Artificial Intelligence AI and Robotics in Modern Healthcare The Dawn of a New Era

Abstract

Artificial intelligence (AI) is a fast-growing area that finds frequent applications in the education, healthcare, and business sectors. AI-based intelligent physical robots have been predicted to alter healthcare delivery significantly. Healthcare organizations are increasingly using robots to do a variety of jobs that improve patient care. During the COVID-19 pandemic, intelligent robot systems have significantly reduced the workload of medical professionals by providing assistance in risk assessment, monitoring, diagnosis, disinfection, telehealthcare, and numerous other areas. AI-powered technologies have also significantly accelerated the long-awaited COVID-19 vaccine discovery and clinical development research process for this deadly pathogen. The pandemic has expedited technological advancements in the digital era. Beyond the advances in safe data-sharing, telemedicine, payments, and remote monitoring, molecular modelling, target/structure-based drug design, cancer prediction, anticancer drug development, additional critical developments in blockchain, augmented reality, virtual reality, and AI-assisted, generative, and/or powered technologies are also remarkable. In the area of robotics in medical education, the majority of recent research has been on robotic surgery training for surgeons, with simulators used to practice surgical techniques. Robots have been utilized extensively in assistive and rehabilitative treatments in addition to surgical education, where the patient has historically been the focus of attention. Over the last twenty years, there has been a growing use of A0049 in the healthcare industry. When human and AI are combined, patients can receive more accurate diagnoses and have better recovery and functional outcomes. In addition to doctors and other healthcare professionals, patients and other members of the public must also embrace AI for it to reach its full potential.

Keywords

Artificial intelligence (AI), AI-assisted technologies, AI-powered technologies, Generative AI technologies, Healthcare organizations, Robotics

Introduction

Artificial intelligence (AI) is a broad and diversified scientific subject that has permeated all aspects of our lives and grown in relevance over the years, with over 20,000 papers published in 2019 alone. In 1956, John McCarthy and Marvin Minsky sponsored a series of workshops at the Dartmouth Summer Research Project on Artificial Intelligence (DSRPAI) where the phrase "artificial intelligence" was introduced ^[1].  As AI has grown, physical robots with AI-based intelligence (consequently, intelligent physical robots) have been used in the healthcare industry to expand the digitization of healthcare work processes and improve the accessibility, affordability, and efficiency of healthcare services, as seen in the case of smart healthcare services ^[2]. AI can address complicated healthcare difficulties by replacing human decision-making and reducing time-consuming and inconvenient aspects of practice. AI systems will transform healthcare from a person-centered approach to a more efficient and technologically driven paradigm that benefits everyone ^[3]. Robotics, which is frequently classified as a branch of AI, is becoming more and more involved in patient care. In the medical context, AI refers to, for example, mimicking the decision-making processes of health professionals. New tools based on AI have been developed to predict disease recurrence and progression or response to treatment ^[4]. Robotics produces tangible results or completes activities that need physical labour, as opposed to AI, which creates data. Robotics and AI employ patient data and expertise to do a range of functions, including diagnosis, surgical planning, monitoring patients physical and mental health, and performing simple physical treatments to increase patients’ independence as they age ^[5]. A significant challenge to the healthcare industry was presented recently by the coronavirus disease 2019 (COVID-19) pandemic, which increased demand for robots, AI-based apps, medications, and equipment. During the COVID-19 pandemic, several reputable hospitals worldwide have utilized AI and robotic operations for tasks like as patient and employee screening at the entrance point and disinfection ^[6]. During the previous pandemic, measures such as remotely supervised surgeries, distance education, telemedicine, and video conferencing with doctors were implemented. The experience obtained during the pandemic has significantly expanded the flexible use of robots in healthcare ^[7]. Additionally, AI enhances the healthcare system by supporting diagnostic and treatment applications, patient engagement, and adherence. By streamlining the work of physicians, nurses, and other healthcare professionals, AI also helps save considerable time ^[7,8]. Today, numerous AI fields, such as machine learning (ML), fuzzy modelling (FM), robotics and robots, and natural language processing (NLP), are critical components of patient care. ML is appropriate for situations requiring pattern recognition to get a certain clinical result. For example, supervised ML may be used to automate electrocardiogram (ECG) and X-ray pictures to arrive at a diagnosis ^[9]. In terms of using robots in health sciences education, the majority of recent research has focused on surgeon training in robotic surgery ^[9,10]. Furthermore, in the context of assistive and rehabilitation robotics, education has traditionally focused on the patient, whether to improve their quality of life, to provide them with information about their disease or a medical procedure they are about to undergo, or to teach them how to use an aiding technology, such as wearable or rehabilitation devices ^[8,9,11,12].  For AI to reach its full potential in healthcare, it must be adopted not only by physicians and health professionals but also by patients and members of the general public. Indeed, government, national and global policies, uniform public health regulations, and public acceptability are crucial for achieving the successful implementation of AI technologies in healthcare.

2. Use and Applications of Artificial Intelligence and Robotics in Healthcare

2.1. Artificial Intelligence in Robot-Assisted Surgery

Robotics and AI have greatly enhanced transplant surgery, yielding superior results in a range of transplant-related procedures. In order to maximize organ matching in the selection and allocation of organs, AI algorithms can first analyse a vast amount of patient data, including medical history, genetic variables, and donor features. Transplant surgeons can make well-informed decisions as a result, which raises the possibility of a successful transplant and decreases rejection rates ^[13].  Robotic technologies have proven useful in kidney and liver transplant surgeries, reducing blood loss, surgical stress, and expediting patient recovery. One example of such a technology is the da Vinci Surgical System ^[14]. Robotic surgery is a rapidly developing technology that will be a feature of the coming decades and is presently being used in surgical operation theatres. The ultimate goal of this technology, like AI, is to automate processes. Therefore, to eliminate human error while maintaining a high degree of accuracy and precision ^[14,15]. AI, particularly machine learning, is becoming increasingly useful in ophthalmology. Recent breakthroughs have been made feasible by incorporating graphics processing units (GPUs) into machine learning applications. With plenty of information accessible, several algorithms are already showing gains in diagnoses and even outcomes prediction for a variety of common ophthalmic diseases. Notable among them are the retina and glaucoma ^[16]. The field of spine surgery has seen a significant transformation in recent years due to technological breakthroughs in robotic-assisted spine surgery, augmented reality, and surgical simulation. As of this writing, the two most significant technological advancements in the modern era of spine surgery, neuro navigation and surgical robotics have the potential to incorporate AI and are particularly well-suited to AI. However, perioperative AI platforms are still in development and experimental stages ^[17]. Thus, to guide the anatomical placement of constructions and prevent iatrogenic harm during surgery, the operating team can also leverage AI-powered picture guidance. In fact, from spinal tumor removal to spinal deformity surgery, operating rooms across the United States frequently employ computer-assisted navigation (CAN) platforms. Surgical robots, in addition to CAN, have the potential to revolutionize the area of spine surgery by improving efficiency and precision, which will reduce consequences resulting from human mistakes ^[17,18]. The inclusion of robots in total knee arthroplasty (TKA) ensures the precise execution of the surgical plan and reporting of the acquired intraoperative result, as well as a better knowledge of intraoperative gap geometry, which secures the route of individualized alignment ^[19]. An additional minimally-invasive surgical approach for prostate cancer was made available in 2018 with the FDA's clearance of the purpose-built Single-Port (SP) robotic platform (Intuitive Surgical Inc., Sunnyvale, California) ^[20]. Compared to the multiport (MP) platform, it has more features. These features gave surgeons the chance to uniquely localize surgeries to the pertinent anatomy, which can significantly improve perioperative outcomes, postoperative quality of life, and surgical technique customization for each patient ^[20,21]. Digital neurosurgery is at the forefront of contemporary neurosurgical advancement. It is not a stand-alone surgical operation, but rather a therapy paradigm that is based on specific patient data and incorporates medical imaging, computer technology, DT, AI, and other digital technologies. This model improves the preoperative planning, intraoperative navigation, postoperative evaluation, and patient rehabilitation for neurosurgical illnesses ^[22].

2.2. Artificial Intelligence in Diagnosis

In the past ten years, the possibility of smart diagnosis has grown. It may be possible to enhance diagnosis and real-time, or point-of-care, detection as well as reduce errors and enable the sharing of medical data between devices, end users, and hospital cloud systems by combining smart technologies, like AI and IoMT (Internet of Medical Things), with traditional diagnostic techniques ^[23]. The detection of COVID-19 has been essential for managing the virus transmission, drug repurposing, antiviral drug discovery, developing antiviral drugs and vaccines, targeted-based biologicals, and providing rescue and curative therapy ^[24-26]. Furthermore, AI has potential applications in molecular diagnostics, predicting disease prognosis, and most importantly, in identifying post-COVID complications ^{[24, 27]}. A number of cutting-edge technologies are used by scientists, such as CAD-based on AI-driven models, AI/IoT-enabled systems, RT-PCR-based molecular diagnostics, and CRISPR/Cas-based biosensors ^[28]. AI has been used in medicine to help in cancer detection, anticancer drug discovery, and various approaches and treatment modalities in cancer management ^[29]. In the process of providing cancer patients with care, the use of its algorithms in onco-imaging and onco-pathology for cancer screening, tumour grading and staging, and the entire clinical decision-making process is gradually becoming crucial ^[30]. Technological developments additionally increased the ability for biomarker detection, especially with the development of large biological multi-omics datasets and AI algorithms ^[31]. Deep convolutional neural networks (CNNs), recurrent neural networks (RNNs), and transformer-based designs have all exhibited exceptional accuracy in tasks such as tumor detection, segmentation, and prognostic prediction. For example, Esteva et al. ^[32] demonstrated that deep neural networks could achieve dermatologist-level classification of skin cancer using clinical photos, representing a paradigm shift in the use of AI in oncology diagnostics ^[33]. Kaur et al. discovered three diagnostic genes that are platform independent using machine learning (ML) and large-scale transcriptomic profiling of data from 2,316 HCC (hepatocellular carcinoma) and 1,665 non-tumorous tissue samples. These genes showed prognostic potential and could detect HCC with high precision (93–98%) in both training and validation datasets. This indicates the contribution of AI-powered tools to the accurate identification of relevant biomarkers ^[34]. AI requires a thorough review of clinical data, which requires algorithms that are very accurate and trustworthy in distinguishing glaucoma from other disorders that may appear similarly. Determining a formal diagnosis of glaucoma is a more complex AI application than screening for suspected illness, and it is not yet widely used or recognized in many clinical procedures. Despite these obstacles, research in AI applications for glaucoma detection has grown exponentially during the last decade ^[35]. AI and ML can help diagnose and classify key neurosurgical problems. CNNs (convolutional neural networks) have reached >96% accuracy in epilepsy detection utilizing electroencephalography (EEG) data, with the ability to forecast seizures in real time ^[35,36]. In recent years, AI has acquired importance in a wide range of medical practices, particularly in image and pathology specialities with a significant imaging and diagnostic component. Gastroenterology has long been known for making groundbreaking advances in patient treatment via the use of cutting-edge technology ^[37]. Capsule endoscopy (CE) is a minimally invasive method that was originally designed to evaluate the small bowel and has demonstrated a good diagnostic yield for detecting small bowel abnormalities. The invention and execution of colon capsule endoscopy gave rise to the concept of a panenteric examination (e.g., for assessing Crohn's disease) ^[38]. In the past 20 years, deep learning models for AI have been used to diagnose individuals with psychiatric problems based on their neuroimaging data. For instance, Kim et al. extracted functional connectivity patterns from resting-state functional MRIs of schizophrenia patients and healthy controls, and this allowed them to categorize the patients and controls with an accuracy of 85.5% ^[37-39]. According to the research that was published in the Journal of Pathology Informatics, 60% of pathologists are presently using AI technologies in their work. Furthermore, almost 35% of pathologists planned to use AI in their training in the near future. The data presented demonstrates the increasing acknowledgement of AI's potential to revolutionize diagnostic analysis ^[36-40].

2.3. Artificial Intelligence in Exclusive Patient Care

Over the previous three decades, there has been a great deal of progress in the field of robotics for rehabilitation. These gadgets range from high-tech interfaces like robotic limbs and speech-generating devices to low-tech alternatives like walking aids. These tools are developing into intelligent technologies that can learn, adapt, and make context-sensitive decisions thanks to the incorporation of AI into assisting systems. These days, AI-powered gadgets can recognize voice, identify faces, decipher gestures, and even anticipate user intent—abilities that can significantly improve human-machine interaction. To increase real-time responsiveness and customisation, wearables, mobile applications, and smart home systems are incorporating technologies including computer vision, natural language processing (NLP), and machine learning (ML) algorithms. When it comes to patient contacts, robots may be repetitive and high-intensity without experiencing the same stress, tiredness, or damage as humans can. Robotic rehabilitation systems are heavily sensorized, providing physiotherapists and occupational therapists with objective, high-quality data to monitor rehabilitation progress or establish the severity of a patient's condition. ^{[41, 42]}. Robotic technologies are often employed in rehabilitation and physical support; they have mostly been introduced in aged care to give elders with mental and physical assistance in multimodal personalized care. Robot therapy, which involves PwDs (person with disabilities) interacting with dogs or humanoid social robots, is gaining popularity as a kind of mental support to lower BPSDs (behavioural and psychological symptoms of dementia) ^[43]. Researchers have been investigating ways to use sophisticated robotic technology to support elderly patients due to the complexity of dementia care and the fact that the ageing population demands greater care from fewer caregivers ^[44]. A robot called Companionable connects to a smart home environment to assist individuals with dementia or mild cognitive impairment in living at home. With its focus on social and cognitive assistance, this robot offers features including video calling, activity suggestions, daily activity reminders, and cognitive training. These features were evaluated over the course of two days with five couples in their homes and may lessen the workload for caregivers ^[43-45]. A recent study found that cognitively helpful robots might benefit both elderly persons and society. Home-based cognitively assistive robots are designed to provide cognitive training to older adults who live alone with cognitive impairments and are at risk of various accidents ^[46]. Stroke victims continue to face significant health challenges due to gait abnormalities. Every year, around 12 million people endure a stroke. For people with hemiparetic stroke who struggle with walking alone, robot-assisted gait training (RAGT) can offer intense, repeated, and task-oriented instruction by partially or entirely supporting their body weight and motions using a robot control system ^[47]. Rehabilitation therapy is regarded as the core of stroke treatment, helping survivors restore their motor abilities and quality of life. Finger gripping training is very useful for improving daily life skills in stroke patients with hand impairment. The spatiotemporal movement trajectory predefined by the robot computer control system is usually the basis for the most widely used hand function rehabilitation robots in clinical practice. This allows patients to passively complete repeated training without needing their active participation, which results in low patient active participation. ^[48,49]. Intelligent assistive devices that allow for adequate standing and walking training in the elderly with deteriorating lower limb function have important consequences for the rehabilitation of lower limb motor function and overall health. The renowned PAMM (Personal Aid for Mobility and Monitoring) system, created by the Massachusetts Institute of Technology, comprises an intelligent walking machine and a smart walking stick. The system uses force sensors as the major input interface to operate the active wheel at the base of the device, providing users with a walking aid ^[50]. To enhance afferent input from peripheral joints and give the central nervous system task-specific stimulation, for instance, robot-assisted treatment (RAT) has been widely utilized in line with the concepts of motor relearning and neuroplasticity ^[51]. So far, various robotic devices have been used for this purpose (exoskeletons, end-effectors, soft-robots), with promising evidence on diverse rehabilitation outcomes related to both upper (e.g., arm range of motion, hand grip and strength, dexterity) and lower (e.g., gait, balance, mobility) limb impairment ^[51,52].  Soft robotic wearable technologies show promise in improving arm function and quality of life for those with amyotrophic lateral sclerosis (ALS) and upper limb injuries. Studies undertaken by Proietti et al ^[53]. Nevertheless, despite the fact that a large number of rehabilitation robots have been created, their cost and bulkiness sometimes prevent people in rural locations or tiny medical facilities from using them ^[52-54].

2.4. Artificial Intelligence in the COVID-19 Pandemic Outbreak

AI systems, like machine learning, deep learning, convolutional neural networks, and cognitive computing, can be extremely helpful in detecting the novel coronavirus (nCOV2), the virus that causes coronavirus disease 2019 (COVID-19), screening it extensively, keeping an eye on it, reducing the amount of work that caregivers have to do, and anticipating potential interactions with the new treatments for it ^[25,26,55]. Following the COVID-19 pandemic, Battineni and colleagues presented a novel architecture for an AI chatbot that may act as a virtual advisor for instant messaging in situations when experts were unavailable, particularly in remote regions. As a result, the agent assists in assessing possible instances involving coronavirus exposure ^[56]. AI-based disease surveillance tools are becoming increasingly popular. AI advancements have improved COVID-19 screening accuracy and effectiveness, and AI currently outperforms humans in several healthcare jobs ^[57]. Due to its advantageous features, including self-reported data analysis, X-ray interpretation, computed tomography (CT) image identification, language processing, and medication infusion management, the use of AI in the medical industry has boomed and remarkably highlighted during the COVID-19 period, with emphasis on nationwide and global data collection of COVID-19-affected individuals, primary and second attack rates, statistical epidemiological prediction of first, second, and third waves of COVID-19 pandemic ^{[25,26,58,59]}. The difficulties found in COVID-19 pandemic prevention and control procedures, including identification and assessment of post-COVID complications, global medicine distribution, national and global COVID-19 vaccination rates, cleaning duties, and modernizing healthcare services and technologies, have been helped by intelligent robots ^{[24-27,59,60]}. Furthermore, the effectiveness and quality of healthcare might be greatly improved by AI-powered telemedicine. AI algorithms, for example, may help physicians analyze large amounts of patient data more rapidly, find patterns and trends, and make accurate diagnoses. Its virtual assistants and chatbots may also provide patients with real-time assistance, support, and education, thereby improving patient engagement, self-management, and treatment adherence ^[60,61]. Collaboration between pharmaceutical discovery, digital technology, and health information is critical in addressing the COVID-19 pandemic. The need for big data analytics and AI integration in healthcare services is driven by access to databases through the IoT (Internet of Things) and EHR (Electronic Health Records) ^[60-62].

2.5. Artificial Intelligence in Drug Discovery

In recent decades, there has been a revolution in data science due to the massive amount of data that can be examined (the era of big data) and the availability of high-performance computers, namely graphics processing unit (GPU) computing. This scenario is not unique in drug discovery: the vast volume of data (chemical, biological, etc.) combined with the automation of processes has created a fertile field for the use of computational intelligence and AI ^[63]. A new drug takes around 14 years to reach the market, at an average cost of $2.6 billion. Furthermore, selecting a novel, effective medication molecule from a pool of potentially pharmacologically active chemical entities (lead molecules) is the most difficult undertaking. Researchers can choose a few therapeutically successful candidates from thousands of compounds using computer-aided drug design tools in less time because of AI ^[64].  A medication typically takes 4.5–5 years from the time of invention to the point of clinical testing. Surprisingly, in 2019, the UK biotech company Exscientia and the Japanese pharmaceutical company Sumitomo Dainippon Pharma collaborated to develop a novel medication that uses AI to treat obsessive-compulsive disorder (OCD). In the medical field, it is the first time a medicine has been designed entirely utilizing AI in less than a year, having taken 4.5 years to complete ^[65]. Exscientia's AI uses a number of techniques to discover a new lead chemical. The molecule is known as DSP-1181, a long-acting 5-HTA1 receptor agonist. Targeting a brain receptor uniquely associated with OCD was the main objective. ^[66]. Recently, in 2015, the Ebola virus outbreak in West Africa and some European countries was controlled through the use of AI, which assisted in the discovery of an appropriate drug in a very short period of time and prevented the outbreak from becoming a global pandemic. Indeed, COVID-19 vaccine discovery and development, their distribution, patient and public health data collection and surveillance of COVID-19 vaccination, national and global vaccination rates, and vaccine-associated complications ^{[24-29,59,66-68]}. AI systems may be used to investigate the three-dimensional structure of drugs and anticipate chemical interactions with possible targets ^[29,61]. Furthermore, clinical trials of newly found medications may be completed in a relatively short period of time because of AI ^[68]. AI may also distinguish between cardiotoxic and non-cardiotoxic anticancer medicines. It can also identify potential antibiotics from a list of thousands of chemicals and serve as a platform for discovering novel antibiotics. These algorithms are also used to find molecules capable of combating antimicrobial resistance, which leads to antibiotic resistance. Studies are underway to study the function of AI in tackling rapidly rising antibiotic resistance ^[69].    

2.6. Artificial Intelligence in Nanotechnology and Precision Medicine

AI refers to sophisticated computing algorithms that are intended to identify patterns in complex datasets and carry out tasks by mimicking human intellect. AI applications in other cutting-edge domains, including radiomics, genomics, or transcriptomics, may speed up improvements in patient management by providing insightful information on outcome prediction and enhancing tailored medical care ^[70].  AI has the potential to completely transform healthcare, particularly in the area of cancer treatment, when combined with the development of nanotechnology-based products. Large datasets may be handled and scrutinize by AI effectively, enabling the development of customized precision nanomedicines ^[71]. AI can improve the accuracy of molecular profiling and early patient diagnosis. Furthermore, by optimising their characteristics, attaining optimal therapeutic synergy, and avoiding possible nontoxicity, AI can enhance the development process of nanomedicines. In the end, this invention improves the effectiveness of nanomedicines generally, customized dosage, and therapeutic accuracy ^[72,73]. Supervised machine learning (SML) is an important tool for comprehending scientific results and learning the behaviour of nanotechnology, which opens the way for the logical extension of SML in nano-systems. SML is now actively utilized in nanotechnology system simulations for a wide range of healthcare application domains. The primary task in the healthcare industry is to create a simulation of a nanoparticle's behaviour and operation to select drug carriers more efficiently and at a lower cost than the actual nanoparticle creation process ^[74]. A self-learning, biocompatible, and degradable nanorobot that uses AI to guide it and is composed of biocompatible materials (carrageenan or capsule coat) and can deliver drugs to specific cancer sites in the body must have all the necessary accessories, such as a target sensor, a tracking sensor, and a self-detonation feature to allow the robot to decompose after it has fulfilled its intended function ^[75]. The path toward more individualized and focused therapies includes investigating nanotechnology for targeted medication delivery systems and maybe using AI-powered algorithms to decode biomarker trends. Additionally, the study of biomarkers may be able to forecast the course of disease, treat autoimmune skin problems, and enable more specialized immunotherapies. Furthermore, real-time biomarker monitoring through the integration of wearable technologies and multi-omics data holds promises for more flexible and responsive methods to customized dermatological therapy ^[74-76]. Nanomedicines are a combination of nanotechnology with medicine, with applications in illness detection, monitoring, and therapy. They can be directly given to patients in clinical settings or incorporated into medical bio-devices, nano-biosensors, and biological machineries to improve healthcare capabilities ^[77]. A wide range of nanomedical products have entered the worldwide market, with applications in the treatment of several cancer types, including ovarian cancer, breast cancer, lung cancer, pancreatic cancer, acute myeloid leukaemia, and more ^[78]. A key problem of nanomedicine is determining the impacts of various medications in terms of duration, dosage, and efficacy for individual patients. SML can be effectively used with nanomedicine to boost the dosage in amalgamation therapy ^[77-79].

2.7. Artificial Intelligence in Medical Education

AI was originally employed in medical education in the 1950s, but until the early 2000s, its presence in the field was relatively static. Its cautious adoption and ongoing scepticism regarding its function led to its limited use in the medical field. In the context of AI's function in medical education, other areas that are still understudied include its potential to help faculty with curriculum building and evaluation. Because medical education is a dynamic field, teachers are under constant pressure to provide engaging and concise lectures that can hold their own against the information found in outside learning materials ^[80]. AI has a huge potential to play a part in medical education, especially large language models (LLMs). These might give students a quick way to find the answers to their questions. However, this needs to be weighed against the requirement that medical students learn to read textbooks and other medical literature. Students might write notes for future review or test preparation with the aid of LLMs ^[81]. There are several educational and communication options available to LLMs. First, a number of publications stated that physicians must understand the underlying algorithms and statistical techniques employed by LLMs for them to be successfully incorporated into clinical practice ^[81,82]. A number of studies have shown that LLMs do rather well on standardized examinations in medicine, which may point to the possibility of using these models to create study materials in the context of clinical education. These models could also be useful for doctors to educate and interact with patients ^[83]. AI is also being utilized to improve surgical education by developing automated skills evaluation tools and providing intraoperative feedback ^[84]. The creation of worldwide deconstructed robotic colorectal procedural descriptions (DPDs) might help with the creation of a global curriculum of component operational abilities backed by objective measures. This will facilitate the standardization of robotic training for colorectal surgery and enable a proficiency-based training methodology ^[85]. At all medical school levels, there is a need for specialized educational programs on AI in medicine to guarantee that the solutions created take into account the particular difficulties associated with dealing with clinical data and are in line with the clinical context ^[84-86].

3. Limitations

AI systems have a lot of potential to improve medical research, but there are a number of current problems that highlight the need for caution and wise application. These are mostly related to biases, data security, model dependability, and the timeliness of AI-provided information ^[87]. The drawbacks of AI must be addressed. These include issues with data security and confidentiality, prejudice and inaccuracy, stereotypes, plagiarism, adherence to data privacy laws, and the indispensable role of human judgment ^[88]. AI chatbots are educated on closed datasets, which are incapable of automatically updating to include the most recent data. This is especially crucial when it comes to the healthcare industry, as best practices, safety data, and clinical practice standards are always evolving. People may receive outdated information in answer to their inquiries if chatbot material is not updated in real-time. The same may apply to human-to-human interactions; yet, unlike AI chatbots, healthcare providers may obtain current information in real time ^[88,89]. With the advancement of AI, there has been a problem with the datasets needed to train algorithms in all fields. Healthcare databases frequently underrepresent equity-seeking populations, as well as those with impairments or uncommon diseases. This is because coloured individuals and those with unusual medical illnesses are typically underrepresented in clinical trials and research ^[90]. As a result, the use of AI systems in healthcare has the potential to increase healthcare disparities. It's critical to recognize the limits of some AI models. Specifically, for some AI models to learn and function at their best, a substantial amount of clear, correct data is required. The main issue with rare illnesses is that it's sometimes impossible to get enough data to properly train a model ^[91]. AI will continue to progress and evolve toward superintelligence. However, it lacks the ability to make empathetic, fair, and equitable choices. AI is incapable of self-reflection, self-correction, or consideration of human variety, views, ethics, and morals. Reframing such future AI for what it truly is, i.e., Artificial Wisdom (AW), emphasizes the limits of today's AI and the necessity for wisdom in the future ^[92].

CONCLUSION

The application of robotics and AI in healthcare is a breakthrough step toward a more accurate, patient-centred, and productive medical environment. These technologies have shown considerable promise in improving surgical outcomes, treatment plan optimization, and diagnostic accuracy. The speed and accuracy with which AI can analyse big datasets and generate insights for application improves the precision and consistency of autonomous systems performing complicated tasks. When used together, they not only enhance procedures but also lower the potential of human error, ensuring higher standards for patient safety and care quality. The combination of robotics and AI has the potential to revolutionize healthcare delivery in the future, making it more efficient, personalized, and accessible. However, in order to fully enjoy these benefits, it is important to address ethical problems, ensure good data security, and promote multidisciplinary collaboration. By appropriately implementing these advances, we can ensure a new age of healthcare that is smarter, more compassionate, and universally helpful.

CONSENT

It is not applicable.

ETHICAL APPROVAL

It is not applicable.

DISCLAIMER (Artificial intelligence)

Author(s) hereby declare that NO generative AI technologies such as Large Language Models (ChatGPT, COPILOT, etc) and text-to-image generators have been used during the writing or editing of manuscripts.

Competing interests

We, the authors, declare no competing interests.

AUTHORS’ CONTRIBUTIONS

All authors contributed to the review design and plan. MJ and SP contributed to the data search, collection, extraction, and quality assessment for this review. Both authors wrote the text, reviewed and edited the manuscript, and made substantial contributions to discussions of the content.

REFERENCES

1. Pishgar M, Issa SF, Sietsema M, Pratap P, Darabi H. REDECA: a novel framework to review artificial intelligence and its applications in occupational safety and health. International journal of environmental research and public health. 2021 Jun 22;18(13):6705.
2. Huang R, Li H, Suomi R, Li C, Peltoniemi T. Intelligent physical robots in healthcare: systematic literature review. Journal of medical Internet research. 2023 Jan 18;25:e39786.
3. Fawns T, Lazarus MD. Tomorrow's doctors are robots: Redefining healthcare education and practice in the technological revolution. Medical Education. 2026 Jan;60(1):51-4.
4. Malik P, Pathania M, Rathaur VK. Overview of artificial intelligence in medicine. Journal of family medicine and primary care. 2019 Jul 1;8(7):2328-31.
5. Denecke K, Baudoin CR. A review of artificial intelligence and robotics in transformed health ecosystems. Frontiers in medicine. 2022 Jul 6;9:795957.
6. Deo N, Anjankar A. Artificial intelligence with robotics in healthcare: a narrative review of its viability in India. Cureus. 2023 May;15(5).
7. Sarker S, Jamal L, Ahmed SF, Irtisam N. Robotics and artificial intelligence in healthcare during COVID-19 pandemic: A systematic review. Robotics and autonomous systems. 2021 Dec 1;146:103902.
8. Davenport T, Kalakota R. The potential for artificial intelligence in healthcare. Future healthcare journal. 2019 Jun 1;6(2):94-8.
9. Eldaly AS, Avila FR, Torres-Guzman RA, Maita K, Garcia JP, Serrano LP, Forte AJ. Artificial intelligence and lymphedema: State of the art. Journal of Clinical and Translational Research. 2022 Jun 6;8(3):234.
10. Marcos-Pablos S, García-Peñalvo FJ. More than surgical tools: a systematic review of robots as didactic tools for the education of professionals in health sciences. Advances in Health Sciences Education. 2022 Oct;27(4):1139-76.
11. Ciullo AS, Veerbeek JM, Temperli E, Luft AR, Tonis FJ, Haarman CJ, Ajoudani A, Catalano MG, Held JP, Bicchi A. A novel soft robotic supernumerary hand for severely affected stroke patients. IEEE transactions on neural systems and rehabilitation engineering. 2020 Mar 31;28(5):1168-77.
12. Beets B, Newman TP, Howell EL, Bao L, Yang S. Surveying public perceptions of artificial intelligence in healthcare in the United States: systematic review. Journal of Medical Internet Research. 2023 Apr 4;25:e40337.
13. Bokhari SF. Artificial Intelligence and Robotics in Transplant Surgery: Advancements and Future Directions. Cureus. 2023 Aug;15(8).
14. Gotlieb N, Azhie A, Sharma D, Spann A, Suo NJ, Tran J, Orchanian-Cheff A, Wang B, Goldenberg A, Chassé M, Cardinal H. The promise of machine learning applications in solid organ transplantation. NPJ digital medicine. 2022 Jul 11;5(1):89.
15. Tarassoli SP. Artificial intelligence, regenerative surgery, robotics? What is realistic for the future of surgery?. Annals of Medicine and Surgery. 2019 May 1;41:53-5.
16. Urias MG, Patel N, He C, Ebrahimi A, Kim JW, Iordachita I, Gehlbach PL. Artificial intelligence, robotics and eye surgery: are we overfitted?. International Journal of Retina and Vitreous. 2019 Dec;5:1-4.
17. Rasouli JJ, Shao J, Neifert S, Gibbs WN, Habboub G, Steinmetz MP, Benzel E, Mroz TE. Artificial intelligence and robotics in spine surgery. Global Spine Journal. 2021 May;11(4):556-64.
18. Kochanski RB, Lombardi JM, Laratta JL, Lehman RA, O’Toole JE. Image-guided navigation and robotics in spine surgery. Neurosurgery. 2019 Jun 1;84(6):1179-89.
19. von Eisenhart-Rothe R, Hinterwimmer F, Graichen H, Hirschmann MT. Artificial intelligence and robotics in TKA surgery: promising options for improved outcomes?. Knee Surgery, Sports Traumatology, Arthroscopy. 2022 Aug;30(8):2535-7.
20. von Eisenhart-Rothe R, Hinterwimmer F, Graichen H, Hirschmann MT. Artificial intelligence and robotics in TKA surgery: promising options for improved outcomes?. Knee Surgery, Sports Traumatology, Arthroscopy. 2022 Aug;30(8):2535-7.
21. Covas Moschovas M, Kind S, Bhat S, Noel J, Sandri M, Rogers T, Moser D, Brady I, Patel V. Implementing the da Vinci SP without increasing positive surgical margins: experience and pathologic outcomes of a prostate cancer referral center. Journal of Endourology. 2022 Apr 1;36(4):493-8.
22. Yuan Z, Shi Z, Wang Z. Digital neurosurgery in the era of intelligent medicine: a scoping review. Frontiers in Medicine. 2025 Dec 16;12:1700166.
23. Irkham I, Ibrahim AU, Nwekwo CW, Al-Turjman F, Hartati YW. Current technologies for detection of COVID-19: Biosensors, artificial intelligence and internet of medical things (IOMT). Sensors. 2022 Dec 30;23(1):426.
24. Avirineni P, Dundigalla SK, Padi SSV. Drug repurposing for COVID-19: Current status of potential therapeutics”. Journal of Advances in Medical and Pharmaceutical Sciences. 2023; 25 (11):40-60. https://doi.org/10.9734/jamps/2023/v25i11653.
25. Gaddam S, Pasupulati H, Padi SSV. Development of vaccines and COVID-19 vaccines. World Journal of Current Med and Pharm Research. 2023 June 9; 5(3):51-56. https://doi.org/10.37022/wjcmpr.v5i3.265
26. Pabbathi N, Pasupulati H, Gaddam S, Padi SSV. The World of vaccines: Phases of clinical trials and current status of COVID-19 vaccines. Asian Journal of Pharmaceutical Research and Development. 2023; 11(3):151–167. https://doi.org/10.22270/ajprd.v11i3.1273
27. Jolam M, Pasupulati H, Padi SSV. Post-COVID-19 associated cardiovascular complications: a scoping review. Int J Health Sci Res. 2024; 14(11):301-313. https://doi.org/10.52403/ijhsr.20241135
28. Samson R, Navale GR, Dharne MS. Biosensors: frontiers in rapid detection of)  COVID-19. 3 Biotech. 2020 Sep;10(9):385.

29. Guduri M, Kolluru S, Pasupulati H, Padi SSV. A comprehensive review on PARP Inhibitors in targeted therapy for cancers. Journal of International Research in Medical and Pharmaceutical Sciences. 2024; 19(2): 44-59. https://doi.org/10.56557/ jirmeps/2024/ v19i28811.
30. Daher H, Punchayil SA, Ismail AA, Fernandes RR, Jacob J, Algazzar MH, Mansour M. Advancements in Pancreatic Cancer Detection: Integrating Biomarkers, Imaging Technologies, and Machine Learning for Early Diagnosis. Cureus. 2024 Mar;16(3).
31. Mansur A, Vrionis A, Charles JP, Hancel K, Panagides JC, Moloudi F, Iqbal S, Daye D. The role of artificial intelligence in the detection and implementation of biomarkers for hepatocellular carcinoma: outlook and opportunities. Cancers. 2023 May 26;15(11):2928.
32. Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, Thrun S. Dermatologist-level classification of skin cancer with deep neural networks. nature. 2017 Feb 2;542(7639):115-8.
33. Folasole A, Noah GU, Akangbe B, Omohoro MU, Elesho OE, Akangbe BO. Leveraging Machine Learning and Artificial Intelligence in Cancer Diagnostics Imaging: A Systematic Review. Cureus. 2025 Dec 5;17(12).
34. Kaur H, Dhall A, Kumar R, Raghava GP. Identification of platform-independent diagnostic biomarker panel for hepatocellular carcinoma using large-scale transcriptomics data. Frontiers in genetics. 2020 Jan 10;10:1306.
35. Zhu Y, Salowe R, Chow C, Li S, Bastani O, O’Brien JM. Advancing glaucoma care: integrating artificial intelligence in diagnosis, management, and progression detection. Bioengineering. 2024 Jan 26;11(2):122.
36. Schonfeld E, Mordekai N, Berg A, Johnstone T, Shah A, Shah V, Haider G, Marianayagam NJ, Veeravagu A. Machine Learning in Neurosurgery: Toward Complex Inputs, Actionable Predictions, and Generalizable Translations. Cureus. 2024 Jan;16(1).
37. Currie G, Hawk KE, Rohren E, Vial A, Klein R. Machine learning and deep learning in medical imaging: intelligent imaging. Journal of medical imaging and radiation sciences. 2019 Dec 1;50(4):477-87.
38. Mascarenhas M, Martins M, Afonso J, Ribeiro T, Cardoso P, Mendes F, Andrade P, Cardoso H, Ferreira J, Macedo G. The Future of Minimally Invasive Capsule Panendoscopy: Robotic Precision, Wireless Imaging and AI-Driven Insights. Cancers. 2023 Dec 15;15(24):5861.
39. Pham KT, Nabizadeh A, Selek S. Artificial intelligence and chatbots in psychiatry. Psychiatric Quarterly. 2022 Mar;93(1):249-53.
40. Kiran N, Sapna FN, Kiran FN, Kumar D, Raja FN, Shiwlani S, Paladini A, Sonam FN, Bendari A, Perkash RS, Anjali FN. Digital pathology: transforming diagnosis in the digital age. Cureus. 2023 Sep;15(9).
41. Alsaleh A. The influence of artificial intelligence on individuals with disabilities. Acta Psychologica. 2026 Feb 1;262:106010.
42. Carriere J, Shafi H, Brehon K, Pohar Manhas K, Churchill K, Ho C, Tavakoli M. Case report: Utilizing AI and NLP to assist with healthcare and rehabilitation during the COVID-19 pandemic. Frontiers in artificial intelligence. 2021 Feb 12;4:613637.
43. Sumioka H, Shiomi M, Honda M, Nakazawa A. Technical challenges for smooth interaction with seniors with dementia: Lessons from Humanitude™. Frontiers in Robotics and AI. 2021 Jun 2;8:650906.
44. Koutentakis D, Pilozzi A, Huang X. Designing socially assistive robots for Alzheimer’s disease and related dementia patients and their caregivers: where we are and where we are headed. InHealthcare 2020 Mar 26 (Vol. 8, No. 2, p. 73). MDPI.
45. Tsoi KK, Jia P, Dowling NM, Titiner JR, Wagner M, Capuano AW, Donohue MC. Applications of artificial intelligence in dementia research. Cambridge Prisms: Precision Medicine. 2023 Jan;1:e9.
46. Tokunaga S, Sekiguchi T, Watanabe Miura K, Sugimoto H, S Abe M, Tamura K, Kishimoto T, Kudo T, Otake-Matsuura M. Home-Based Cognitive Intervention for Healthy Older Adults Through Asking Robots Questions: Randomized Controlled Trial. JMIR aging. 2024 Apr 22;7:e47229.
47. Hirano S, Saitoh E, Imoto D, Ii T, Tsunoda T, Otaka Y. Effects of robot-assisted gait training using the Welwalk on gait independence for individuals with hemiparetic stroke: an assessor-blinded, multicenter randomized controlled trial. Journal of NeuroEngineering and Rehabilitation. 2024 May 14;21(1):76.
48. Li Y, Lian Y, Chen X, Zhang H, Xu G, Duan H, Xie X, Li Z. Effect of task-oriented training assisted by force feedback hand rehabilitation robot on finger grasping function in stroke patients with hemiplegia: a randomised controlled trial. Journal of NeuroEngineering and Rehabilitation. 2024 May 14;21(1):77.
49. Takebayashi T, Takahashi K, Okita Y, Kubo H, Hachisuka K, Domen K. Impact of the robotic-assistance level on upper extremity function in stroke patients receiving adjunct robotic rehabilitation: sub-analysis of a randomized clinical trial. Journal of NeuroEngineering and Rehabilitation. 2022 Feb 25;19(1):25.
50. Zhao D, Sun X, Shan B, Yang Z, Yang J, Liu H, Jiang Y, Hiroshi Y. Research status of elderly-care robots and safe human-robot interaction methods. Frontiers in Neuroscience. 2023 Nov 30;17:1291682.
51. Zanatta F, Farhane-Medina NZ, Adorni R, Steca P, Giardini A, D’Addario M, Pierobon A. Combining robot-assisted therapy with virtual reality or using it alone? A systematic review on health-related quality of life in neurological patients. Health and Quality of Life Outcomes. 2023 Feb 21;21(1):18.
52. Giansanti D. The rehabilitation and the robotics: Are they going together well?. In Healthcare 2020 Dec 30 (Vol. 9, No. 1, p. 26). MDPI.
53. Proietti T, O’Neill C, Gerez L, Cole T, Mendelowitz S, Nuckols K, Hohimer C, Lin D, Paganoni S, Walsh C. Restoring arm function with a soft robotic wearable for individuals with amyotrophic lateral sclerosis. Science Translational Medicine. 2023 Feb 1;15(681):eadd1504.
54. Tseng KC, Wang L, Hsieh C, Wong AM. Portable robots for upper-limb rehabilitation after stroke: a systematic review and meta-analysis. Annals of Medicine. 2024 Dec 31;56(1):2337735.
55. Adly AS, Adly AS, Adly MS. Approaches based on artificial intelligence and the internet of intelligent things to prevent the spread of COVID-19: scoping review. Journal of medical Internet research. 2020 Aug 10;22(8):e19104.
56. Albalawi U, Mustafa M. Current artificial intelligence (AI) techniques, challenges, and approaches in controlling and fighting COVID-19: a review. International Journal of Environmental Research and Public Health. 2022 May 12;19(10):5901.
57. Rehman A, Xing H, Hussain M, Hussain A, Gulzar N. Emerging technologies for COVID (ET-CoV) detection and diagnosis: Recent advancements, applications, challenges, and future perspectives. Biomedical Signal Processing and Control. 2023 May 1;83:104642.
58. Ahuja V, Nair LV. Artificial Intelligence and technology in COVID Era: A narrative review. Journal of Anaesthesiology Clinical Pharmacology. 2021 Jan 1;37(1):28-34.
59. Soma S, Narla M, Rajuri N, Gaddam AS, Padi SSV. COVID-19 Vaccination Status and Rational Use of Antibiotics in Women: A Prospective Cross-Sectional Study during the COVID-19 Pandemic in India. J Young Pharm. 2024; 16(3):563-9. doi: 10.5530/jyp.2024.16.70
60. Yi J, Zhang H, Mao J, Chen Y, Zhong H, Wang Y. Review on the COVID-19 pandemic prevention and control system based on AI. Engineering Applications of Artificial Intelligence. 2022 Sep 1;114:105184.
61. Kandukuri A, Pasupulati H, Padi SSV. Orexants, orexin receptor antagonists: Novel therapeutic agents for insomnia disorder. International Neuropsychiatric Disease Journal. 2024; 21 (6):92-108. https://doi.org/10.9734/indj/2024/v21i6457.
62. Sharma S, Rawal R, Shah D. Addressing the challenges of AI-based telemedicine: Best practices and lessons learned. Journal of education and health promotion. 2023 Sep 1(1):338.
63. Blanco-Gonzalez A, Cabezon A, Seco-Gonzalez A, Conde-Torres D, Antelo-Riveiro P, Pineiro A, Garcia-Fandino R. The role of AI in drug discovery: challenges, opportunities, and strategies. Pharmaceuticals. 2023 Jun 18;16(6):891.
64. Lipinski CF, Maltarollo VG, Oliveira PR, Da Silva AB, Honorio KM. Advances and perspectives in applying deep learning for drug design and discovery. Frontiers in Robotics and AI. 2019 Nov 5;6:108.
65. Kumar A, Gadag S, Nayak UY. The beginning of a new era: artificial intelligence in healthcare. Advanced Pharmaceutical Bulletin. 2020 Jul 15;11(3):414.
66. Lamberti MJ, Wilkinson M, Donzanti BA, Wohlhieter GE, Parikh S, Wilkins RG, Getz K. A study on the application and use of artificial intelligence to support drug development. Clinical therapeutics. 2019 Aug 1;41(8):1414-26.
67. Batool M, Ahmad B, Choi S. A structure-based drug discovery paradigm. International journal of molecular sciences. 2019 Jun 6;20(11):2783.
68. Wing K, Oza S, Houlihan C, Glynn JR, Irvine S, Warrell CE, Simpson AJ, Boufkhed S, Sesay A, Vandi L, Sebba SC. Surviving Ebola: A historical cohort study of Ebola mortality and survival in Sierra Leone 2014-2015. PLoS One. 2018 Dec 27;13(12):e0209655.
69. Dance A. Using Machine Learning to Battle Antibiotic Resistance. The Scientist; 2019. Available from: https://www.the-scientist.com/lab-tools/using-machine-learning-to-battle-antibiotic-resistance-65785.  Accessed 28 May 2024.
70. Bilgin GB, Bilgin C, Burkett BJ, Orme JJ, Childs DS, Thorpe MP, Halfdanarson TR, Johnson GB, Kendi AT, Sartor O. Theranostics and artificial intelligence: new frontiers in personalized medicine. Theranostics. 2024;14(6):2367.
71. Weerarathna IN, Kamble AR, Luharia A. Artificial Intelligence Applications for Biomedical Cancer Research: A Review. Cureus. 2023 Nov 5;15(11):e48307. doi: 10.7759/cureus.48307.
72. Li Z, Cai H, Li Z, Ren L, Ma X, Zhu H, Gong Q, Zhang H, Gu Z, Luo K. A tumor cell membrane-coated self-amplified nanosystem as a nanovaccine to boost the therapeutic effect of anti-PD-L1 antibody. Bioactive materials. 2023 Mar 1;21:299-312.
73. Green MR, Manikhas GM, Orlov S, Afanasyev B, Makhson AM, Bhar P, Hawkins MJ. Abraxane®, a novel Cremophor®-free, albumin-bound particle form of paclitaxel for the treatment of advanced non-small-cell lung cancer. Annals of oncology. 2006 Aug 1;17(8):1263-8.
74. Roy S, Meena T, Lim SJ. Demystifying supervised learning in healthcare 4.0: A new reality of transforming diagnostic medicine. Diagnostics. 2022 Oct 20;12(10):2549.
75. Thakur V, Kutty RV. Recent advances in nanotheranostics for triple negative breast cancer treatment. Journal of Experimental & Clinical Cancer Research. 2019 Oct 28;38(1):430.
76. Tan IJ, Podwojniak A, Parikh A, Cohen BA. Precision dermatology: a review of molecular biomarkers and personalized therapies. Current Issues in Molecular Biology. 2024 Mar 30;46(4):2975-90.
77. Prasad M, Lambe UP, Brar B, Shah I, Manimegalai J, Ranjan K, Rao R, Kumar S, Mahant S, Khurana SK, Iqbal HM. Nanotherapeutics: An insight into healthcare and multi-dimensional applications in medical sector of the modern world. Biomedicine & Pharmacotherapy. 2018 Jan 1;97:1521-37.
78. Edis Z, Wang J, Waqas MK, Ijaz M, Ijaz M. Nanocarriers-mediated drug delivery systems for anticancer agents: an overview and perspectives. International journal of nanomedicine. 2021 Feb 17:1313-30.
79. Zhang P, Guo Z, Ullah S, Melagraki G, Afantitis A, Lynch I. Nanotechnology and artificial intelligence to enable sustainable and precision agriculture. Nature Plants. 2021 Jul;7(7):864-76.
80. Hirani R, Noruzi K, Khuram H, Hussaini AS, Aifuwa EI, Ely KE, Lewis JM, Gabr AE, Smiley A, Tiwari RK, Etienne M. Artificial Intelligence and Healthcare: A Journey through History, Present Innovations, and Future Possibilities. Life. 2024 Apr 26;14(5):557.
81. Chandwar K, Misra DP. What does artificial intelligence mean in rheumatology?. Archives of Rheumatology. 2024 Mar;39(1):1.
82. Preiksaitis C, Ashenburg N, Bunney G, Chu A, Kabeer R, Riley F, Ribeira R, Rose C. The Role of Large Language Models in Transforming Emergency Medicine: Scoping Review. JMIR Medical Informatics. 2024 May 10;12:e53787.
83. El Dahdah J, Kassab J, El Helou MC, Gaballa A, Sayles III S, Phelan MP. ChatGPT: a valuable tool for emergency medical assistance. Annals of Emergency Medicine. 2023 Sep 1;82(3):411-3.
84. Knudsen JE, Ghaffar U, Ma R, Hung AJ. Clinical applications of artificial intelligence in robotic surgery. Journal of Robotic Surgery. 2024 Mar 1;18(1):102.
85. Larkins K, Quirke N, Ong HI, Mohamed JE, Heriot A, Warrier S, Mohan H. The deconstructed procedural description in robotic colorectal surgery. Journal of Robotic Surgery. 2024 Mar 30;18(1):147.
86. Preiksaitis C, Rose C. Opportunities, challenges, and future directions of generative artificial intelligence in medical education: scoping review. JMIR medical education. 2023 Oct 20;9:e48785.
87. Arshad HB, Butt SA, Khan SU, Javed Z, Nasir K. Chatgpt and artificial intelligence in hospital level research: potential, precautions, and prospects. Methodist DeBakey Cardiovascular Journal. 2023;19(5):77.
88. Klang E, Sourosh A, Nadkarni GN, Sharif K, Lahat A. Evaluating the role of ChatGPT in gastroenterology: a comprehensive systematic review of applications, benefits, and limitations. Therapeutic Advances in Gastroenterology. 2023 Dec;16:17562848231218618.
89. Clark M, Bailey S. Chatbots in Healthcare: Connecting Patients to Information. Canadian Journal of Health Technologies. 2024 Jan 22;4(1).
90. Madakadze C, McGill SC. Artificial Intelligence–Enhanced Rapid Response Electroencephalography for the Identification of Nonconvulsive Seizure. Canadian Journal of Health Technologies. 2023 Dec 12;3(12).
91. Wojtara M, Rana E, Rahman T, Khanna P, Singh H. Artificial intelligence in rare disease diagnosis and treatment. Clinical and Translational Science. 2023 Nov;16(11):2106-11.
92. Lee EE, Torous J, De Choudhury M, Depp CA, Graham SA, Kim HC, Paulus MP, Krystal JH, Jeste DV. Artificial intelligence for mental healthcare: clinical applications, barriers, facilitators, and artificial wisdom. Biological Psychiatry: Cognitive Neuroscience and Neuroimaging. 2021 Sep 1;6(9):856-64