Artificial intelligence in cardiovascular risk management: from digital medical history to personalized therapy

Czech version

Authors: Štefan Tóth ¹; Patrik Buček ¹; Adriána Jarolímková ²; Pavol Fulop ³; Mariana Dvorožňáková ³; Tibor Porubän ³; Marianna Barbierik Vachalcová ³; Natália Vaňová ⁴
Authors‘ workplace: Kardiologická ambulancia, Kardiocomp s. r. o., Košice ¹; Klinika všeobecného lekárstva UPJŠ LF a Nemocnice AGEL Košice-Šaca a. s. ²; Kardiologická klinika UPJŠ LF a VÚSCH, a. s., Košice ³; Interná klinika UPJŠ LF a Nemocnice AGEL Košice-Šaca a. s. ⁴
Published in: AtheroRev 2026; 11(1): 57-63
Category: Reviews

Overview

Artificial intelligence (AI) is a rapidly developing tool with significant potential to improve the management of patients with cardiovascular (CV) risk. The aim of this review is to summarize and critically evaluate the latest findings from 2020–2025 on the use of AI in the care of high-risk cardiology patients, focusing on atherosclerosis, arterial hypertension, dyslipidemia, and comprehensive CV risk assessment. We begin by pointing out the current systemic challenges facing European healthcare, including the overload of outpatient care, long waiting times, growing administrative burdens, and the inefficient use of doctors’ time. We then analyze the main areas of AI application in cardiology: automated collection of anamnestic and symptomatic data through chatbots and digital assistants, AI-supported risk stratification and prediction of CV events, personalized management of hyperlipidemia, including the identification of high-risk individuals and optimization of hypolipidemic treatment, as well as the use of AI in the management of hypertension in blood pressure measurement, therapy selection, and adherence support. Special attention is paid to complex AI systems for clinical decision support and remote patient monitoring. A review of available studies points to the higher accuracy of AI models compared to traditional methods in predicting CV risk, the ability of AI to identify subclinical atherosclerosis in imaging tests, and the potential of machine learning in individualizing treatment. In conclusion, we note that properly integrated AI can significantly contribute to more effective prevention and treatment of CV diseases, reducing the burden on the healthcare system and improving patient prognosis. However, key challenges for its routine clinical use remain high-quality clinical validation, personal data protection, algorithm transparency, and ensuring the ethical and explainable use of AI in medicine.

Keywords:

artificial intelligence – hypertension – Atherosclerosis – dyslipidemia – personalized medicine – cardiovascular risk – clinical decision support

Sources

1. OECD/European Commission. Health at a Glance: Europe 2024. State of Health in the EU Cycle. OECD Publishing. Paris. Dostupné z DOI: <https://doi.org/10.1787/b3704e14en>.
2. Sinsky C, Colligan L, Li L et al. Allocation of physician time in ambulatory practice: A time and motion study in 4 specialties. Ann Intern Med 2016; 165(11): 753–760. Dostupné z DOI: <https://doi.org/10.7326/ M16–0961>.
3. Sasseville M, Yousefi F, Ouellet S et al. The impact of AI scribes on streamlining clinical documentation: A systematic review. Healthcare (Basel) 2025; 13(12): 1447. Dostupné z DOI: <https://doi.org/10.3390/ healthcare13121447>.
4. Toth S, Turek M, Pella D. Success in achieving LDLC target values in a highrisk population in Slovakia: the SlovakLipid retrospective study. Arch Med Sci 2023; 21(3): 738–746. Dostupné z DOI: <https://doi.org/10.5114/ aoms/170961>.
5. Mathur P, Srivastava S, Xu X et al. Artificial Intelligence, Machine Learning, and Cardiovascular Disease. Clin Med Insights Cardiol 2020; 14 : 1179546820927404. Dostupné z DOI: <https://doi. org/10.1177/1179546820927404>.
6. Hindelang M, Zink A, Egeberg A. Transforming health care through chatbots for medical history–taking and future directions: Comprehensive systematic review. JMIR Med Inform 2024; 12: e56628.Dostupné z DOI: <https://doi.org/10.2196/56628>.
7. Pearlman K, Wan W, Shah SD et al. Use of an AI scribe and electronic health record efficiency. JAMA Network Open 2025; 8(10): e2537000. Dostupné z DOI: <https://doi.org/10.1001/jamanetworkopen.2025.37000>.
8. Olson KD, Patel SV, Ryu S. Use of ambient AI scribes to reduce administrative burden and professional burnout. JAMA Network Open 2025; 8(10): e2534976. Dostupné z DOI: <https://doi.org/10.1001/ jamanetworkopen.2025.34976>.
9. UCLA Health. UCLA study finds AI scribes may reduce documentation time and improve physician wellbeing. UCLA Health Newsroom 2025. Dostupné z WWW: <https://www.uclahealth.org/news/release/ uclastudyfindsaiscribesmayreducedocumentationtime>.
10. American Medical Association. 2025. AI scribes save 15,000 hours —⁠ and restore the human side of medicine. Dostupné z WWW: <https://www.amaassn.org/practicemanagement/digitalhealth/ aiscribessave15000hoursandrestorehumansidemedicine>.
11. Chen S, Eagan B, Chen M. The impact of responding to patient messages with large language models. arXiv preprint arXiv 2023; 2310.17703. Dostupné z DOI: <https://doi.org/10.48550/arXiv.2310.17703>.
12. Ridker PM, Bhatt DL, Pradhan AD et al. Inflammation and cholesterol as predictors of cardiovascular events among patients receiving statin therapy: A collaborative analysis of three randomized trials. The Lancet 2023; 401(10384): 1293–1301. Dostupné z DOI: <https://doi.org/10.1016/ S0140–6736(23)00215–5>.
13. Cai Y, Cai YO, Tang LY et al. Artificial intelligence in the risk prediction models of cardiovascular disease and development of an independent validation screening tool: a systematic review. BMC Med 2024; 22(1): 56. Dostupné z DOI: <https://doi.org/10.1186/s12916–024–03273–7>
14. Nogimori Y, Sato K, Takamizawa K et al. Prediction of adverse cardiovascular events in children using artificial intelligencebased electrocardiogram. Int J Cardiol 2024; 406 : 132019. Dostupné z DOI: <https://doi.org/10.1016/j.ijcard.2024.132019>.
15. Agarbattiwala MM, Iqbalbhai SA, Patel P. Comparative study of artificial intelligencedriven diagnostic models and traditional risk scores in predicting cardiovascular events. Eur J Cardiovasc Med 2025; 15(4): 323–326. Dostupné z DOI: <http://dx.doi.org/10.61336/ejcm/25–04–60>.
16. Bibi I, Schaffert D, Blanke P et al. Cardiovascular risk assessment enhanced by automated machine learning in a multiphase study. Sci Rep 2025; 15(1): 36474. Dostupné z DOI: <https://doi.org/10.1038/ s41598–025–24189z>.
17. GonzalezFranco JD, GalavizMosqueda A, VillarrealReyes S et al. Revolutionizing cardiac risk assessment: AIpowered patient segmentation using advanced machine learning techniques. Mach Learn Knowl Extr 2025; 7(2): 46. Dostupné z DOI: <https://doi.org/10.3390/make7020046>.
18. Li A, Wang Y, Chen H. AI driven cardiovascular risk prediction using NLP and Large Language Models for personalized medicine in athletes. SLAS Technol 2025; 32 : 100286. Dostupné z DOI: <https://doi.org/10.1016/j. slast.2025.100286>.
19. Gallone G, Belmonte M, Conte E. Detection of subclinical atherosclerosis by imagebased deep learning on chest radiographs. Eur Heart J Digit Health 2025; 6(4): 567–576. Dostupné z DOI: <https://doi.org/10.1093/ ehjdh/ztaf033>.
20. Weiss J, Raghu VK, Bontempi D et al. Deep learning to estimate cardiovascular risk from chest radiographs: A risk prediction study. Ann Intern Med 2024; 177(4): 409–417. Dostupné z DOI: <https://doi.org/10.7326/ M23–1898>.
21. Steinfeldt J, Buergel T, Loock L et al. Neural networkbased integration of polygenic and clinical information: development and validation of a prediction model for 10year risk of major adverse cardiac events in the UK Biobank cohort. Lancet Digit Health 2022; 4(2): e84–e94. Dostupné z DOI: <https://doi.org/10.1016/S2589–7500(21)00249–1>.
22. Paquette M, Trinder M, Ruel I et al. Polygenic risk score for coronary artery disease predicts atherosclerotic cardiovascular disease in familial hypercholesterolemia. J Clin Lipidol 2025; 19(3): 595–604. Dostupné z DOI: <https://doi.org/10.1016/j.jacl.2025.01.004>.
23. Zamora A, Masana L, Civeira F et al. Prognostic stratification of familial hypercholesterolaemia patients using AI algorithms: a genderspecific approach. Eur Heart J Digit Health 2025; 6(6): 1113–1123. Dostupné z DOI: <https://doi.org/10.1093/ehjdh/ztaf092>.
24. Carter SV, Triana T, Basit M et al. Performance of the FINDFH machine learning algorithm for the identification of individuals with suspected familial hypercholesterolemia. J Clin Lipidol 2025; 19(4):1037–1043. Dostupné z DOI: <https://doi.org/10.1016/j.jacl.2025.06.009>.
25. Luo RF, Wang JH, Hu LJ et al. Applications of machine learning in familial hypercholesterolemia. Front Cardiovasc Med 2023; 10 : 1237258. Dostupné z DOI: <https://doi.org/10.3389/fcvm.2023.1237258>.
26. Mohammadnia N, Akyea RK, Qureshi N et al. Electronic health recordbased facilitation of familial hypercholesterolaemia detection sensitivity of different algorithms in genetically confirmed patients. Eur Heart J Digit Health 2022; 3(4): 578–586. Dostupné z DOI: <https://doi. org/10.1093/ehjdh/ztac059>.
27. Osei J, Razavi AC, Otchere B et al. A Scoping Review of Electronic Health RecordsBased Screening Algorithms for Familial Hypercholesterolemia. JACC Adv 2024; 3(12): 101297. Dostupné z DOI: <https://doi.org/10.1016/j.jacadv.2024.101297>.
28. Meng JB, An ZJ, Jiang CS. Machine learningbased prediction of LDL cholesterol: Performance evaluation and validation. PeerJ 2025; 13: e19248. Dostupné z DOI: <https://doi.org/10.7717/peerj.19248>.
29. Xiong Y, Liu X, Wang Q et al. Machine learningbased prediction model for the efficacy and safety of statins. Front Pharmacol 2024; 15 : 1334929. Dostupné z DOI: <https://doi.org/10.3389/fphar.2024.1334929>.
30. Stergiou GS, Mukkamala R, Avolio A et al. Cuffless blood pressure measuring devices: Review and statement by the European Society of Hypertension Working Group on Blood Pressure Monitoring and Cardiovascular Variability. J Hypertens 2022; 40(8): 1449–1460. Dostupné z DOI: <https:// doi.org/10.1097/HJH.0000000000003224>.
31. Elgendi M, Fletcher R, Ward R. Recommendations for evaluating photoplethysmographybased algorithms for blood pressure assessment. Commun Med (Lond) 2024; 4(1): 555. Dostupné z DOI: <https://doi. org/10.1038/s43856–024–00555–2>.
32. Leitner J, Chiang PH, Agnihotri P et al. The effect of an AIbased, autonomous, digital health intervention using precise lifestyle guidance on blood pressure in adults with hypertension: Singlearm nonrandomized trial. JMIR Cardio 2024; 8: e51916. Dostupné z DOI: <https://doi. org/10.2196/51916>.
33. Liu J, Li Y, Ge J et al. Lowering systolic blood pressure to less than 120 mm Hg versus less than 140 mm Hg in patients with high cardiovascular risk with and without diabetes or previous stroke: an openlabel, blindedoutcome, randomised trial. Lancet 2024; 404(10449): 245–255.Dostupné z DOI: <https://doi.org/10.1016/S0140–6736(24)01028–6>.
34. Ye X, Zeng QT, Facelli JC et al. Predicting Optimal Hypertension Treatment Pathways Using Recurrent Neural Networks. Int J Med Inform 2020; 139 : 104122. Dostupné z DOI: <https://doi.org/10.1016/j. ijmedinf.2020.104122>.
35. Li Y, Jasani F, Su D et al. Decoding Nonadherence to Hypertensive Medication in New York City: A Population Segmentation Approach. J Prim Care Community Health 2019; 10 : 2150132719829311. Dostupné z DOI: <https://doi.org/10.1177/2150132719829311>.