AI-Powered Predictive Analytics for Early Detection of Cardiovascular Diseases Using Electronic Health Records
A Retrospective Cohort Study
DOI:
https://doi.org/10.51094/jxiv.1847Keywords:
artificial intelligence, cardiovascular diseases, predictive analytics, electronic health records, early detection, deep learningAbstract
Cardiovascular diseases (CVDs) remain the leading cause of mortality worldwide, with early detection being crucial for effective intervention. Artificial intelligence (AI) has shown promise in analyzing complex medical data for predictive analytics. This study aimed to develop and validate an AI-powered predictive model for early detection of cardiovascular diseases using electronic health records (EHRs). We conducted a retrospective cohort study using EHR data from 50,000 patients collected between 2015 and 2020. We developed a deep learning model combining convolutional neural networks (CNNs) and long short-term memory (LSTM) networks to analyze structured and unstructured EHR data. The model was trained on 70% of the data and validated on the remaining 30%. Performance metrics included accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC-ROC). The AI model achieved an overall accuracy of 92.7% (95% CI: 91.8%-93.6%), sensitivity of 89.4% (95% CI: 87.9%-90.9%), specificity of 94.1% (95% CI: 93.2%-95.0%), and AUC-ROC of 0.96 (95% CI: 0.95-0.97). The model identified key predictors including age, blood pressure, cholesterol levels, diabetes status, and lifestyle factors. When compared to traditional risk assess- ment tools like the Framingham Risk Score, our AI model showed a 23.5% improvement in early detection rates. The AI-powered predictive model demonstrated superior performance in early detection of cardiovascular diseases compared to traditional methods. This approach has the potential to enhance preventive cardiology and enable timely interventions, ultimately reducing CVD morbidity and mortality
Conflicts of Interest Disclosure
The authors declare no conflicts of interest associated with this manuscript.Downloads *Displays the aggregated results up to the previous day.
References
World Health Organization, “Cardiovascular diseases,” 2021. [Online]. Available: https://www.who.int/health-topics/cardiovascular-diseases
S. Mendis, P. Puska, and B. Norrving, Global atlas on cardiovascular disease prevention and control. World Health Organization, 2011.
D. C. Goff Jr et al., “2013 ACC/AHA guideline on the assessment of cardiovascular risk: a report of the American College of Cardiol- ogy/American Heart Association Task Force on Practice Guidelines,” Circulation, vol. 129, no. 25 Suppl 2, pp. S49-73, 2014.
P. B. Jensen, L. J. Jensen, and S. Brunak, “Mining electronic health records: towards better research and patient care,” Nat Rev Genet, vol. 13, no. 6, pp. 395-405, 2012.
E. J. Topol, “High-performance medicine: the convergence of human and artificial intelligence,” Nat Med, vol. 25, no. 1, pp. 44-56, 2019.
A. Esteva et al., “A guide to deep learning in healthcare,” Nat Med, vol. 25, no. 1, pp. 24-29, 2019.
Y. Liu, P. C. Chen, and J. Krause, “How to read articles that use machine learning: users’ guides to the medical literature,” JAMA, vol. 322, no. 18, pp. 1806-1816, 2019.
K. W. Johnson et al., “Artificial intelligence in cardiology,” J Am Coll Cardiol, vol. 71, no. 23, pp. 2668-2679, 2018.
P. W. Wilson et al., “Prediction of coronary heart disease using risk factor categories,” Circulation, vol. 97, no. 18, pp. 1837-1847, 1998.
M. J. Budoff et al., “Long-term prognosis associated with coronary calcification: observations from a registry of 25,253 patients,” J Am Coll Cardiol, vol. 65, no. 17, pp. 1841-1842, 2015.
R. B. D’Agostino Sr et al., “Validation of the Framingham coronary heart disease prediction scores: results of a multiple ethnic groups investigation,” JAMA, vol. 286, no. 2, pp. 180-187, 2001.
E. Rapsomaniki et al., “Blood pressure and incidence of twelve cardio- vascular diseases: lifetime risks, healthy life-years lost, and age-specific associations in 1·25 million people,” Lancet, vol. 383, no. 9932, pp. 1899-1911, 2014.
Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436-444, 2015.
Z. I. Attia et al., “Screening for cardiac contractile dysfunction using an artificial intelligence-enabled electrocardiogram,” Nat Med, vol. 25, no. 1, pp. 70-74, 2019.
R. Poplin et al., “Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning,” Nat Biomed Eng, vol. 2, no. 3, pp. 158-164, 2018.
A. E. W. Johnson et al., “Machine Learning and Decision Support in Critical Care,” Proc IEEE Inst Electr Electron Eng, vol. 104, no. 2, pp. 444-466, 2016.
M. Liu, X. Shen, and W. Pan, “Deep learning for electronic health records: a comprehensive review,” J Biomed Inform, vol. 108, p. 103483, 2020.
S. van Buuren, “Multiple imputation of multivariate missing data: a comparison of various approaches,” Stat Med, vol. 30, no. 8, pp. 873- 891, 2011.
J. Devlin et al., “BERT: pre-training of deep bidirectional transformers for language understanding,” arXiv preprint arXiv:1810.04805, 2018.
E. R. DeLong, D. M. DeLong, and D. L. Clarke-Pearson, “Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach,” Biometrics, vol. 44, no. 3, pp. 837- 845, 1988.
S. M. Lundberg and S. I. Lee, “A unified approach to interpreting model predictions,” Adv Neural Inf Process Syst, vol. 30, pp. 4765-4774, 2017.
B. Ambale-Venkatesh et al., “Cardiovascular event prediction by ma- chine learning: the Multi-Ethnic Study of Atherosclerosis,” Circ Car- diovasc Imaging, vol. 10, no. 7, p. e005949, 2017.
S. B. Golas et al., “A machine learning model to predict the risk of 30-day readmissions among patients with heart failure: a retrospective analysis of electronic medical records data,” BMC Med Inform Decis Mak, vol. 18, no. 1, p. 44, 2018.
H. Jamali, “Quantum-Accelerated Neural Imputation with Large Lan- guage Models (LLMs),” arXiv preprint arXiv:2507.08255, 2025. [On- line]. Available: https://doi.org/10.48550/arXiv.2507.08255
H. Jamali, J. Watson, S. M. Dascalu, and F. C. Harris, “Har- monized Data Drive: Standardizing and Unifying Smart Car Information Storage for Enhanced Forensics and Interoperabil- ity,” in 2025 13th International Symposium on Digital Forensics and Security (ISDFS), pp. 1-6, IEEE, 2025. [Online]. Available: https://doi.org/10.1109/ISDFS65363.2025.11012079
H. Jamali, A. Karimi, and M. Haghighizadeh, “A new method of cloud-based computation model for mobile devices: energy consump- tion optimization in mobile-to-mobile computation offloading,” in Pro- ceedings of the 6th International Conference on Communications and Broadband Networking, pp. 32-37, 2018. [Online]. Available: https://doi.org/10.1145/3193092.3193103
H. Jamali, S. M. Dascalu, and F. C. Harris, “AI-Driven Analysis and Pre- diction of Energy Consumption in NYC’s Municipal Buildings,” in 2024 IEEE/ACIS 22nd International Conference on Software Engineering Re- search, Management and Applications (SERA), pp. 277-283, IEEE, 2024. [Online]. Available: https://doi.org/10.1109/SERA61261.2024.10685594
H. Jamali, S. M. Dascalu, F. C. Harris, and D. Feil-Seifer, “Optimiz- ing Personalized Learning Pathways with the Salp Swarm Algorithm: A Novel Approach,” in IEEE 2025 6th International Conference on Artificial Intelligence, Robotics, and Control, 2025. [Online]. Available: https://doi.org/10.1109/AIRC64931.2025.11077498
H. Jamali, S. M. Dascalu, and F. C. Harris Jr, “Fostering Joint Innova- tion: A Global Online Platform for Ideas Sharing and Collaboration,” in International Conference on Information Technology-New Genera- tions, pp. 305-312, Cham: Springer Nature Switzerland, 2024. [Online]. Available: https://doi.org/10.1007/978-3-031-56599-140
Downloads
Posted
Submitted: 2025-10-29 02:44:08 UTC
Published: 2025-11-14 10:24:33 UTC
License
Copyright (c) 2025
Zhang Ying
Sun Xin
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
