A New Era of AI Driven Cardiovascular care

Integration of AI in cardiovascular medication management becomes increasingly recognized as an antidote with challenges by adverse drug reactions (ADRs) and drug-drug interactions (DDIs). ADRs have been regarded as one of the significant issues in cardiovascular therapies. According to the studies, up to 30% patients being treated on these medications are affected. Recently, a comprehensive review has reported that machine learning methods can predict the risk of ADRs based on analysis of clinical and omics data by accomplishing a mean validation accuracy of 89.4% using deep learning models. This makes the tool rather fundamental because it will enable clinicians to predict risks from a particular drug regimen, meaning that clinicians may diagnose risk factors linked to a number of drug regimens before experiencing adverse events, hence improving patient safety along with therapeutic results.[1] Further, AI would improve pharmacovigilance through automated coding of ADR reports, thus allowing prioritization of cases for manual review when reporting volumes peak as in the period of influenza outbreaks.[2]

Apart from ADRs, AI also plays a massive role in the management of DDIs, mainly in patients with cardiovascular diseases who most frequently suffer from polypharmacy. Studies have suggested that combinations such as clopidogrel and proton pump inhibitors reduce drug effectiveness quite considerably through interactions that occur at the metabolic level. Thus, AI algorithms will analyze electronic health records and genetic data obtained to better understand a patient's individual response to the treatment being offered. For example, the combination of pharmacogenomics and AI has been shown to optimize warfarin dosing, and therapeutic outcomes are improved.[3] Of particular interest is a recently published report discussing frequency regarding clinically relevant DDGIs that require AI-driven prediction of such interactions. These developments, apart from improving precision in the actual application of cardiovascular therapies, even mitigate risks associated with traditional approaches towards medication management, paving the way for a more customized and effective healthcare paradigm.[4]

Addressing barriers in cardiovascular care is critical, as these obstacles significantly impact patient outcomes and adherence to treatment regimens. High prescription costs, difficult preauthorization procedures, and administrative responsibilities that interfere with direct patient treatment are typical obstacles. According to a poll of cardiologists, 78% of respondents mentioned onerous preauthorization processes that frequently cause delays in critical treatments, and 85% of respondents named cost concerns as the main obstacle.[5] These obstacles not only irritate medical professionals but also lead to unequal access to successful treatments, especially for disadvantaged groups. By improving decision-making skills and optimizing procedures, the incorporation of artificial intelligence (AI) is a viable way to lessen these difficulties. AI can evaluate large datasets to forecast negative drug reactions and enhance patient-specific treatment regimens.

Current Barriers in Cardiovascular Medicine

Factors Associated With Nonadherence to Cardiovascular Medications

Since cardiovascular diseases (CVD) account for a large portion of morbidity and mortality worldwide, effective management and prevention measures are required. Cardiovascular drugs are known to slow the progression of the disease and increase lifespan, but adherence to recommended regimens is still not at its best. According to a recent study, rates vary by prescription class, with approximately 43% of patients not taking their cardiovascular medications as directed. Nonadherence frequently results from both deliberate and inadvertent causes, such as patients' worries about the need for or adverse effects of their medications, as well as from forgetting to take their medications. These actions worsen patient outcomes, raise hospital stays, and raise healthcare expenses. Targeted interventions that emphasize improving patient education, encouraging favorable attitudes about drugs, and removing obstacles to adherence are necessary to address these problems.[6]

With a focus on five domains - social/economic, patient-related, condition-related, therapy-related, and healthcare system-related - the World Health Organization's (WHO) multidimensional model provides a thorough framework for comprehending medication adherence. In this situation, it can be very important to use tools like medication reminders and individualized counseling to address inadvertent nonadherence, such as forgetfulness. In a similar vein, addressing deliberate nonadherence entails changing perceptions regarding the value and security of pharmaceuticals. In order to increase adherence rates, research emphasizes the value of patient-provider contact and suggests tailored, context-sensitive interventions.[7] Utilizing cutting-edge approaches, such patient monitoring and teaching programs powered by artificial intelligence (AI), has the potential to remove these obstacles and revolutionize the provision of cardiovascular care.[8]

Limitations of Fixed Dose Combination in Cardiovascular Care

Although FDC treatment promised to significantly improve medication adherence, several limitations were revealed in the study that counterbalance the usefulness of FDC in broader scenarios and impact. Among the major challenges, a high discontinuation rate was particularly striking: 37% of participants ceased treatment primarily because of side effects such as dizziness, hypotension, and fatigue.[10] This reduces the flexibility of FDC regimens because individual treatment adjustments in terms of either type of drugs or dosages cannot be accommodated, thereby making such treatment less suitable for patients who need tailored therapy. The clinical impact on risk factor control, such as blood pressure and LDL cholesterol levels, was also minimal and not statistically significant even though adherence to prescribed medications was highly improved. Baseline treatment rates may have been already very high, so not much scope remained for quantitative evidence of improvement. The design of an open-label trial may also have introduced bias in assessing treatment intensity or reporting adverse events.[9]

Patient-Reported Barriers

Barriers to medication adherence are prevalent among patients with cardiovascular diseases (CVD), making it challenging to manage conditions like hypertension and hyperlipidemia effectively.[11] The Cardiovascular Intervention Improvement Telemedicine Study (CITIES) explored these barriers through a tailored, telephone-based intervention administered by pharmacists to reduce CVD risk. In a cohort of 428 patients, primarily men (85%) and individuals with both hypertension and hyperlipidemia (64%), the most commonly reported barriers included managing an overwhelming number of medications (31%) and forgetting whether a dose had been taken (24%). Patients who were unemployed (adjusted score: 1.32; 95% CI: 0.50–2.14) or lacked assistance with daily tasks (adjusted score: 1.66; 95% CI: 0.42–2.89) reported significantly higher medication barrier scores. Additionally, those diagnosed solely with hypertension (adjusted score: 0.91; 95% CI: 0.04–1.79) faced greater barriers compared to patients with both conditions. These findings underscore the importance of identifying and addressing specific barriers to enhance medication adherence and optimize CVD management outcomes.[11]

Availability and Affordability

A study by Clara Kayei Chow et al, established that there is a quite big challenge in the availability and affordability of drugs for CVD treatment, particularly in LMICs and LICs. Strong associations were demonstrated between unavailability or unaffordability of drugs and the risk of MACE, even after controlling for sociodemographic, economic, and comorbidity factors.[12] Overall, previous studies uniformly indicated that medicines for CVD have poor availability and inadequate affordability in resource-constrained settings. For instance, a report by van Mourik et al in 2010 indicated that the availability of cardiovascular medicines was only 26.3% within the public sector and 57.3% within private sectors, with the poorest having the highest problems of unaffordability. Similarly, a 2007 survey of Mendis et al found extremely low availability of key medicines, such as hydrochlorothiazide and statins, in LICs and LMICs.[13] Recent studies further point out that though accessibility improved to a small extent, affordability is still high on the list. The issue of affordability is more highlighted in LICs and LMICs wherein vulnerable populations cannot reach brand and generic drugs. These are some factors that reflect the great and urgent need for interventions that not only improve access and affordability of this medicine for CVD but also influence treatment outcomes and survival rates worldwide.[12]

Factors Associated with Nonadherence

A study by Danielle M van der Laan et al., identified several challenges and barriers associated with nonadherence to cardiovascular drugs, many of which were unintentional but also some of which were intentional. The most significant unintentional factors identified were forgetting to take medications, and it was found that patients did not know what to do when they missed a dose. Again, this highlights a key role for HCPs as providers of comprehensive, individualised medication-related information. This includes information about dosage, timing, benefits, side effects, and how to take a missed dose. Although guidelines encourage patient activation, evidence indicates that pharmacy staff often provide minimal information, and potential side effects or difficulties in adhering are rarely discussed.[14]

Intentional nonadherence, related to the patient's beliefs and attitudes about treatment, was the most important barrier as well. An ambivalent attitude—patients balancing concerns about medication use with perceived necessity—was associated with lower rates of adherence. The concern about medications usually outweighs the perceived benefits concerning them and, thus affects adherence behavior. In addition, patients holding indifferent attitudes, characterized by low beliefs in the need for medication and minimal concern, were more likely to be nonadherent. It underscores the need to examine the beliefs of patients and work through their concerns to enhance adherence.[14] Other trends observed by the study involved males, limited resources for remembering, and apathy towards medication use. Notably, complicated medication regimens and comorbidities did not correlate significantly with non-adherence; however, more research might clarify their relationships. To overcome these barriers, HCPs should take into account strategies designed to counter forgetfulness; discussions that make sense for resolving conflicting beliefs; and adequate support to balance patients' concerns with the necessity of taking medication.

Suboptimal Adherence Rates

Rajiv Chowdhury's meta-analysis highlights significant challenges in achieving optimal adherence to cardiovascular medications, which remains a global issue. Suboptimal adherence was prevalent across all types of CVD medications, contributing to approximately 9% of CVD cases in Europe and an absolute risk difference of 13 CVD deaths per 100,000 annually.[16] Factors influencing poor adherence include low social status, health literacy, comorbid conditions, polypharmacy, and barriers such as high medication costs, irregular refills, side effects, and uncertainty about medication effectiveness.[15]

The meta-analysis also emphasizes the "healthy adherer effect," where good adherence may reflect healthier behaviors rather than direct medication benefits, although substantial evidence supports the clinical advantages of adherence. For instance, adherence to statin therapy resulting in a 1 mmol/L reduction in LDL cholesterol over four years corresponds to a 13% reduction in all-cause mortality. Nonadherence can lead to intensified treatment, adverse effects, misdiagnoses, and unnecessary interventions, further exacerbating health outcomes.[17] Global disparities in adherence are stark, with much lower rates observed in low- and middle-income countries (LMICs) due to high out-of-pocket expenses, limited medication availability, and fragile healthcare systems. The findings underscore the urgent need for cost-effective strategies to improve adherence and emphasize the importance of integrating adherence interventions into healthcare systems to maximize the benefits of cardiovascular therapies worldwide.[15-17]

Access Barriers in Low-Income Settings

Access to cardiovascular medications is significantly hindered in low-income countries due to factors such as low availability, high costs, and lack of insurance coverage. According to a study conducted in India and Ghana, patients with atherosclerotic cardiovascular disease (ASCVD) reported that the cost of medications and limited access to healthcare facilities were critical barriers affecting their adherence.[18] The study emphasized that patients often relied on alternative medications due to distrust in the healthcare system, which further complicates adherence to prescribed treatments. The findings suggest that strengthening healthcare systems and improving access to affordable medications are essential for enhancing patient outcomes in these regions.[18]

Physician Challenges:

This study has identified several challenges in the assessment, treatment, and management of cardiovascular (CV) risk factors. The most important barriers in this regard include poor adherence, suboptimal patient-physician communication, and complex comorbidities. Among cardiologists surveyed, 70% referred inadequate quality of referral from PCPs, frequently returning too early, too late, or devoid of critical clinical information. Consequently, cardiology evaluations of CV risk factors often end up as a premature assessment, hence delaying necessary interventions by cardiologists.[19,20]

Patient compliance was still a significant problem. In fact, 76% of cardiologists believed that inadequate patient knowledge of their condition and low commitment to risk-reducing behaviors are important barriers. Treatment costs and intricate drug regimens were the other factors that added to compliance problems.[21] Elderly patients and those having comorbidities were more difficult to manage mainly because of increased risk of drug interactions and adverse effects. Drug side effects, such as hypotension or cognitive impairment for example, are also cited by cardiologists to deter patients from adhering to recommended therapies. Clinical guidelines, though considered essential, were criticized by 65% of cardiologists for being overly simplistic and not accommodating patient-specific complexities. Deviations from guidelines were common, with cardiologists adopting more aggressive or individualized approaches for patients with highrisk profiles or unique comorbidities.[21,22] These findings emphasize the urgent need for systemlevel reforms, improved interprofessional communication, and targeted educational interventions to address these gaps and enhance patient outcomes.

COM-B Model of Behavior

From investigations done on the basis of COM-B model, which means Capability, Opportunity, Motivation - Behaviour, several important barriers that affect the adherence of patients to medication have been said. The first is that from a study by Pallavi Mishra et al. in the year 2021, who reported understanding of a patient's condition and treatment options as an important barrier to patient adherence to medication regimes. Many patients do not understand their cardiovascular disease well, causing them to be confused about how seriously they should take their treatments. Furthermore, following complicated medication schedules is also a barrier to adherence for those with multiple prescriptions. Vacations also interfere with medication routines, leading to missed doses.[23]

Opportunity barriers then further complicate adherence; the cost of the medications themselves is a major problem, as many patients report inability to afford necessary treatments due to monetary limitations. Largely inadequate coverage by insurance further compounds access problems and makes treatment unaffordable to the patient. For example, lack of access to pharmacies or healthcare settings can negatively impact adherence; in low-resource settings, for instance, patients may be handicapped by long distances to pharmacies or over extended waits to gain access to prescriptions.[24-25]

Motivational barriers also play a role, including the patient's beliefs regarding the treatment efficacy. For example, if patients do not think that their medications are effective, or fear possible side effects, they may not see a strong motivation to adhere to their regimens. Expectations related to the results of the treatment also have a motivating effect. In case the patients do not see tangible benefits from their use, they may stop taking their medications. Mood swings and psychosocial stress can also result in decreased levels of motivation and combined non-adherence. In summary, all these interrelated problems prove that complying with cardiovascular medication schemes is a hard procedure for patients and that new interventions particular to such challenges are needed (Mishra et al., 2021).[23-26]

Long-Term Use of Cardiovascular Drugs: 

The long-term use of commonly prescribed cardiovascular drugs involves some issues, mainly related to interactions of polypharmacy and the reality that only a few have been tested using extensive clinical trial data over long periods.[27] A study of four of the most commonly prescribed cardiovascular drug classes-aspirin, statins, beta-blockers, and angiotensin-converting enzyme (ACE) inhibitors-found that although crucial to the management of post-myocardial infarction cardiovascular diseases, there is a challenging gap in knowledge about their long-term effects. Specifically, evidence drawn from RCTs generally does not extend more than a few years of follow-up, yet patients are often put on these drugs for decades. Important questions about safety and efficacy of long-term treatment now arise, especially for older patients who are often treated with multiple medications.[27]

According to the study, polypharmacy tends to occur significantly among the elderly, who suffer cardiovascular diseases.[28] Indeed, 82% of such patients are said to be on multiple drugs. The risks triggered by polypharmacy include increased potential for adverse drug reactions and drugdrug interactions plus complications such as acute kidney injury. Indeed, the study revealed that the practice currently lacks sufficient evidence in respect to the withdrawal of these drugs after long consumption, which may bring about avoidable medication burdens and health risks.[29] 

 

 

Figure 1: Challenges in Cardiovascular Medicine

This table summarizes key AI tools used in cardiovascular medicine, detailing the data sources utilized, their primary applications, how they function, and corresponding citation references. It highlights advancements in risk prediction, treatment personalization, diagnostic accuracy, and patient-physician communication driven by various machine learning and AI technologies.

 Challenges in Integrating AI into Cardiovascular Medicine

Ethical and legal hurdles to integrate AI into cardiovascular medicine are necessary in ensuring its proper implementation. Issues of privacy and data security will play a prominent role because most of the AI would be sensitive in terms of the data available to them. According to one study, "Concerns related to data privacy and security remain key inhibitors to trust in AI-enabled healthcare, with both providers and patients worried about breaches of confidentiality and misuse of their personal health information.".[57] In addition, accountability and transparency questions arise from the ethical implications of algorithms making decisions. Many clinicians are wary of the transparency that may be linked with coming up with decisions by AI algorithms. Such lack in transparency breeds general distrust in these technologies. Furthermore, the lack of more robust regulatory frameworks addressing the ethical use of AI in clinical settings thus could alleviate some of these concerns.[58]

Technical barriers also restrict the spread of AI in cardiovascular medicine, particularly with regards to data quality and representation. Most AI models have been developed to use enormous datasets that very often are incomplete or otherwise inherently biased, reducing their validity and generalizability across a population. There is a natural need to train and validate the model; most healthcare institutions do not have the infrastructure and resources to support this process. It was discovered that sometimes, the introduction of AI tools may cause difficulties with integration in EHR systems due to interoperability problems. This would result in inconsistent data presentation and reduce the usability level. This further emphasizes the need for standardized protocols so as to allow effective integration of AI tools in clinical practice.[59]

Economic and infrastructural hindrances are significant barriers to the integration of AI in cardiovascular care. The cost of developing AI technologies is usually prohibitively expensive for healthcare providers to undertake investments in such technologies, especially in scarce resource settings. Additionally, the greatest deficit of professionals trained in AI by professionals in healthcare settings highlights the challenges of adopting advanced technologies.[60] A mixedmethods study found that, although a significant number of cardiologists believe that AI tools could be of potential value, resistance to their use remains mainly based on lack of knowledge and training. These economic and infrastructural barriers must be overcome if the environment for AI to flourish is to be established within cardiovascular medicine.

CONCLUSION

The integration of AI in cardiovascular medicine promises to be one major advance in overcoming the limitations presented by ADRs, DDIs, and adherence-related issues. Deep learning models achieve mean validation accuracy of as high as 89.4% in AI-powered systems for predicting ADRs. This possibility ensures that clinicians could proactively measure against specific drug regimens raising individual risks and contribute to better patient safety and therapeutic outcome. AI further involves significant improvements in managing DDIs, particularly to cardiovascular patients, who are mainly exposed to polypharmacy. The AI models adapt drug dosage and treatment plans based on the analysis of electronic health records as well as integration of pharmacogenomic data to minimize the risk of inefficacy and adverse interactions. AI tools have also been great promises in overcoming high prescription costs, complex preauthorization processes, and geographic disparities to ensure equitable access.

The multifaceted potential of AI is also improved adherence to medication through specific interventions or reminders and addressing unintentional nonadherence in adding shifts on the perspectives of patients toward treatment. Algorithms in machine learning, like Random Forest, Gradient Boosting Machines, and Neural Networks, have been shown to be effective in predicting greater accuracy in cardiovascular risks than traditional methods; technologies now form robust frameworks for early detection, personalized care, and better clinical decision-making. Some of these challenges, such as data privacy, technical integration, and economic constraints, remain; however, they all speak to the need for systemic reforms and investment. Infrastructural deficits coupled with ethical implementation of AI will be crux to harnessing AI's full potential in the transformation of cardiovascular care. In the ultimate analysis, it is application of AI in cardiovascular medicine bringing benefits in terms of improved clinical outcomes while heralding a new paradigm in precision and efficiency in health delivery.

ACKNOWLEDGEMENT

I extend my sincere gratitude to Dr. Venkateswaramurthy.N, Head of the Department, in the Department of Pharmacy Practice, for his invaluable support and contributions to this review. His expert guidance, thoughtful advice, and unwavering encouragement were pivotal in the successful completion of this work. This endeavor would not have been possible without his mentorship.

Conflicting Interests: The authors declared no potential conflicts of interest.

Funding sources: None

REFERENCES

1. Mohsen A, Tripathi LP, Mizuguchi K. Deep Learning Prediction of Adverse Drug Reactions in Drug Discovery Using Open TG–GATEs and FAERS Databases. Frontiers in Drug Discovery. 2021;1. doi:https://doi.org/10.3389/fddsv.2021.768792
2. Martin GL, Jouganous J, Savidan R, et al. Validation of Artificial Intelligence to Support the Automatic Coding of Patient Adverse Drug Reaction Reports, Using Nationwide Pharmacovigilance Data. Drug Saf. 2022;45(5):535-548. doi:10.1007/s40264-022-011538
3. Mathur P, Srivastava S, Xu X, Mehta JL. Artificial Intelligence, Machine Learning, and Cardiovascular Disease. Clin Med Insights Cardiol. 2020;14:1179546820927404. Published 2020 Sep 9. doi:10.1177/1179546820927404
4. Zhang Y, Deng Z, Xu X, Feng Y, Junliang S. Application of Artificial Intelligence in DrugDrug Interactions Prediction: A Review. J Chem Inf Model. 2024;64(7):2158-2173. doi:10.1021/acs.jcim.3c00582
5. Wilkinson MJ, Lepor NE, Michos ED. Evolving Management of Low‐Density Lipoprotein Cholesterol: A Personalized Approach to Preventing Atherosclerotic Cardiovascular Disease Across the Risk Continuum. Journal of the American Heart Association. 2023;12(11). doi:https://doi.org/10.1161/jaha.122.028892
6. van der Laan DM, Elders PJM, Boons CCLM, Nijpels G, Hugtenburg JG. Factors Associated With Nonadherence to Cardiovascular Medications: A Cross-sectional Study. J Cardiovasc Nurs. 2019;34(4):344-352. doi:10.1097/JCN.0000000000000582
7. Kuntz JL, Safford MM, Singh JA, et al. Patient-centered interventions to improve medication management and adherence: a qualitative review of research findings. Patient Educ Couns. 2014;97(3):310-326. doi:10.1016/j.pec.2014.08.021
8. Khera R, Khera R, Khera R, et al. Transforming Cardiovascular Care With Artificial Intelligence: From Discovery to Practice. Journal of the American College of Cardiology. 2024;84(1):97-114. doi:https://doi.org/10.1016/j.jacc.2024.05.003
9. Selak V, Elley CR, Bullen C, et al. Effect of fixed dose combination treatment on adherence and risk factor control among patients at high risk of cardiovascular disease: randomised controlled trial in primary care. BMJ. 2014;348(may27 11):g3318-g3318. doi:https://doi.org/10.1136/bmj.g3318
10. Yusuf S, Islam S, Chow CK, et al. Use of secondary prevention drugs for cardiovascular disease in the community in high-income, middle-income, and low-income countries (the PURE Study): a prospective epidemiological survey. Lancet. 2011;378(9798):1231-1243. doi:10.1016/S0140-6736(11)61215-4
11. Zullig LL, Stechuchak KM, Goldstein KM, et al. Patient-reported medication adherence barriers among patients with cardiovascular risk factors. J Manag Care Spec Pharm. 2015;21(6):479-485. doi:10.18553/jmcp.2015.21.6.479
12. Chow CK, Nguyen TN, Marschner S, et al. Availability and affordability of medicines and cardiovascular outcomes in 21 high-income, middle-income and low-income countries. BMJ Global Health. 2020;5(11):e002640. doi:https://doi.org/10.1136/bmjgh-2020-002640
13. Khatib R, McKee M, Shannon H, et al. Availability and affordability of cardiovascular disease medicines and their effect on use in high-income, middle-income, and low-income countries: an analysis of the PURE study data. Lancet. 2016;387(10013):61-69. doi:10.1016/S0140-6736(15)00469-9
14. van der Laan DM, Elders PJM, Boons CCLM, Nijpels G, Hugtenburg JG. Factors Associated With Nonadherence to Cardiovascular Medications: A Cross-sectional Study. J Cardiovasc Nurs. 2019;34(4):344-352. doi:10.1097/JCN.0000000000000582
15. Chowdhury R, Khan H, Heydon E, et al. Adherence to cardiovascular therapy: a metaanalysis of prevalence and clinical consequences. European Heart Journal. 2013;34(38):2940-2948. doi:https://doi.org/10.1093/eurheartj/eht295
16. Cutler DM, Everett W. Thinking outside the pillbox--medication adherence as a priority for health care reform. N Engl J Med. 2010;362(17):1553-1555. doi:10.1056/NEJMp1002305
17. Walsh CA, Cahir C, Tecklenborg S, Byrne C, Culbertson MA, Bennett KE. The association between medication non-adherence and adverse health outcomes in ageing populations: A systematic review and meta-analysis. Br J Clin Pharmacol. 2019;85(11):2464-2478. doi:10.1111/bcp.14075
18. Mishra P, Vamadevan AS, Roy A, et al. Exploring Barriers to Medication Adherence Using COM-B Model of Behaviour Among Patients with Cardiovascular Diseases in Low- and Middle-Income Countries: A Qualitative Study. Patient Prefer Adherence. 2021;15:1359-1371. Published 2021 Jun 23. doi:10.2147/PPA.S285442

19. Hayes SM, Dupuis M, Murray S. Issues and challenges in the assessment, diagnosis and treatment of cardiovascular risk factors: Assessing the needs of cardiologists. BMC Medical Education. 2008;8(1). doi:https://doi.org/10.1186/1472-6920-8-30
20. Fletcher GF, Balady GJ, Vogel RA. Preventive cardiology: How can we do better? J Am Coll Cardiol. 2002;40(4):579-651.
21. Staessen JA, Wang JG, Thijs L. Cardiovascular protection and blood pressure reduction: A meta-analysis. Lancet. 2001;358(9290):1305-1315.
22. LaRosa JC, He J, Vupputuri S. Effect of statins on risk of coronary disease: A meta-analysis of randomized controlled trials. JAMA. 1999;282(24):2340-2346.
23. Mishra P, Vamadevan A, Roy A, et al. Exploring barriers to medication adherence using COM-B model of behavior among patients with cardiovascular diseases in low- and middle-income countries. BMC Public Health. 2021;21(1):1-10. doi:10.1186/s12889-02110776-4. 
24. Kaur H, Gupta S, Bansal R, et al. Patient and provider's perspective on barriers and facilitators for medication adherence among patients with cardiovascular diseases and diabetes mellitus in India: a systematic review of qualitative studies. BMJ Open. 2022;12(1):e052907. doi:10.1136/bmjopen-2021-052907. 
25. Hamine S, Gerth-Guyette E, Faulx D, et al. The role of mHealth for improving medication adherence in patients with cardiovascular disease: a systematic review. J Am Coll Cardiol. 2016;67(23):2870-2880. doi:10.1016/j.jacc.2016.04.028. 
26. Bansal R, Kaur H, Gupta S, et al. Barriers to medication adherence among patients with coronary heart disease: a qualitative study using the COM-B model framework. BMC Cardiovasc Disord. 2022;22(1):1-10. doi:10.1186/s12872-022-02577-9. 
27. Rossello X, Pocock SJ, Julian DG. Long-Term Use of Cardiovascular Drugs: Challenges for Research and for Patient Care. J Am Coll Cardiol. 2015;66(11):1273-1285. doi:10.1016/j.jacc.2015.07.0183
28. Patel S, Kumar M, Beavers CJ, Karamat S, Alenezi F. Polypharmacy and Cardiovascular Diseases: Consideration for Older Adults and Women. Curr Atheroscler Rep.

2022;24(10):813-820. doi:10.1007/s11883-022-01055-1

29. Morris AH, Ioannidis JPA. Limitations of medical research and evidence at the patientclinician encounter scale. Chest. 2013;143(4):1127-1135. doi:10.1378/chest.12-1908
30. Grant JK, Javaid A, Carrick RT, et al. Digital health innovation and artificial intelligence in cardiovascular care: a case-based review. NPJ Cardiovasc Health. 2024;1:26. doi:10.1038/s44325-024-00020-y.
31. Eng D, Lessmann N, de Vos BD, et al. Automated coronary calcium scoring using deep learning with multicenter external validation. NPJ Digit Med. 2021;4:88. doi:10.1038/s41746-021-00443-8.
32. Marvel FA, Grant JK, Martin SS. Clinician decision support tools: advances in lipidlowering treatment intensification. Circulation. 2024;17. doi:10.1161/CIRCULATIONAHA.123.010884.
33. Narang A, Ouyang D, Rajpurkar P, et al. Utility of a deep-learning algorithm to guide novices to acquire echocardiograms for limited diagnostic use. JAMA Cardiol. 2021;6(6):624-632. doi:10.1001/jamacardio.2021.0346.
34. Friedrich S, Groß S, König IR, et al. Applications of artificial intelligence/machine learning approaches in cardiovascular medicine: a systematic review with recommendations. Eur

Heart J Digit Health. 2021;2(3):424-436. Published 2021 Jun 8. doi:10.1093/ehjdh/ztab054

35. Wang C, Zhao Y, Jin B, et al. Development and Validation of a Predictive Model for Coronary Artery Disease Using Machine Learning. Front Cardiovasc Med. 2021;8:614204. Published 2021 Feb 2. doi:10.3389/fcvm.2021.614204
36. Gautam N, Mueller J, Alqaisi O, et al. Machine Learning in Cardiovascular Risk Prediction and Precision Preventive Approaches. Curr Atheroscler Rep. 2023;25(12):1069-1081. doi:10.1007/s11883-023-01174-3
37. Weng SF, Reps J, Kai J, Garibaldi JM, Qureshi N. Can machine-learning improve cardiovascular risk prediction using routine clinical data?. PLoS One. 2017;12(4):e0174944. Published 2017 Apr 4. doi:10.1371/journal.pone.0174944
38. Golpour P, Ghayour-Mobarhan M, Saki A, et al. Comparison of Support Vector Machine, Naïve Bayes and Logistic Regression for Assessing the Necessity for Coronary Angiography. Int J Environ Res Public Health. 2020;17(18):6449. Published 2020 Sep 4. doi:10.3390/ijerph17186449
39. Zhou X, Li X, Zhang Z, et al. Support vector machine deep mining of electronic medical records to predict the prognosis of severe acute myocardial infarction. Front Physiol. 2022;13:991990. Published 2022 Sep 29. doi:10.3389/fphys.2022.991990
40. Unnikrishnan P, Kumar DK, Poosapadi Arjunan S, Kumar H, Mitchell P, Kawasaki R. Development of Health Parameter Model for Risk Prediction of CVD Using SVM. Comput Math Methods Med. 2016;2016:3016245. doi:10.1155/2016/3016245
41. Weng SF, Reps J, Kai J, Garibaldi JM, Qureshi N. Can machine-learning improve cardiovascular risk prediction using routine clinical data?. PLoS One. 2017;12(4):e0174944. Published 2017 Apr 4. doi:10.1371/journal.pone.0174944
42. Javaid A, Zghyer F, Kim C, et al. Medicine 2032: The future of cardiovascular disease prevention with machine learning and digital health technology. Am J Prev Cardiol.2022;12:100379. Published 2022 Aug 29. doi:10.1016/j.ajpc.2022.100379
43. Baghdadi NA, Mohammed S, Malki A, Gad I, Ewis AA, El-Sayed Atlam. Advanced machine learning techniques for cardiovascular disease early detection and diagnosis. Journal of Big Data. 2023;10(1). doi:https://doi.org/10.1186/s40537-02300817-1
44. Kar E, Masoud Fakhimi, Turner C, Tillal Eldabi. Hybrid simulation in healthcare: a systematic exploration of models, applications, and emerging trends. Journal of Simulation.          Publihed          online May     19,       2024:1-19. i:https://doi.org/10.1080/17477778.2024.2354250
45. Yi J, Wang L, Song J, et al. Development of a machine learning-based model for predicting individual responses to antihypertensive treatments. Nutr Metab Cardiovasc Dis. 2024;34(7):1660-1669. i:10.1016/j.numecd.2024.02.014
46. Zhu H, Qiao S, Zhao D, et al. Machine learning model for cardiovascular disease prediction in patients with chronic kidney disease. Front Endocrinol (Lausanne). 2024;15:1390729. Published 2024 May 28. doi:10.3389/fendo.2024.1390729
47. Elyamani HA, Salem MA, Farid Melgani, Yhiea NM. Deep residual 2D convolutional neural network for cardiovascular disease classification. Scientific Reports. 2024;14(1). doi:https://doi.org/10.1038/s41598-024-72382-3
48. Mathur P, Srivastava S, Xu X, Mehta JL. Artificial Intelligence, Machine Learning, and Cardiovascular Disease. Clin Med Insights Cardiol. 2020;14:1179546820927404. Published 2020 Sep 9. doi:10.1177/1179546820927404
49. Haq IU, Chhatwal K, Sanaka K, Xu B. Artificial Intelligence in Cardiovascular Medicine: Current Insights and Future Prospects. Vasc Health Risk Manag. 2022;18:517-528. Published 2022 Jul 12. doi:10.2147/VHRM.S279337
50. Warner JJ, Crook HL, Whelan KM, et al. Improving Cardiovascular Drug and Device Development and Evidence Through Patient-Centered Research and Clinical Trials. Circulation: Cardiovascular Quality and Outcomes. 2020;13(7). doi: https://doi.org/10.1161/circoutcomes.120.006606
51. Moore A, Bell M. XGBoost, A Novel Explainable AI Technique, in the Prediction of Myocardial Infarction: A UK Biobank Cohort Study. Clin Med Insights Cardiol. 2022;16:11795468221133611. Published 2022 Nov 8. doi:10.1177/11795468221133611
52. Lee J, Choi Y, Ko T, Lee K, Shin J, Kim HS. Prediction of Cardiovascular Complication in Patients with Newly Diagnosed Type 2 Diabetes Using an XGBoost/GRU-ODE-BayesBased Machine-Learning Algorithm. Endocrinol Metab (Seoul). 2024;39(1):176-185. doi:10.3803/EnM.2023.1739
53. Fuadah YN, Qauli AI, Pramudito MA, Marcellinus A, Hanum UL, Lim KM. A stacking ensemble machine learning model for evaluating cardiac toxicity of drugs based on in silico biomarkers. CPT Pharmacometrics Syst Pharmacol. Published online August 26, 2024.

doi:10.1002/psp4.13229

54. Zhu H, Qiao S, Zhao D, et al. Machine learning model for cardiovascular disease prediction in patients with chronic kidney disease. Front Endocrinol (Lausanne). 2024;15:1390729. Published 2024 May 28. doi:10.3389/fendo.2024.1390729
55. Cicha I. The Grand Challenges in Cardiovascular Drug Delivery. Frontiers in Drug Delivery. 2021;1. doi:https://doi.org/10.3389/fddev.2021.784731
56. Jamal S, Ali W, Nagpal P, Grover S, Grover A. Computational models for the prediction of adverse cardiovascular drug reactions. J Transl Med. 2019;17(1):171. Published 2019 May 22. doi:10.1186/s12967-019-1918-z
57. Mooghali M, Stroud AM, Dong Whi Yoo, et al. Trustworthy and ethical AI-enabled cardiovascular care: a rapid review. BMC Medical Informatics and Decision Making. 2024;24(1). doi:https://doi.org/10.1186/s12911-024-02653-6
58. Zargarzadeh A, Javanshir E, Ghaffari A, Mosharkesh E, Anari B. Artificial intelligence in cardiovascular medicine: An updated review of the literature. J Cardiovasc Thorac Res. 2023;15(4):204-209. doi:10.34172/jcvtr.2023.33031
59. Quer G, Topol EJ. The potential for large language models to transform cardiovascular medicine. The Lancet Digital Health. 2024;6(10):e767-e771. doi:https://doi.org/10.1016/s2589-7500(24)00151-1
60. Ashinze P, Akande E, Chukwu Bethrand, et al. Artificial intelligence: transforming cardiovascular healthcare in Africa. The Egyptian Heart Journal. 2024;76(1). doi:https://doi.org/10.1186/s43044-024-00551-w