PMCID: PMC10333692. doi: 10.3389/fcimb.2023.1188684. 2023 Jun 27;13:1188684

7. Artificial intelligence, informatics, and laboratory automation

The automation of the complete diagnostic process, including agar plate inoculation, incubation, reading of culture findings, identification (ID), and antimicrobial susceptibility testing (AST), is referred to as "Total Laboratory Automation" (TLA) in clinical microbiology.  In a conventional laboratory, each of these procedures is typically carried out by hand using a sample-centric methodology.  There are currently Two methods for laboratory automation (LA) on the market: Copan Diagnostics' WASPLAB system Murrieta, CA as well as the BD KiestraTM Becton Dickinson's system Sparks, MD) [143].

CONCLUSION

A revolutionary change in biomedical research and clinical practice is represented by the incorporation of AI and ML in microbiology.  Numerous uses for these technologies have been revealed by this investigation, ranging from improving clinical microbiology diagnostic accuracy to leading the way in drug discovery and improving public health management.  Significant progress has been made in pathogen identification, antibiotic resistance prediction, and infectious disease management thanks to AI's capacity to process and evaluate complicated biological data.  Notwithstanding these developments, issues including algorithmic constraints, data quality, and ethical considerations continue to be significant.  AI models that are flexible, interpretable, and can be easily incorporated into clinical settings are desperately needed in order to match computing power with medical knowledge and moral principles. Imagine a time in the future when microbiological research and practice are heavily reliant on AI and ML.  It is essential to construct self-updating, flexible AI models that can operate in a variety of medical environments. Furthermore, healthcare workers will need greater education and training in AI-based technologies to include AI into medical procedures. To sum up, ML and AI have the power to completely microbiology and present previously unheard-of chances to enhance public health and patient care results.  For AI and ML to dramatically improve healthcare and usher in a new era of precision medicine in microbiology, it is imperative that present issues be addressed and future advancements be prioritized.

REFERENCES

  1. Maraz KM, Khan RA. An overview on impact and application of microorganisms on human health, medicine and environment. GSC Biolpharm Sci. 2021;16:89-104.
  2. Karalis VD. The integration of artificial intelligence into clinical practice. Appl Biosci. 2024;3(1):14–44. doi: 10.3390/applbiosci3010002.
  3. Juhas M. Artificial intelligence in microbiology. In Brief lessons in microbiology. cham: Springer; 2023. doi: 10.1007/978-3-031-29544-7_8.
  4. Mishra A, Khan S, Das A, et al. Evolution of diagnostic and forensic microbiology in the era of artificial intelligence. cureus. 2023;15(9):e45738. doi: 10.7759/cureus.45738.
  5. Wilson S, Steele S, Adeli K. Innovative technological advancements in laboratory medicine: predicting the lab of the future. Biotechnol Biotechonal Equip. 2022;36(supl):S9 S21. doi: 10.1080/13102818.2021.2011413.
  6. Signoroni A, Ferrari A, Lombardi S, et al. hierarchical AI enables global interpretation of culture plates in the era of digital microbiology. Nat commun. 2023;14(1): 6874. doi: 10.1038/s41467-023-42563-1.
  7. Sarrafzadeh M-h, Mansouri SS, Zahiri J, et al. Artificial intelligence in environmental microbiology. Front Microbiol. 2022;13:944242. doi: 10.3389/fmicb.2022.944242.
  8. Jiang Y, Luo J, huang D, et al. Machine learning advanc es in microbiology: a review of methods and applications. Front Microbiol. 2022;13:925454. doi: 10.3389/ fmicb.2022.925454.
  9. Saheb T, Saheb T, carpenter DO. Mapping research strands of ethics of artificial intelligence in healthcare: a bibliometric and content analysis. comput Biol Med. 2021;135:104660. doi: 104660. 10.1016/j.compbiomed.2021.
  10. Kavvas ES, catoiu E, Mih N, et al. Machine learning and structural analysis of Mycobacterium tuberculosis pan-genome identifies genetic signatures of antibiotic resistance. Nat commun. 2018;9(1):4306. doi: 10.1038/ s41467-018-06634-y.
  11. Davis J, Boisvert S, Brettin T, et al. Antimicrobial resistance prediction in PATRIc and RAST. Sci Rep. 2016;6(1):27930. doi: 10.1038/srep27930.
  12. Freund Y, Schapire RE. A decision-theoretic generalization of on-line learning and an application to boosting. J comput Syst Sci. 1997;55(1):119–139. doi: 10.1006/ jcss.1997.1504
  13. Aniro g, et al. Variability of strain engraftment and predictability of microbiome composition after fecal microbiota transplantation across different diseases. Nat Med. 2022;28:1913–1923.
  14. Smillie CS, Sauk J, gevers D, et al. Strain tracking reveals the determinants of bacterial engraftment in the human gut following fecal microbiota transplantation. cell host Microbe. 2018;23(2):229–240.e5. doi: 10.1016/j. chom.2018.01.003.
  15. Schmidt TSB, Li SS, Maistrenko OM, et al. Drivers and determinants of strain dynamics following fecal microbiota transplantation. Nat Med. 2022;28(9):1902–1912. doi: 10.1038/s41591-022-01913-0.
  16. Signoroni A, Ferrari A, Lombardi S, et al. hierarchical AI enables global interpretation of culture plates in the era of digital microbiology. Nat commun. 2023;14(1): 6874. doi: 10.1038/s41467-023-42563-1.
  17. Sarrafzadeh M-h, Mansouri SS, Zahiri J, et al. Artificial intelligence in environmental microbiology. Front Microbiol. 2022;13:944242. doi: 10.3389/fmicb.2022.944242.
  18. Jiang Y, Luo J, huang D, et al. Machine learning advances in microbiology: a review of methods and applications. Front Microbiol. 2022;13:925454. doi: 10.3389/ fmicb.2022.925454.
  19. Saheb T, Saheb T, carpenter DO. Mapping research strands of ethics of artificial intelligence in healthcare: a bibliometric and content analysis. comput Biol Med. 2021;135:104660. doi: 10.1016/j.compbiomed.2021. 104660.
  20. Kavvas ES, catoiu E, Mih N, et al. Machine learning and structural analysis of Mycobacterium tuberculosis pan-genome identifies genetic signatures of antibiotic resistance. Nat commun. 2018;9(1):4306. doi: 10.1038/ s41467-018-06634-y.
  21. Davis J, Boisvert S, Brettin T, et al. Antimicrobial resistance prediction in pATRIc and RAST. Sci Rep. 2016;6(1):27930. doi: 10.1038/srep27930.
  22. Freund Y, Schapire RE. A decision-theoretic generalization of on-line learning and an application to boosting. J comput Syst Sci. 1997;55(1):119–139. doi: 10.1006/ jcss.1997.1504
  23. Aniro g, et al. Variability of strain engraftment and predictability of microbiome composition after fecal microbiota transplantation across different diseases. Nat Med. 2022;28:1913–1923.
  24. Smillie CS, Sauk J, gevers D, et al. Strain tracking reveals the determinants of bacterial engraftment in the human gut following fecal microbiota transplantation. cell host Microbe. 2018;23(2):229–240.e5. doi: 10.1016/j. chom.2018.01.003.
  25. Schmidt TSB, Li SS, Maistrenko OM, et al. Drivers and determinants of strain dynamics following fecal microbiota transplantation. Nat Med. 2022;28(9):1902–1912. doi: 10.1038/s41591-022-01913-0.
  26. Steinegger M, Söding J. MMseqs2 enables sensitive protein sequence searching for the analysis of massive data sets. Nat Biotechnol. 2017;35(11):1026–1028. doi: 10.1038/nbt.3988.
  27. Vanni c, Schechter MS, Acinas Sg, et al. Unifying the known and unknown microbial coding sequence space. Elife. 2022;11:e67667. doi: 10.7554/eLife.67667.
  28. Arango-Argoty g, garner E, pruden A, et al. DeepARg: a deep learning approach for predicting antibiotic resistance genes from metagenomic data. Microbiome. 2018;6(1):23. doi: 10.1186/s40168-018-0401-z.
  29. Baldi p. Deep learning in biomedical data science. Annu Rev Biomed Data Sci. 2018;1(1):181–205. doi: 10.1146/ annurev-biodatasci-080917-013343.
  30. Henry KE, Kornfield R, Sridharan A, Linton RC, Groh C, Wang T, et al. Human-machine teaming is key to AI adoption: Clinicians’ experiences with a deployed machine learning system. NPJ Digit Med. 2022;5(1):97. doi:10.1038/s41746-022-00597-7.
  31. Rajaraman S, Antani SK, poostchi M, et al. pre-trained convolutional neural networks as feature extractors toward improved malaria parasite detection in thin blood smear images. peerJ. 2018;6:e4568. doi: 10.7717/peerj.4568.
  32. Baldi p. Deep learning in biomedical data science. Annu Rev Biomed Data Sci. 2018;1(1):181–205. doi: 10.1146/ annurev-biodatasci-080917-013343.
  33. Mohseni P, Ghorbani A. Exploring the synergy of artificial intelligence in microbiology: Advancements, challenges, and future prospects. Comput Struct Biotechnol Rep. 2024;1:100005. doi:10.1016/j.csbr.2024.100005.
  34. Miller S, Chiu C, Rodino KG, Miller MB. Point-Counterpoint: Should We Be Performing Metagenomic Next- Generation Sequencing for Infectious Disease Diagnosis in the Clinical Laboratory? J Clin Microbiol. 2020;58(3):e01739-19. doi:10.1128/jcm.01739-19
  35. Ghosh D, Chakraborty S, Kodamana H, Chakraborty S. Application of machine learning in understanding plant virus pathogenesis: Trends and perspectives on emergence, diagnosis, host-virus interplay and management. Virol J. 2022;19(1):42. doi:10.1186/s12985-022-01767-5.
  36. Ross NE, pritchard cJ, Rubin DM, et al. Automated image processing method for the diagnosis and classification of malaria on thin blood smears. Med Biol Eng comput. 2006;44(5):427–436. doi: 10.1007/s11517-006-0044-2.
  37. Poostchi M, Silamut K, Maude RJ, et al. Image analysis and machine learning for detecting malaria. Transl Res. 2018;194:36–55. doi: 10.1016/j.trsl.2017.12.004.
  38. Mathison BA, Kohan JL, Walker JF, et al. Detection of intestinal protozoa in Trichrome-Stained stool specimens by use of a deep convolutional neural network. J clin Microbiol. 2020;58(6). doi: 10.1128/JcM.02053-19.
  39. Forero Mg, cristóbal g, Desco M. Automatic identification of Mycobacterium tuberculosis by gaussian mixture models. J Microsc. 2006;223(pt 2):120–132. doi: 10.1111/j.1365-2818.2006.01610.x.
  40. Zieli?ski B, plichta A, Misztal K, et al. Deep learning approach to bacterial colony classification. pLoS One. 2017;12(9):e0184554. doi: 10.1371/journal.pone.018.
  41. colubri A, Silver T, Fradet T, et al. Transforming clinical data into actionable prognosis models: machine learning frame-work and field-deployable app to predict outcome of Ebola patients. pLoS Negl Trop Dis. 2016;10(3):e0004549. doi:
  42. Wang hY, hung cc, chen ch, et al. Increase Trichomonas vaginalis detection based on urine routine analysis through a machine learning approach. Sci Rep. 2019;9(1):11074. doi: 10.1038/s41598-019-47361-8.
  43. pirnstill cW, coté gL. Malaria diagnosis using a mobile phone polarized microscope. Sci Rep. 2015;5(1):13368. doi: 10.1038/srep13368.
  44. Diederich B, Wartmann R, Schadwinkel h, et al. Using machine-learning to optimize phase contrast in a low-cost cellphone microscope. pLoS One. 2018;13(3): e0192937. doi: 10.1371/journal.pone.0192937.
  45. Ong DSY, poljak M. Smartphones as mobile microbiological laboratories. clin Microbiol Infect. 2020;26(4):421–424. doi: 10.1016/j.cmi.2019.09.026.
  46. Ouyang Y, Yuan Y, Zhang L, Chen Q, Li J. AI- powered diagnostic tools in microbiology: Revolutionizing the detection and identification of pathogens. Frontiers in Microbiology. 2023;14:1057923. doi:10.3389/fmicb.2023.1057923.
  47. Zorn KM, Lane TR, Russo Dp, et al. Multiple machine learning comparisons of hIV cell-based 10.1021/acs.molpharmaceut.8b01297 and reverse transcriptase data sets. Mol pharm. 2019;16(4):1620–1632. doi:.
  48. Svarovskaia ES, cheslock SR, Zhang Wh, et al. Retroviral mutation rates and reverse transcriptase fidelity. Front Bioscience-Landmark. 2003;8:d117–d134.
  49. goodswen SJ, Kennedy pJ, Ellis JT. A novel strategy for classifying the output from an insilico vaccine discovery pipeline for eukaryotic pathogens using machine learning algorithms. BMc Bioinformatics. 2013;14(1):315. doi: 10.1186/1471-2105-14-315.
  50. Verma R, Tiwari A, Kaur S, et al. Identification of proteins secreted by malaria parasite into erythrocyte usteins secreted by malaria parasite into erythrocyte using SVM and pSSM profiles. BMc Bioinformatics. 2008;9(1):201. doi: 10.1186/1471-2105-9-201.
  51. Rahman MS, Rahman MK, Saha S, et al. Antigenic: an improved prediction model of protective antigens. ArtifIntell Med. 2019;94:28–41. doi: 10.1016/j.artmed.2018.12.010.
  52. Zhang hT, Li DF, Zhao LL, et al. genome sequencing of161 Mycobacterium tuberculosis isolates from china identifies genes and intergenic regions associated with drug resistance. Nat genet. 2013;45(10):1255–1260. doi: 10.1038/ng.2735.
  53. Walker TM, Kohl TA, Omar SV. Whole-genome sequencing for prediction of Mycobacterium tuberculosis drug susceptibility and resistance: a retrospective cohort study. Lancet Infect Dis. 2018;18:21–21.
  54. Yang Y, Niehaus KE, Walker TM, et al. Machine learning for classifying tuberculosis drug-resistance from DNA sequencing data. Bioinformatics. 2018;34(10):1666–1671. doi: 10.1093/bioinformatics/btx801.
  55. Kouchaki S, Yang Y, Walker TM, et al. Application of machine learning techniques to tuberculosis drug resistance analysis. Bioinformatics. 2019;35(13):2276–2282. doi: 10.1093/bioinformatics/bty949.
  56. Farhat MR, Sultana R, Iartchouk O, et al. genetic determinants of drug resistance in Mycobacterium tuberculosis and their diagnostic value. Am J Respir crit care Med. 2016;194:621–630. doi: 10.1164/rccm.201510-2091Oc.
  57. Iyidogan p, Anderson KS. current perspectives on hIV-1 antiretroviral drug resistance. Viruses–Basel. 2014;6(10): 4095–4139. doi: 10.3390/v6104095.
  58. Ramon E, Belanche-Muñoz L, pérez-Enciso M. hIV drug resistance prediction with weighted categorical kernel functions. BMc Bioinformatics. 2019;20(1):410. doi: 10.1186/s12859-019-2991-2.
  59. peng Y, Li c, Rong Y, et al. Retrospective analysis of the accuracy of predicting the alert level of cOVID-19 in202 countries using google trends and machine learning. J glob health. 2020;10(2):020511. doi: 10.7189/ ing. J glob health. 2020;10(2):020511. doi: 10.7189/ jogh.10.020511.
  60. ginsberg J, Mohebbi Mh, patel RS, et al. Detecting influenza epidemics using search engine query data. Nature. 2009;457(7232):1012–1014. doi: 10.1038/na- ture07634.
  61. Shin S-Y, Seo D-W, AnJ, et al. high correlation of Middle East respiratory syndrome spread with google search and twitter trends in Korea. Sci Rep. 2016;6(1):32920. doi: 10.1038/srep32920
  62. Marques-Toledo c, Degener cM, Vinhal L, et al. Dengue prediction by the web: tweets are a useful tool for estimating and forecasting dengue at country and cityslevel. pLoS Negl Trop Dis. 2017;11.
  63. DiMucci D, Kon M, Segrè D. Machine learning reveals missing edges and putative interaction mechanisms in microbial ecosystem networks. Msystems. 2018;3(5): 10-1128. doi: 10.1128/mSystems.00181-18.
  64. Zhang Y, pechal JL, Schmidt CJ, et al. Machine learning performance in a microbial molecular autopsy context: a cross-sectional postmortem human population study. pLoS One. 2019;14(4):e0213829. doi: 10.1371/journal. pone.0213829.
  65. garcia E, Kundu I, Ali A, et al. The American society for clinical pathology’s 2016-2017 vacancy survey of medical laboratories in the United States. Am J clin pathol. 2018;149(5):387–400. doi: 10.1093/ajcp/aqy005.
  66. Smith Kp, Kang AD, Kirby JE. Automated interpretation of blood culture gram stains by use of a deep convolutional neural network. J clin Microbiol. 2018;56(3): e01521-17. doi: 10.1128/JcM.01521-17
  67. glasson J, hill R, Summerford M, et al. Multicenter evaluation of an image analysis device (ApAS): comparison between digital image and traditional plate reading using urine cultures. Ann Lab Med. 2017;37(6):499–504. doi: 10.3343/alm.2017.37.6.499.
  68. Faron ML, Buchan BW, Samra h, et al. Evaluation of the WASpLab software to automatically read chROMID CPS elite agar for reporting of urine cultures. J clin Microbiol. 2019;58(1). doi: 10.1128/JcM.00540-19.
  69. Van TT, Mata K, Dien Bard J. Automated detection of Streptococcus pyogenes pharyngitis by use of colorex strep a chROMagar and WASpLab artificial intelligence chromogenic detection module software. J clin Microbiol. 2019;57(11). doi: 10.1128/JcM.00811-19.
  70. Florio W, Tavanti A, Barnini S, et al. Recent advances and ongoing challenges in the diagnosis of microbial infections by MALDI-TOF mass spectrometry. Front Microbiol. 2018;9:1097. doi: 10.3389/fmicb.2018.0109.
  71. Datta S. Mass spectrometry data analysis in proteomics. 2nd ed. Berlin: Springer; 2013. chapter.10: feature selection and machine learning with mass spectrometry data.
  72. Wang h-Y, chen c-h, Lee T-Y, et al. Rapid detection of heterogeneous vancomycin-intermediate Staphylococcus aureus based on matrix-assisted laser desorption ionization time-of-flight: using a machine learning approach and unbiased validation. Front Microbiol. 2018;9:2393. doi: 10.3389/fmicb.2018.02393.
  73. Mather cA, Werth BJ, Sivagnanam S, et al. Rapid detection of vancomycin-intermediate Staphylococcus aureus by matrix-assisted laser desorption ionization-time of flight mass spectrometry. J clin Microbiol. 2016;54(4): 883–890. doi: 10.1128/JcM.02428-15.
  74. Lau AF, Walchak Rc, Miller hB, et al. Multicenter study demonstrates standardization requirements for mold identification by MALDI-TOF MS. Front Microbiol. 2019;10:2098. doi: 10.3389/fmicb.2019.02098.
  75. Long SW, Olsen RJ, Eagar TN, et al. population genomic analysis of 1,777 extended-spectrum beta-lactamase-pro- analysis of 1,777 extended-spectrum beta-lactamase-pro- ducing Klebsiella pneumoniae isolates, houston, Texas: unexpected abundance of clonal group 2017;307. MBio. 2017;8(3). doi: 10.1128/mBio.00489-17.
  76. Nguyen M, Long SW, McDermott pF, et al. Using machine learning to predict antimicrobial MIcs and associated genomic features for nontyphoidal Salmonella. J clin Microbiol. JcM.01260-18.2019;57(2):e01260-18. doi: 10.1128/ JcM.01260-18.
  77. Zhang W, he S, hong W, et al. A review of Raman-based technologies for bacterial identification and antimicrobial susceptibility testing. photonics. 2022;9(3):133. doi: 10.3390/photonics9030133.
  78. Undru TR, Uday U, Lakshmi JT, et al. Integrating artificial intelligence for clinical and laboratory diagnosis - a review. Maedica (Bucur). 2022;17(2):420–426.
  79. ghaffar Nia N, Kaplanoglu E, Nasab A. Evaluation of artificial intelligence techniques in disease diagnosis and prediction. Discover Artif Intell. 2023;10(5). doi: 10.1007/ s44163-023-00049-5.
  80. Rahmani AM, Azhir E, Ali S, et al. Artificial intelligence approaches and mechanisms for big data analytics: a systematic study. peerJ comput Sci. 2021;7:e488. doi: 10.7717/peerj-cs.488.
  81. Rhoads DD. computer vision and artificial intelligence are emerging diagnostic tools for the clinical microbiologist. J clin Microbiol. 2020;58(6). doi: 10.1128/JcM.00511-20.
  82. DeYoung B, Morales M, giglio S. Microbiology 2.0-a “behind the scenes” consideration for artificial intelligence applications for interpretive culture plate reading in routine diagnostic laboratories. Front Microbiol. 2022;13:976068. doi: 10.3389/fmicb.2022.976068.
  83. Alouani DJ, Ransom EM, Jani M, et al. Deep convolutional neural networks implementation for the analysis of urine culture. clin chem. 2022;68(4):574–583. doi: 10.1093/clinchem/hvab270.
  84. peiffer-Smadja N, Dellière S, Rodriguez c, et al. Machine learning in the clinical microbiology laboratory: has the time come for routine practice? clin Microbiol Infect. 2020;26(10):1300–1309. doi: 10.1016/j.cmi.2020.02.006.
  85. croxatto A, prod’hom g, Faverjon F, et al. Laboratory automation in clinical bacteriology: what system to choose? clin Microbiol Infect. 2016;22(3):217–235. doi: 10.1016/j.cmi.2015.09.030.
  86. slam MM, Nasrin T, Walther BA, et al. prediction of sepsis patients using machine learning approach: a meta-analysis. comput Methods programs Biomed. 2019;170:1–9. doi: 10.1016/j.cmpb.2018.12.027.
  87. Wang D, Li J, Sun Y, et al. A machine learning model for accurate prediction of sepsis in IcU patients. Front public health. 2021;9. doi: 10.3389/fpubh.2021;754348.
  88. Fleuren LM, Klausch TLT, Zwager cL, et al. Machine learning for the prediction of sepsis: a systematic review and meta-analysis of diagnostic test accuracy. Intensive care Med. 2020;46(3):383–400. doi: 10.1007/ s00134-019-05872-y.
  89. Lauritsen SM, Kalør ME, Kongsgaard EL, et al. Early detection of sepsis utilizing deep learning on electronic health record event sequences. Artif Intell Med. 2020;104:101820. doi: 10.1016/j.artmed.2020.101820.
  90. Shashikumar Sp, Wardi g, Malhotra A, et al. Artificial intelligence sepsis prediction algorithm learns to say “I don’t know. NPJ Digit Med. 2021;4(1):134. doi: 10.1038/ s41746-021-00504-6.
  91. Delahanty RJ, Alvarez J, Flynn LM, et al. Development and evaluation of a machine learning model for the early identification of patients at risk for sepsis. AnnEmerg Med. 2019;73(4):334–344. doi: 10.1016/j. annemergmed.2018.11.036
  92. GOH, Kh, Wang L, Yeow AYK, et al. Artificial intelligence in sepsis early prediction and diagnosis using unstructured data in healthcare. Nat commun. 2021;12(1):711. doi: 10.1038/s41467-021-20910-4.
  93. Adams R, henry KE, Sridharan A, et al. prospective, multi-site study of patient outcomes after implementation of the TREWS machine learning-based early warning system for sepsis. Nat Med. 2022;28(7):1455–1460. doi: 10.1038/s41591-022-01894-0.
  94. Seymour CW, Kennedy JN, Wang S, et al. Derivation, validation, and potential treatment implications of novel clinical phenotypes for sepsis. JAMA. 2019; 321(20):2003–2017. doi: 10.1001/jama.2019.5791.
  95. HO C-S, Jean N, hogan CA, et al. Rapid identification of pathogenic bacteria using Raman spectroscopy and deep learning. Nat commun. 2019;10(1):4927. doi: 10.1038/s41467-019-12898-9.
  96. Lin p-c, huang h-c, Komorowski M, et al. A machine learning approach for predicting urine output after fluid administration. comput Methods programs Biomed. 2019;177:155–159. doi: 10.1016/j.cmpb.2019.05.009.
  97. Bataille B, Selle J, Moussot p-E, et al. Machine learning methods to improve bedside fluid responsiveness prediction in severe sepsis or septic shock: an observation- al study. Br J Anaesth. 2021;126(4):826–834. doi: 10.1016/j.bja.2020.11.039.
  98. Liu R, hunold KM, caterino JM, et al. Estimating treatment effects for time-to-treatment antibiotic steward- ship in sepsis. Nat Mach Intell. 2023;5(4):421–431. doi: 10.1038/s42256-023-00638-0.
  99. Shimabukuro DW, Barton CW, Feldman MD, et al. Effect of a machine learning-based severe sepsis prediction algorithm on patient survival and hospital length of stay: a randomised clinical trial. BMJ Open Respir Res. 2017;4(1):e000234. doi: 10.1136/bmjresp-2017-000234.
  100. HOU N, Li M, he L, et al. predicting 30-days mortality for MIMIc-III patients with sepsis-3: a machine learning approach using Xgboost. J Transl Med. 2020;18(1):462. doi: 10.1186/s12967-020-02620-5.
  101. Yin J, Ngiam KY, Teo hh. Role of artificial intelligence applications in real-life clinical practice: systematic review. J Med Internet Res. 2021;23(4):e25759. doi: 10.2196/25759.
  102. cusumano-Towner M, Li DY, Tuo S, et al. A social network of hospital acquired infection built from electronic medical record data. J Am Med Inform Assoc. 2013;20(3):427–434. doi: 10.1136/amiajnl-2012-001401.
  103. Lakhani p, Sundaram B. Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks. Radiology. 2017;284(2):574–582. doi: 10.1148/radiol.2017162326.
  104. Méric g, Mageiros L, pensar J, et al. Disease- associated genotypes of the commensal skin bacterium Staphylococcus epidermidis. Nat commun. 2018;9(1):5034. doi: 10.1038/s41467-018-07368-7.
  105. Drew RJ, Murphy T, Broderick D, et al. An interpretation algorithm for molecular diagnosis of bacterial vaginosis in a maternity hospital using machine learning: proof-of-con- cept study. Diagn Microbiol Infect Dis. 2020;96(2):114950. doi: 10.1016/j.diagmicrobio.2019.114950.[96].
  106. Shillan D, Sterne JAC, champneys A, et al. Use of machine learning to analyse routinely collected intensive care unit data: a systematic review. crit care. 2019;23(1):284. doi: 10.1186/s13054-019-2564-9
  107. Lee AS, de Lencastre h, garau J, et al. Methicillin-resistant Staphylococcus aureus. Nat Rev Dis primers. 20018; 4(1):18033. doi: 10.1038/nrdp.2018.33
  108. gilmer J, et al. Neural message passing for quantum chemistry. In proceedings of the 34th International conference on Machine Learning 2017
  109. Yang K, Swanson K, Jin W, et al. Analyzing learned molecular representations for property prediction. J chem Inf Model. 2019;59(8):3370–3388. doi: 10.1021/acs. jcim.9b00237
  110. Toxicology in the 21st century. [cited 2022 Oct 20]. Available from: https://tripod.nih.gov/tox/.
  111. The human Metabolome Database. [cited 2022 Oct 20]. Available from: https://hmdb.ca/metabolites.
  112. Silver D, Schrittwieser J, Simonyan K, et al. Mastering the game of go without human knowledge. Nature. 2017;550(7676):354–359. doi: 10.1038/nature24270.
  113. cao Y, Jiang T, girke T. A maximum common substructure-based algorithm for searching and predicting drug-like compounds. Bioinformatics. 2018;24(13):i366– i374. doi: 10.1093/bioinformatics/btn186
  114. Stokes JM, Yang K, Swanson K, et al. A deep learning approach to antibiotic discovery. cell. 2020;180(4):688–702.e13. doi: 10.1016/j.cell.2020.01.021.
  115. Wong F, Stokes JM, Bening Sc, et al. Reactive metabolic byproducts contribute to antibiotic lethality under anaerobic conditions. Mol cell. 2020;82(18):3499–3512. e10. doi: 10.1016/j.molcel.2022.07.009.
  116. Wong F, Stokes JM, cervantes B, et al. cytoplasmic condensation induced by membrane damage is associated with antibiotic lethality. Nat commun. 2021;12(1):2321. doi: 10.1038/s41467-021-22485-6.
  117. Wong F, Wilson S, helbig R, et al. Understanding beta-lactam-induced lysis at the single-cell level. Front Microbiol. 2021;12:712007. doi: 10.3389/fmicb.2021. 712007.
  118. Wong F, Amir A. Mechanics and dynamics of bacterial cell lysis. Biophys J. 2019;116(12):2378–2389. doi: 10.1016/j.bpj.2019.04.040.
  119. Wu Y, gadsden SA. Machine learning algorithms in microbial classification: a comparative analysis. Front Artif Intell. 2023;6:1200994. doi: 10.3389/frai.2023.1200994
  120. Wu Y, gadsden SA. Machine learning algorithms in mi- crobial classification: a comparative analysis. Front Artif Intell. 2023;6:1200994. doi: 10.3389/frai.2023.1200994
  121. Farha MA, Verschoor cp, Bowdish D, et al. collapsing the proton motive force to identify synergistic combinations against Staphylococcus aureus. chem Biol. 2013;20(9):1168–1178. doi: 10.1016/j.chembiol.2013.07.006.
  122. Scott IA, cook D, coiera EW, et al. Machine learning in clinical practice: prospects and pitfalls. Med J Aust. 2019;211(5):203–205.e1. doi: 10.5694/mja2.50294.
  123. Rajkomar A, Dean J, Kohane I. Machine learning in medicine. N Engl J Med. 2019;380(14):1347–1358. doi: 10.1056/NEJMra1814259
  124. panch T, Mattie h, celi LA. The “inconvenient truth” about AI in healthcare. NpJ Digit Med. 2019;2(1):77. doi: 10.1038/s41746-019-0155-4.
  125. Finlayson Sg, Subbaswamy A, Singh K, et al. The clinician and dataset shift in artificial intelligence. N Engl J Med. 2021;385(3):283–286. doi: 10.1056/NEJMc2104626.
  126. Wong A, Otles E, Donnelly Jp, et al. External validation of a widely implemented proprietary sepsis prediction model in hospitalized patients. JAMA Intern Med. 2021;181(8):1065–1070. doi: 10.1001/jamainternmed. 2021.2626.
  127. Wong A, cao J, Lyons pg, et al. quantification of sepsis model alerts in 24 US hospitals before and during the COVID-19 pandemic. JAMA Netw Open. 2021;4(11):e2135286. doi: 10.1001/jamanetworkopen. 2021.35286.
  128. Kheterpal S, Singh K, Topol EJ. Digitising the prediction and management of sepsis. Lancet. 2022;399(10334):1459. doi: 10.1016/S0140-6736(22)00658-4.
  129. ginestra Jc, giannini hM, Schweickert WD, et al. clinician perception of a machine learning–based early warning system designed to predict severe sepsis and septic shock. crit care Med. 2019;47(11):1477–1484. doi: 10.1097/ccM.0000000000003803.
  130. henry KE, Adams R, parent c, et al. Factors driving provider adoption of the TREWS machine learning-based early warning system and its effects on sepsis treatment timing. Nat Med. 2022;28(7):1447–1454. doi: 10.1038/s41591-022-01895-z.
  131. henry KE, Kornfield R, Sridharan A, et al. human-machine teaming is key to AI adoption: clinicians’ experiences with a deployed machine learning system. NPJ Digit Med. 2022;5(1):97. doi: 10.1038/s41746-022-00597-7.
  132. Rhoads DD, Sintchenko V, Rauch cA, et al. clinical microbiology informatics. clin Microbiol Rev. 2014;27(4): 1025e47–1021047. doi: 10.1128/cMR.00049-14.
  133. Sweeney L. confidentiality, disclosure, and data access: theory and practical applications for statistical agencies. In: Zayatz L, Doyle p, Theeuwes J, Lane J, editors. Washington, Dc: Urban Institute; 2001. p. e26.
  134. Densen p. challenges and opportunities facing medical education. Trans Am clin climatol Assoc. 2011;122:48e58.
  135. Bunsow E, Vecchio Mg-D, Sanchez c, et al. Improved sepsis alert with a telephone call from the clinical microbiology laboratory:12 V.-M. TSITOU ET AL. Medicine (Baltimore). .2015;94(39):e1454. doi: 10.1097/ MD.0000000000001454.
  136. Wang X, Williams c, Liu Zh, et al. Big data management challenges in health research-a literature review. Brief Bioinform. 2019;20(1):156e67–156167. doi: 10.1093/bib/ bbx086.
  137. Turner p, Fox-Lewis A, Shrestha p, et al. Microbiology investigation criteria for reporting objectively (MICRO): a framework for the reporting and interpretation of clinical microbiology data. BMC Med. 2019;17(1):70. doi: 10.1186/s12916-019-1301-1.
  138. chiu cY, Miller SA. clinical metagenomics. Nat Rev genet. 2019;20(6):341e55–341355. doi: 10.1038/ s41576-019-0113-7.
  139. Miller S, chiu c, Rodino Kg, et al. Should we be performing meta-genomic next-generation sequencing for infectious disease diagnosis in the clinical laboratory? J clin Microbiol. 2019;58(3). doi: 10.1128/JcM.01739-19.
  140. Amid c, pakseresht N, Silvester N, et al. The COMPARE10.1093/database/baz136.
  141. Littler K, Boon W-M, carson g, et al. progress in promoting data sharing in public health emergencies. Bull World health Organ. 2017;95(4):243–243. doi: 10.2471/ BLT.17.192096.
  142. Kostkova p. Disease surveillance data sharing for public health: the next ethical frontiers. Life Sci Soc policy. 2018;14(1):16. doi: 10.1186/s40504-018-0078-x.
  143. Brall c, Schröder-Bäck p, Maeckelberghe E. Ethical aspects of digital health from a justice point of view. Eur J public health. 2019;29(Supplement_3):18e22–18e22. doi: 10.1093/eurpub/ckz167.
  144. Topol EJ. high-performance medicine: the convergence of human and artificial intelligence. Nat Med. 2019;25(1):44e56. doi: 10.1038/s41591-018-0300-7.
  145. Ba?tanlar Y, Ozuysal M. Introduction to machine learning. Methods Mol Biol. 2014;1107:105e28–105128. doi: 10.1007/978-1-62703-748-8_7.
  146. Luz CF, Vollmer M, Decruyenaere J, et al. Machine learning in infection management using routine electronic health records: tools, techniques, and reporting of future technologies. clin Microbiol Infect. 2020;26(10):1291e9–121299. doi: 10.1016/j.cmi.2020.02.003.
  147. Macesic N, polubriaginof F, Tatonetti Np. Machine learning: novel bioinformatics approaches for combating anti- microbial resistance. curr Opin Infect Dis. 2017;30(6):511e7–51517. doi: 10.1097/qcO.0000000000000406.
  148. Wiens J, Shenoy ES. Machine learning for healthcare: on the verge of a major shift in healthcare epidemiology. clin Infect Dis. 2018;66(1):149e53–149153. doi: 10.1093/ cid/cix731.
  149. Rawson TM, hernandez B, Moore LSp, et al. Supervised machine learning for the prediction of infection on admission to hospital: a prospective observational cohort study. J Antimicrob chemother. 2019;74(4):1108e15–1101115. doi: 10.1093/jac/dky514.
  150. Montesinos López OA, Montesinos López A, Crossa J. Multivariate Statistical Machine [Internet]. Cham (CH): Springer; 2022. Learning Methods for Genomic Prediction Chapter 10, Fundamentals of Artificial Neural Networks and Deep Learning. 2022 Jan 14. Available from: https://www.ncbi.nlm.nih. gov/books/NBK583971/ doi: 10.1007/978-3-030-89010-0_10
  151. Zhang J, Zhang ZM. Ethics and governance of trustworthy medical artificial intelligence. BMC Med Inform Decis Mak. 2023 Jan13;23(1):7. doi: 10.1186/s12911-023-02103-9. PMID: 36639799; PMCID: PMC9840286.
  152. Garcia-Vidal C, Sanjuan G, Puerta-Alcalde P, Moreno-García E, Soriano A. Artificial intelligence to support clinical decision- making processes. EBioMedicine. 2019 Aug;46:27-29. doi: 10.1016/j. ebiom.2019.07.019. Epub 2019 Jul 11. PMID: 31303500; PMCID: PMC6710912.
  153. Croxatto A, Prod›hom G, Faverjon F, Rochais Y, Greub G. Laboratory automation in clinical bacteriology: what system to choose? Clinical Microbiol Infect. 2016 Mar;22(3):217-35. doi: 10.1016/j.cmi.2015.09.030. Epub 2016 Jan20. PMID: 26806135.

Reference

  1. Maraz KM, Khan RA. An overview on impact and application of microorganisms on human health, medicine and environment. GSC Biolpharm Sci. 2021;16:89-104.
  2. Karalis VD. The integration of artificial intelligence into clinical practice. Appl Biosci. 2024;3(1):14–44. doi: 10.3390/applbiosci3010002.
  3. Juhas M. Artificial intelligence in microbiology. In Brief lessons in microbiology. cham: Springer; 2023. doi: 10.1007/978-3-031-29544-7_8.
  4. Mishra A, Khan S, Das A, et al. Evolution of diagnostic and forensic microbiology in the era of artificial intelligence. cureus. 2023;15(9):e45738. doi: 10.7759/cureus.45738.
  5. Wilson S, Steele S, Adeli K. Innovative technological advancements in laboratory medicine: predicting the lab of the future. Biotechnol Biotechonal Equip. 2022;36(supl):S9 S21. doi: 10.1080/13102818.2021.2011413.
  6. Signoroni A, Ferrari A, Lombardi S, et al. hierarchical AI enables global interpretation of culture plates in the era of digital microbiology. Nat commun. 2023;14(1): 6874. doi: 10.1038/s41467-023-42563-1.
  7. Sarrafzadeh M-h, Mansouri SS, Zahiri J, et al. Artificial intelligence in environmental microbiology. Front Microbiol. 2022;13:944242. doi: 10.3389/fmicb.2022.944242.
  8. Jiang Y, Luo J, huang D, et al. Machine learning advanc es in microbiology: a review of methods and applications. Front Microbiol. 2022;13:925454. doi: 10.3389/ fmicb.2022.925454.
  9. Saheb T, Saheb T, carpenter DO. Mapping research strands of ethics of artificial intelligence in healthcare: a bibliometric and content analysis. comput Biol Med. 2021;135:104660. doi: 104660. 10.1016/j.compbiomed.2021.
  10. Kavvas ES, catoiu E, Mih N, et al. Machine learning and structural analysis of Mycobacterium tuberculosis pan-genome identifies genetic signatures of antibiotic resistance. Nat commun. 2018;9(1):4306. doi: 10.1038/ s41467-018-06634-y.
  11. Davis J, Boisvert S, Brettin T, et al. Antimicrobial resistance prediction in PATRIc and RAST. Sci Rep. 2016;6(1):27930. doi: 10.1038/srep27930.
  12. Freund Y, Schapire RE. A decision-theoretic generalization of on-line learning and an application to boosting. J comput Syst Sci. 1997;55(1):119–139. doi: 10.1006/ jcss.1997.1504
  13. Aniro g, et al. Variability of strain engraftment and predictability of microbiome composition after fecal microbiota transplantation across different diseases. Nat Med. 2022;28:1913–1923.
  14. Smillie CS, Sauk J, gevers D, et al. Strain tracking reveals the determinants of bacterial engraftment in the human gut following fecal microbiota transplantation. cell host Microbe. 2018;23(2):229–240.e5. doi: 10.1016/j. chom.2018.01.003.
  15. Schmidt TSB, Li SS, Maistrenko OM, et al. Drivers and determinants of strain dynamics following fecal microbiota transplantation. Nat Med. 2022;28(9):1902–1912. doi: 10.1038/s41591-022-01913-0.
  16. Signoroni A, Ferrari A, Lombardi S, et al. hierarchical AI enables global interpretation of culture plates in the era of digital microbiology. Nat commun. 2023;14(1): 6874. doi: 10.1038/s41467-023-42563-1.
  17. Sarrafzadeh M-h, Mansouri SS, Zahiri J, et al. Artificial intelligence in environmental microbiology. Front Microbiol. 2022;13:944242. doi: 10.3389/fmicb.2022.944242.
  18. Jiang Y, Luo J, huang D, et al. Machine learning advances in microbiology: a review of methods and applications. Front Microbiol. 2022;13:925454. doi: 10.3389/ fmicb.2022.925454.
  19. Saheb T, Saheb T, carpenter DO. Mapping research strands of ethics of artificial intelligence in healthcare: a bibliometric and content analysis. comput Biol Med. 2021;135:104660. doi: 10.1016/j.compbiomed.2021. 104660.
  20. Kavvas ES, catoiu E, Mih N, et al. Machine learning and structural analysis of Mycobacterium tuberculosis pan-genome identifies genetic signatures of antibiotic resistance. Nat commun. 2018;9(1):4306. doi: 10.1038/ s41467-018-06634-y.
  21. Davis J, Boisvert S, Brettin T, et al. Antimicrobial resistance prediction in pATRIc and RAST. Sci Rep. 2016;6(1):27930. doi: 10.1038/srep27930.
  22. Freund Y, Schapire RE. A decision-theoretic generalization of on-line learning and an application to boosting. J comput Syst Sci. 1997;55(1):119–139. doi: 10.1006/ jcss.1997.1504
  23. Aniro g, et al. Variability of strain engraftment and predictability of microbiome composition after fecal microbiota transplantation across different diseases. Nat Med. 2022;28:1913–1923.
  24. Smillie CS, Sauk J, gevers D, et al. Strain tracking reveals the determinants of bacterial engraftment in the human gut following fecal microbiota transplantation. cell host Microbe. 2018;23(2):229–240.e5. doi: 10.1016/j. chom.2018.01.003.
  25. Schmidt TSB, Li SS, Maistrenko OM, et al. Drivers and determinants of strain dynamics following fecal microbiota transplantation. Nat Med. 2022;28(9):1902–1912. doi: 10.1038/s41591-022-01913-0.
  26. Steinegger M, Söding J. MMseqs2 enables sensitive protein sequence searching for the analysis of massive data sets. Nat Biotechnol. 2017;35(11):1026–1028. doi: 10.1038/nbt.3988.
  27. Vanni c, Schechter MS, Acinas Sg, et al. Unifying the known and unknown microbial coding sequence space. Elife. 2022;11:e67667. doi: 10.7554/eLife.67667.
  28. Arango-Argoty g, garner E, pruden A, et al. DeepARg: a deep learning approach for predicting antibiotic resistance genes from metagenomic data. Microbiome. 2018;6(1):23. doi: 10.1186/s40168-018-0401-z.
  29. Baldi p. Deep learning in biomedical data science. Annu Rev Biomed Data Sci. 2018;1(1):181–205. doi: 10.1146/ annurev-biodatasci-080917-013343.
  30. Henry KE, Kornfield R, Sridharan A, Linton RC, Groh C, Wang T, et al. Human-machine teaming is key to AI adoption: Clinicians’ experiences with a deployed machine learning system. NPJ Digit Med. 2022;5(1):97. doi:10.1038/s41746-022-00597-7.
  31. Rajaraman S, Antani SK, poostchi M, et al. pre-trained convolutional neural networks as feature extractors toward improved malaria parasite detection in thin blood smear images. peerJ. 2018;6:e4568. doi: 10.7717/peerj.4568.
  32. Baldi p. Deep learning in biomedical data science. Annu Rev Biomed Data Sci. 2018;1(1):181–205. doi: 10.1146/ annurev-biodatasci-080917-013343.
  33. Mohseni P, Ghorbani A. Exploring the synergy of artificial intelligence in microbiology: Advancements, challenges, and future prospects. Comput Struct Biotechnol Rep. 2024;1:100005. doi:10.1016/j.csbr.2024.100005.
  34. Miller S, Chiu C, Rodino KG, Miller MB. Point-Counterpoint: Should We Be Performing Metagenomic Next- Generation Sequencing for Infectious Disease Diagnosis in the Clinical Laboratory? J Clin Microbiol. 2020;58(3):e01739-19. doi:10.1128/jcm.01739-19
  35. Ghosh D, Chakraborty S, Kodamana H, Chakraborty S. Application of machine learning in understanding plant virus pathogenesis: Trends and perspectives on emergence, diagnosis, host-virus interplay and management. Virol J. 2022;19(1):42. doi:10.1186/s12985-022-01767-5.
  36. Ross NE, pritchard cJ, Rubin DM, et al. Automated image processing method for the diagnosis and classification of malaria on thin blood smears. Med Biol Eng comput. 2006;44(5):427–436. doi: 10.1007/s11517-006-0044-2.
  37. Poostchi M, Silamut K, Maude RJ, et al. Image analysis and machine learning for detecting malaria. Transl Res. 2018;194:36–55. doi: 10.1016/j.trsl.2017.12.004.
  38. Mathison BA, Kohan JL, Walker JF, et al. Detection of intestinal protozoa in Trichrome-Stained stool specimens by use of a deep convolutional neural network. J clin Microbiol. 2020;58(6). doi: 10.1128/JcM.02053-19.
  39. Forero Mg, cristóbal g, Desco M. Automatic identification of Mycobacterium tuberculosis by gaussian mixture models. J Microsc. 2006;223(pt 2):120–132. doi: 10.1111/j.1365-2818.2006.01610.x.
  40. Zieli?ski B, plichta A, Misztal K, et al. Deep learning approach to bacterial colony classification. pLoS One. 2017;12(9):e0184554. doi: 10.1371/journal.pone.018.
  41. colubri A, Silver T, Fradet T, et al. Transforming clinical data into actionable prognosis models: machine learning frame-work and field-deployable app to predict outcome of Ebola patients. pLoS Negl Trop Dis. 2016;10(3):e0004549. doi:
  42. Wang hY, hung cc, chen ch, et al. Increase Trichomonas vaginalis detection based on urine routine analysis through a machine learning approach. Sci Rep. 2019;9(1):11074. doi: 10.1038/s41598-019-47361-8.
  43. pirnstill cW, coté gL. Malaria diagnosis using a mobile phone polarized microscope. Sci Rep. 2015;5(1):13368. doi: 10.1038/srep13368.
  44. Diederich B, Wartmann R, Schadwinkel h, et al. Using machine-learning to optimize phase contrast in a low-cost cellphone microscope. pLoS One. 2018;13(3): e0192937. doi: 10.1371/journal.pone.0192937.
  45. Ong DSY, poljak M. Smartphones as mobile microbiological laboratories. clin Microbiol Infect. 2020;26(4):421–424. doi: 10.1016/j.cmi.2019.09.026.
  46. Ouyang Y, Yuan Y, Zhang L, Chen Q, Li J. AI- powered diagnostic tools in microbiology: Revolutionizing the detection and identification of pathogens. Frontiers in Microbiology. 2023;14:1057923. doi:10.3389/fmicb.2023.1057923.
  47. Zorn KM, Lane TR, Russo Dp, et al. Multiple machine learning comparisons of hIV cell-based 10.1021/acs.molpharmaceut.8b01297 and reverse transcriptase data sets. Mol pharm. 2019;16(4):1620–1632. doi:.
  48. Svarovskaia ES, cheslock SR, Zhang Wh, et al. Retroviral mutation rates and reverse transcriptase fidelity. Front Bioscience-Landmark. 2003;8:d117–d134.
  49. goodswen SJ, Kennedy pJ, Ellis JT. A novel strategy for classifying the output from an insilico vaccine discovery pipeline for eukaryotic pathogens using machine learning algorithms. BMc Bioinformatics. 2013;14(1):315. doi: 10.1186/1471-2105-14-315.
  50. Verma R, Tiwari A, Kaur S, et al. Identification of proteins secreted by malaria parasite into erythrocyte usteins secreted by malaria parasite into erythrocyte using SVM and pSSM profiles. BMc Bioinformatics. 2008;9(1):201. doi: 10.1186/1471-2105-9-201.
  51. Rahman MS, Rahman MK, Saha S, et al. Antigenic: an improved prediction model of protective antigens. ArtifIntell Med. 2019;94:28–41. doi: 10.1016/j.artmed.2018.12.010.
  52. Zhang hT, Li DF, Zhao LL, et al. genome sequencing of161 Mycobacterium tuberculosis isolates from china identifies genes and intergenic regions associated with drug resistance. Nat genet. 2013;45(10):1255–1260. doi: 10.1038/ng.2735.
  53. Walker TM, Kohl TA, Omar SV. Whole-genome sequencing for prediction of Mycobacterium tuberculosis drug susceptibility and resistance: a retrospective cohort study. Lancet Infect Dis. 2018;18:21–21.
  54. Yang Y, Niehaus KE, Walker TM, et al. Machine learning for classifying tuberculosis drug-resistance from DNA sequencing data. Bioinformatics. 2018;34(10):1666–1671. doi: 10.1093/bioinformatics/btx801.
  55. Kouchaki S, Yang Y, Walker TM, et al. Application of machine learning techniques to tuberculosis drug resistance analysis. Bioinformatics. 2019;35(13):2276–2282. doi: 10.1093/bioinformatics/bty949.
  56. Farhat MR, Sultana R, Iartchouk O, et al. genetic determinants of drug resistance in Mycobacterium tuberculosis and their diagnostic value. Am J Respir crit care Med. 2016;194:621–630. doi: 10.1164/rccm.201510-2091Oc.
  57. Iyidogan p, Anderson KS. current perspectives on hIV-1 antiretroviral drug resistance. Viruses–Basel. 2014;6(10): 4095–4139. doi: 10.3390/v6104095.
  58. Ramon E, Belanche-Muñoz L, pérez-Enciso M. hIV drug resistance prediction with weighted categorical kernel functions. BMc Bioinformatics. 2019;20(1):410. doi: 10.1186/s12859-019-2991-2.
  59. peng Y, Li c, Rong Y, et al. Retrospective analysis of the accuracy of predicting the alert level of cOVID-19 in202 countries using google trends and machine learning. J glob health. 2020;10(2):020511. doi: 10.7189/ ing. J glob health. 2020;10(2):020511. doi: 10.7189/ jogh.10.020511.
  60. ginsberg J, Mohebbi Mh, patel RS, et al. Detecting influenza epidemics using search engine query data. Nature. 2009;457(7232):1012–1014. doi: 10.1038/na- ture07634.
  61. Shin S-Y, Seo D-W, AnJ, et al. high correlation of Middle East respiratory syndrome spread with google search and twitter trends in Korea. Sci Rep. 2016;6(1):32920. doi: 10.1038/srep32920
  62. Marques-Toledo c, Degener cM, Vinhal L, et al. Dengue prediction by the web: tweets are a useful tool for estimating and forecasting dengue at country and cityslevel. pLoS Negl Trop Dis. 2017;11.
  63. DiMucci D, Kon M, Segrè D. Machine learning reveals missing edges and putative interaction mechanisms in microbial ecosystem networks. Msystems. 2018;3(5): 10-1128. doi: 10.1128/mSystems.00181-18.
  64. Zhang Y, pechal JL, Schmidt CJ, et al. Machine learning performance in a microbial molecular autopsy context: a cross-sectional postmortem human population study. pLoS One. 2019;14(4):e0213829. doi: 10.1371/journal. pone.0213829.
  65. garcia E, Kundu I, Ali A, et al. The American society for clinical pathology’s 2016-2017 vacancy survey of medical laboratories in the United States. Am J clin pathol. 2018;149(5):387–400. doi: 10.1093/ajcp/aqy005.
  66. Smith Kp, Kang AD, Kirby JE. Automated interpretation of blood culture gram stains by use of a deep convolutional neural network. J clin Microbiol. 2018;56(3): e01521-17. doi: 10.1128/JcM.01521-17
  67. glasson J, hill R, Summerford M, et al. Multicenter evaluation of an image analysis device (ApAS): comparison between digital image and traditional plate reading using urine cultures. Ann Lab Med. 2017;37(6):499–504. doi: 10.3343/alm.2017.37.6.499.
  68. Faron ML, Buchan BW, Samra h, et al. Evaluation of the WASpLab software to automatically read chROMID CPS elite agar for reporting of urine cultures. J clin Microbiol. 2019;58(1). doi: 10.1128/JcM.00540-19.
  69. Van TT, Mata K, Dien Bard J. Automated detection of Streptococcus pyogenes pharyngitis by use of colorex strep a chROMagar and WASpLab artificial intelligence chromogenic detection module software. J clin Microbiol. 2019;57(11). doi: 10.1128/JcM.00811-19.
  70. Florio W, Tavanti A, Barnini S, et al. Recent advances and ongoing challenges in the diagnosis of microbial infections by MALDI-TOF mass spectrometry. Front Microbiol. 2018;9:1097. doi: 10.3389/fmicb.2018.0109.
  71. Datta S. Mass spectrometry data analysis in proteomics. 2nd ed. Berlin: Springer; 2013. chapter.10: feature selection and machine learning with mass spectrometry data.
  72. Wang h-Y, chen c-h, Lee T-Y, et al. Rapid detection of heterogeneous vancomycin-intermediate Staphylococcus aureus based on matrix-assisted laser desorption ionization time-of-flight: using a machine learning approach and unbiased validation. Front Microbiol. 2018;9:2393. doi: 10.3389/fmicb.2018.02393.
  73. Mather cA, Werth BJ, Sivagnanam S, et al. Rapid detection of vancomycin-intermediate Staphylococcus aureus by matrix-assisted laser desorption ionization-time of flight mass spectrometry. J clin Microbiol. 2016;54(4): 883–890. doi: 10.1128/JcM.02428-15.
  74. Lau AF, Walchak Rc, Miller hB, et al. Multicenter study demonstrates standardization requirements for mold identification by MALDI-TOF MS. Front Microbiol. 2019;10:2098. doi: 10.3389/fmicb.2019.02098.
  75. Long SW, Olsen RJ, Eagar TN, et al. population genomic analysis of 1,777 extended-spectrum beta-lactamase-pro- analysis of 1,777 extended-spectrum beta-lactamase-pro- ducing Klebsiella pneumoniae isolates, houston, Texas: unexpected abundance of clonal group 2017;307. MBio. 2017;8(3). doi: 10.1128/mBio.00489-17.
  76. Nguyen M, Long SW, McDermott pF, et al. Using machine learning to predict antimicrobial MIcs and associated genomic features for nontyphoidal Salmonella. J clin Microbiol. JcM.01260-18.2019;57(2):e01260-18. doi: 10.1128/ JcM.01260-18.
  77. Zhang W, he S, hong W, et al. A review of Raman-based technologies for bacterial identification and antimicrobial susceptibility testing. photonics. 2022;9(3):133. doi: 10.3390/photonics9030133.
  78. Undru TR, Uday U, Lakshmi JT, et al. Integrating artificial intelligence for clinical and laboratory diagnosis - a review. Maedica (Bucur). 2022;17(2):420–426.
  79. ghaffar Nia N, Kaplanoglu E, Nasab A. Evaluation of artificial intelligence techniques in disease diagnosis and prediction. Discover Artif Intell. 2023;10(5). doi: 10.1007/ s44163-023-00049-5.
  80. Rahmani AM, Azhir E, Ali S, et al. Artificial intelligence approaches and mechanisms for big data analytics: a systematic study. peerJ comput Sci. 2021;7:e488. doi: 10.7717/peerj-cs.488.
  81. Rhoads DD. computer vision and artificial intelligence are emerging diagnostic tools for the clinical microbiologist. J clin Microbiol. 2020;58(6). doi: 10.1128/JcM.00511-20.
  82. DeYoung B, Morales M, giglio S. Microbiology 2.0-a “behind the scenes” consideration for artificial intelligence applications for interpretive culture plate reading in routine diagnostic laboratories. Front Microbiol. 2022;13:976068. doi: 10.3389/fmicb.2022.976068.
  83. Alouani DJ, Ransom EM, Jani M, et al. Deep convolutional neural networks implementation for the analysis of urine culture. clin chem. 2022;68(4):574–583. doi: 10.1093/clinchem/hvab270.
  84. peiffer-Smadja N, Dellière S, Rodriguez c, et al. Machine learning in the clinical microbiology laboratory: has the time come for routine practice? clin Microbiol Infect. 2020;26(10):1300–1309. doi: 10.1016/j.cmi.2020.02.006.
  85. croxatto A, prod’hom g, Faverjon F, et al. Laboratory automation in clinical bacteriology: what system to choose? clin Microbiol Infect. 2016;22(3):217–235. doi: 10.1016/j.cmi.2015.09.030.
  86. slam MM, Nasrin T, Walther BA, et al. prediction of sepsis patients using machine learning approach: a meta-analysis. comput Methods programs Biomed. 2019;170:1–9. doi: 10.1016/j.cmpb.2018.12.027.
  87. Wang D, Li J, Sun Y, et al. A machine learning model for accurate prediction of sepsis in IcU patients. Front public health. 2021;9. doi: 10.3389/fpubh.2021;754348.
  88. Fleuren LM, Klausch TLT, Zwager cL, et al. Machine learning for the prediction of sepsis: a systematic review and meta-analysis of diagnostic test accuracy. Intensive care Med. 2020;46(3):383–400. doi: 10.1007/ s00134-019-05872-y.
  89. Lauritsen SM, Kalør ME, Kongsgaard EL, et al. Early detection of sepsis utilizing deep learning on electronic health record event sequences. Artif Intell Med. 2020;104:101820. doi: 10.1016/j.artmed.2020.101820.
  90. Shashikumar Sp, Wardi g, Malhotra A, et al. Artificial intelligence sepsis prediction algorithm learns to say “I don’t know. NPJ Digit Med. 2021;4(1):134. doi: 10.1038/ s41746-021-00504-6.
  91. Delahanty RJ, Alvarez J, Flynn LM, et al. Development and evaluation of a machine learning model for the early identification of patients at risk for sepsis. AnnEmerg Med. 2019;73(4):334–344. doi: 10.1016/j. annemergmed.2018.11.036
  92. GOH, Kh, Wang L, Yeow AYK, et al. Artificial intelligence in sepsis early prediction and diagnosis using unstructured data in healthcare. Nat commun. 2021;12(1):711. doi: 10.1038/s41467-021-20910-4.
  93. Adams R, henry KE, Sridharan A, et al. prospective, multi-site study of patient outcomes after implementation of the TREWS machine learning-based early warning system for sepsis. Nat Med. 2022;28(7):1455–1460. doi: 10.1038/s41591-022-01894-0.
  94. Seymour CW, Kennedy JN, Wang S, et al. Derivation, validation, and potential treatment implications of novel clinical phenotypes for sepsis. JAMA. 2019; 321(20):2003–2017. doi: 10.1001/jama.2019.5791.
  95. HO C-S, Jean N, hogan CA, et al. Rapid identification of pathogenic bacteria using Raman spectroscopy and deep learning. Nat commun. 2019;10(1):4927. doi: 10.1038/s41467-019-12898-9.
  96. Lin p-c, huang h-c, Komorowski M, et al. A machine learning approach for predicting urine output after fluid administration. comput Methods programs Biomed. 2019;177:155–159. doi: 10.1016/j.cmpb.2019.05.009.
  97. Bataille B, Selle J, Moussot p-E, et al. Machine learning methods to improve bedside fluid responsiveness prediction in severe sepsis or septic shock: an observation- al study. Br J Anaesth. 2021;126(4):826–834. doi: 10.1016/j.bja.2020.11.039.
  98. Liu R, hunold KM, caterino JM, et al. Estimating treatment effects for time-to-treatment antibiotic steward- ship in sepsis. Nat Mach Intell. 2023;5(4):421–431. doi: 10.1038/s42256-023-00638-0.
  99. Shimabukuro DW, Barton CW, Feldman MD, et al. Effect of a machine learning-based severe sepsis prediction algorithm on patient survival and hospital length of stay: a randomised clinical trial. BMJ Open Respir Res. 2017;4(1):e000234. doi: 10.1136/bmjresp-2017-000234.
  100. HOU N, Li M, he L, et al. predicting 30-days mortality for MIMIc-III patients with sepsis-3: a machine learning approach using Xgboost. J Transl Med. 2020;18(1):462. doi: 10.1186/s12967-020-02620-5.
  101. Yin J, Ngiam KY, Teo hh. Role of artificial intelligence applications in real-life clinical practice: systematic review. J Med Internet Res. 2021;23(4):e25759. doi: 10.2196/25759.
  102. cusumano-Towner M, Li DY, Tuo S, et al. A social network of hospital acquired infection built from electronic medical record data. J Am Med Inform Assoc. 2013;20(3):427–434. doi: 10.1136/amiajnl-2012-001401.
  103. Lakhani p, Sundaram B. Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks. Radiology. 2017;284(2):574–582. doi: 10.1148/radiol.2017162326.
  104. Méric g, Mageiros L, pensar J, et al. Disease- associated genotypes of the commensal skin bacterium Staphylococcus epidermidis. Nat commun. 2018;9(1):5034. doi: 10.1038/s41467-018-07368-7.
  105. Drew RJ, Murphy T, Broderick D, et al. An interpretation algorithm for molecular diagnosis of bacterial vaginosis in a maternity hospital using machine learning: proof-of-con- cept study. Diagn Microbiol Infect Dis. 2020;96(2):114950. doi: 10.1016/j.diagmicrobio.2019.114950.[96].
  106. Shillan D, Sterne JAC, champneys A, et al. Use of machine learning to analyse routinely collected intensive care unit data: a systematic review. crit care. 2019;23(1):284. doi: 10.1186/s13054-019-2564-9
  107. Lee AS, de Lencastre h, garau J, et al. Methicillin-resistant Staphylococcus aureus. Nat Rev Dis primers. 20018; 4(1):18033. doi: 10.1038/nrdp.2018.33
  108. gilmer J, et al. Neural message passing for quantum chemistry. In proceedings of the 34th International conference on Machine Learning 2017
  109. Yang K, Swanson K, Jin W, et al. Analyzing learned molecular representations for property prediction. J chem Inf Model. 2019;59(8):3370–3388. doi: 10.1021/acs. jcim.9b00237
  110. Toxicology in the 21st century. [cited 2022 Oct 20]. Available from: https://tripod.nih.gov/tox/.
  111. The human Metabolome Database. [cited 2022 Oct 20]. Available from: https://hmdb.ca/metabolites.
  112. Silver D, Schrittwieser J, Simonyan K, et al. Mastering the game of go without human knowledge. Nature. 2017;550(7676):354–359. doi: 10.1038/nature24270.
  113. cao Y, Jiang T, girke T. A maximum common substructure-based algorithm for searching and predicting drug-like compounds. Bioinformatics. 2018;24(13):i366– i374. doi: 10.1093/bioinformatics/btn186
  114. Stokes JM, Yang K, Swanson K, et al. A deep learning approach to antibiotic discovery. cell. 2020;180(4):688–702.e13. doi: 10.1016/j.cell.2020.01.021.
  115. Wong F, Stokes JM, Bening Sc, et al. Reactive metabolic byproducts contribute to antibiotic lethality under anaerobic conditions. Mol cell. 2020;82(18):3499–3512. e10. doi: 10.1016/j.molcel.2022.07.009.
  116. Wong F, Stokes JM, cervantes B, et al. cytoplasmic condensation induced by membrane damage is associated with antibiotic lethality. Nat commun. 2021;12(1):2321. doi: 10.1038/s41467-021-22485-6.
  117. Wong F, Wilson S, helbig R, et al. Understanding beta-lactam-induced lysis at the single-cell level. Front Microbiol. 2021;12:712007. doi: 10.3389/fmicb.2021. 712007.
  118. Wong F, Amir A. Mechanics and dynamics of bacterial cell lysis. Biophys J. 2019;116(12):2378–2389. doi: 10.1016/j.bpj.2019.04.040.
  119. Wu Y, gadsden SA. Machine learning algorithms in microbial classification: a comparative analysis. Front Artif Intell. 2023;6:1200994. doi: 10.3389/frai.2023.1200994
  120. Wu Y, gadsden SA. Machine learning algorithms in mi- crobial classification: a comparative analysis. Front Artif Intell. 2023;6:1200994. doi: 10.3389/frai.2023.1200994
  121. Farha MA, Verschoor cp, Bowdish D, et al. collapsing the proton motive force to identify synergistic combinations against Staphylococcus aureus. chem Biol. 2013;20(9):1168–1178. doi: 10.1016/j.chembiol.2013.07.006.
  122. Scott IA, cook D, coiera EW, et al. Machine learning in clinical practice: prospects and pitfalls. Med J Aust. 2019;211(5):203–205.e1. doi: 10.5694/mja2.50294.
  123. Rajkomar A, Dean J, Kohane I. Machine learning in medicine. N Engl J Med. 2019;380(14):1347–1358. doi: 10.1056/NEJMra1814259
  124. panch T, Mattie h, celi LA. The “inconvenient truth” about AI in healthcare. NpJ Digit Med. 2019;2(1):77. doi: 10.1038/s41746-019-0155-4.
  125. Finlayson Sg, Subbaswamy A, Singh K, et al. The clinician and dataset shift in artificial intelligence. N Engl J Med. 2021;385(3):283–286. doi: 10.1056/NEJMc2104626.
  126. Wong A, Otles E, Donnelly Jp, et al. External validation of a widely implemented proprietary sepsis prediction model in hospitalized patients. JAMA Intern Med. 2021;181(8):1065–1070. doi: 10.1001/jamainternmed. 2021.2626.
  127. Wong A, cao J, Lyons pg, et al. quantification of sepsis model alerts in 24 US hospitals before and during the COVID-19 pandemic. JAMA Netw Open. 2021;4(11):e2135286. doi: 10.1001/jamanetworkopen. 2021.35286.
  128. Kheterpal S, Singh K, Topol EJ. Digitising the prediction and management of sepsis. Lancet. 2022;399(10334):1459. doi: 10.1016/S0140-6736(22)00658-4.
  129. ginestra Jc, giannini hM, Schweickert WD, et al. clinician perception of a machine learning–based early warning system designed to predict severe sepsis and septic shock. crit care Med. 2019;47(11):1477–1484. doi: 10.1097/ccM.0000000000003803.
  130. henry KE, Adams R, parent c, et al. Factors driving provider adoption of the TREWS machine learning-based early warning system and its effects on sepsis treatment timing. Nat Med. 2022;28(7):1447–1454. doi: 10.1038/s41591-022-01895-z.
  131. henry KE, Kornfield R, Sridharan A, et al. human-machine teaming is key to AI adoption: clinicians’ experiences with a deployed machine learning system. NPJ Digit Med. 2022;5(1):97. doi: 10.1038/s41746-022-00597-7.
  132. Rhoads DD, Sintchenko V, Rauch cA, et al. clinical microbiology informatics. clin Microbiol Rev. 2014;27(4): 1025e47–1021047. doi: 10.1128/cMR.00049-14.
  133. Sweeney L. confidentiality, disclosure, and data access: theory and practical applications for statistical agencies. In: Zayatz L, Doyle p, Theeuwes J, Lane J, editors. Washington, Dc: Urban Institute; 2001. p. e26.
  134. Densen p. challenges and opportunities facing medical education. Trans Am clin climatol Assoc. 2011;122:48e58.
  135. Bunsow E, Vecchio Mg-D, Sanchez c, et al. Improved sepsis alert with a telephone call from the clinical microbiology laboratory:12 V.-M. TSITOU ET AL. Medicine (Baltimore). .2015;94(39):e1454. doi: 10.1097/ MD.0000000000001454.
  136. Wang X, Williams c, Liu Zh, et al. Big data management challenges in health research-a literature review. Brief Bioinform. 2019;20(1):156e67–156167. doi: 10.1093/bib/ bbx086.
  137. Turner p, Fox-Lewis A, Shrestha p, et al. Microbiology investigation criteria for reporting objectively (MICRO): a framework for the reporting and interpretation of clinical microbiology data. BMC Med. 2019;17(1):70. doi: 10.1186/s12916-019-1301-1.
  138. chiu cY, Miller SA. clinical metagenomics. Nat Rev genet. 2019;20(6):341e55–341355. doi: 10.1038/ s41576-019-0113-7.
  139. Miller S, chiu c, Rodino Kg, et al. Should we be performing meta-genomic next-generation sequencing for infectious disease diagnosis in the clinical laboratory? J clin Microbiol. 2019;58(3). doi: 10.1128/JcM.01739-19.
  140. Amid c, pakseresht N, Silvester N, et al. The COMPARE10.1093/database/baz136.
  141. Littler K, Boon W-M, carson g, et al. progress in promoting data sharing in public health emergencies. Bull World health Organ. 2017;95(4):243–243. doi: 10.2471/ BLT.17.192096.
  142. Kostkova p. Disease surveillance data sharing for public health: the next ethical frontiers. Life Sci Soc policy. 2018;14(1):16. doi: 10.1186/s40504-018-0078-x.
  143. Brall c, Schröder-Bäck p, Maeckelberghe E. Ethical aspects of digital health from a justice point of view. Eur J public health. 2019;29(Supplement_3):18e22–18e22. doi: 10.1093/eurpub/ckz167.
  144. Topol EJ. high-performance medicine: the convergence of human and artificial intelligence. Nat Med. 2019;25(1):44e56. doi: 10.1038/s41591-018-0300-7.
  145. Ba?tanlar Y, Ozuysal M. Introduction to machine learning. Methods Mol Biol. 2014;1107:105e28–105128. doi: 10.1007/978-1-62703-748-8_7.
  146. Luz CF, Vollmer M, Decruyenaere J, et al. Machine learning in infection management using routine electronic health records: tools, techniques, and reporting of future technologies. clin Microbiol Infect. 2020;26(10):1291e9–121299. doi: 10.1016/j.cmi.2020.02.003.
  147. Macesic N, polubriaginof F, Tatonetti Np. Machine learning: novel bioinformatics approaches for combating anti- microbial resistance. curr Opin Infect Dis. 2017;30(6):511e7–51517. doi: 10.1097/qcO.0000000000000406.
  148. Wiens J, Shenoy ES. Machine learning for healthcare: on the verge of a major shift in healthcare epidemiology. clin Infect Dis. 2018;66(1):149e53–149153. doi: 10.1093/ cid/cix731.
  149. Rawson TM, hernandez B, Moore LSp, et al. Supervised machine learning for the prediction of infection on admission to hospital: a prospective observational cohort study. J Antimicrob chemother. 2019;74(4):1108e15–1101115. doi: 10.1093/jac/dky514.
  150. Montesinos López OA, Montesinos López A, Crossa J. Multivariate Statistical Machine [Internet]. Cham (CH): Springer; 2022. Learning Methods for Genomic Prediction Chapter 10, Fundamentals of Artificial Neural Networks and Deep Learning. 2022 Jan 14. Available from: https://www.ncbi.nlm.nih. gov/books/NBK583971/ doi: 10.1007/978-3-030-89010-0_10
  151. Zhang J, Zhang ZM. Ethics and governance of trustworthy medical artificial intelligence. BMC Med Inform Decis Mak. 2023 Jan13;23(1):7. doi: 10.1186/s12911-023-02103-9. PMID: 36639799; PMCID: PMC9840286.
  152. Garcia-Vidal C, Sanjuan G, Puerta-Alcalde P, Moreno-García E, Soriano A. Artificial intelligence to support clinical decision- making processes. EBioMedicine. 2019 Aug;46:27-29. doi: 10.1016/j. ebiom.2019.07.019. Epub 2019 Jul 11. PMID: 31303500; PMCID: PMC6710912.
  153. Croxatto A, Prod›hom G, Faverjon F, Rochais Y, Greub G. Laboratory automation in clinical bacteriology: what system to choose? Clinical Microbiol Infect. 2016 Mar;22(3):217-35. doi: 10.1016/j.cmi.2015.09.030. Epub 2016 Jan20. PMID: 26806135.

Photo
Siddhi Gangurde
Corresponding author

Loknete Dr. J. D. Pawar College of Pharmacy Manur, Kalwan, Nashik

Photo
Poonam Gangurde
Co-author

Loknete Dr. J. D. Pawar College of Pharmacy Manur, Kalwan, Nashik

Photo
Yashpal More
Co-author

Loknete Dr. J. D. Pawar College of Pharmacy Manur, Kalwan, Nashik

Siddhi Gangurde, Poonam Gangurde, Yashpal More, Microbiology in The Era of Artificial Intelligence Transforming Pharmaceutical Microbiology, Int. J. of Pharm. Sci., 2025, Vol 3, Issue 10, 2660-2682. https://doi.org/10.5281/zenodo.17441860

More related articles
Ecofriendly Q-Absorbance Ratio Spectrophotometric ...
Devang Tandel, Kalpana Patel, Margi Patel, Vaishali Thakkar, Teja...
Formulation And Evaluation Of Polyherbal Wound Hea...
Sainabi P, Meghna, Thashreefa P M, Sheetal Krishna T, Vyshnavy De...
Pharmaceutical Process Validation: A Review...
Durga Bhagavan zade, Mrs, Smita.S.Aher, Sakshi.B.Tarle, Dr.Rishik...
View more
Download PDF
Related Articles
Hair Structure and Care: A Review of Herbal Hair Care Cosmetics...
Balaji Jadhav, Pratibha Bhalerao, Deep Gulave, Mayuri Jangle, ...
Network Pharmacology and Molecular Docking of Mucuna Pruriens in Treatment of De...
Akshaya P., Anusree S., Rupitha N. S., Liya S. Saji, Shabin P., Jyothi B. N., Kiran K. J., Prasobh G...
Antioxidant and Antimicrobial Activities of Methanolic Extract of Sorghum Bicolo...
Ganesh Sonawane, Anil Thakare, Kirti Sonare, Kajal Pansare, Chandrashekhar Patil, Mayur Bhamare, Rus...
Parthenogenesis: An Expansive Review of Asexual Reproduction in Plants and Anima...
Snehal Kakde, Sakshi Shinde , Anushka Kamble, ...
Ecofriendly Q-Absorbance Ratio Spectrophotometric Method for Simultaneous Quanti...
Devang Tandel, Kalpana Patel, Margi Patel, Vaishali Thakkar, Tejal Gandhi, ...
More related articles
Ecofriendly Q-Absorbance Ratio Spectrophotometric Method for Simultaneous Quanti...
Devang Tandel, Kalpana Patel, Margi Patel, Vaishali Thakkar, Tejal Gandhi, ...
Formulation And Evaluation Of Polyherbal Wound Healing Ointment Using Chromolaen...
Sainabi P, Meghna, Thashreefa P M, Sheetal Krishna T, Vyshnavy Devy D K, ...
Pharmaceutical Process Validation: A Review...
Durga Bhagavan zade, Mrs, Smita.S.Aher, Sakshi.B.Tarle, Dr.Rishikesh.S.Bachhav, ...
View more
Ecofriendly Q-Absorbance Ratio Spectrophotometric Method for Simultaneous Quanti...
Devang Tandel, Kalpana Patel, Margi Patel, Vaishali Thakkar, Tejal Gandhi, ...
Formulation And Evaluation Of Polyherbal Wound Healing Ointment Using Chromolaen...
Sainabi P, Meghna, Thashreefa P M, Sheetal Krishna T, Vyshnavy Devy D K, ...
Pharmaceutical Process Validation: A Review...
Durga Bhagavan zade, Mrs, Smita.S.Aher, Sakshi.B.Tarle, Dr.Rishikesh.S.Bachhav, ...
View more

Copyright © 2025 IJPS. All rights reserved