Use of artificial intelligence for heart rate variability analysis as a tool for cardiovascular risk prediction: an integrative review
DOI:
https://doi.org/10.55892/jrg.v9i20.3406Keywords:
heart rate variability, artificial intelligence, machine learning, cardiovascular risk, cardiovascular predictionAbstract
Heart rate variability (HRV) is an important marker of cardiac autonomic modulation and has been widely used in cardiovascular risk assessment. With the advancement of artificial intelligence (AI), different machine learning and deep learning algorithms have been applied to physiological signal analysis, enabling the identification of complex patterns associated with cardiovascular events. In this context, the present study aimed to understand the use of artificial intelligence applied to HRV analysis as a tool for cardiovascular risk prediction. This study is an integrative literature review conducted through searches in the PubMed/MEDLINE, Scopus, Web of Science, Embase, and Google Scholar databases. Studies addressing the application of artificial intelligence models associated with HRV in the prediction, classification, or monitoring of cardiovascular outcomes were included. After screening, full-text reading, and eligibility assessment, 21 studies were included in the review. The results demonstrated that machine learning-based models showed promising performance in predicting cardiovascular events, with AUC values ranging from 0.75 to 0.98, in addition to high diagnostic accuracy rates. The main algorithms used included support vector machine (SVM), artificial neural networks, boosting methods, and deep learning models. The evaluated outcomes included acute myocardial infarction, heart failure, cardiovascular mortality, and in-hospital cardiac arrest. However, significant methodological heterogeneity was observed among the studies, especially regarding sample size, HRV parameters analyzed, and algorithm training strategies.It is concluded that artificial intelligence applied to heart rate variability analysis presents relevant potential to assist in cardiovascular risk prediction and clinical patient stratification. However, multicenter studies with robust external validation and greater methodological standardization are still necessary to improve the clinical applicability of these tools.
Downloads
References
AGLIARI, E. et al. Detecting cardiac pathologies via machine learning on heart-rate variability time series and related markers. Scientific Reports, Londres, v. 10, n. 1, 2020. DOI:10.1038/s41598-020-64083-4
BRINZA, C. et al. Heart Rate Variability in Acute Myocardial Infarction: Results of the HeaRt-V-AMI Single-Center Cohort Study. Journal of Clinical Medicine, Basileia, v. 13, n. 4, 2024. DOI: 10.3390/jcdd11080254.
CHUMACHENKO, V. et al. Machine Learning Methods in Predicting Patients with Suspected Myocardial Infarction Based on Short-Time HRV Data. Sensors, Basileia, v. 22, n. 18, 2022. DOI:10.3390/s22187033.
FAUST, O. et al. Heart rate variability for healthcare applications using artificial intelligence techniques: a review. Computer Methods and Programs in Biomedicine, Amsterdã, v. 223, 2022. DOI: 10.1016/j.cmpb.2022.106991.
GONZÁLEZ, A. et al. Multimodal deep learning for heart failure prediction using ECG and heart rate variability. arXiv, Ithaca, 2024. Disponível em: https://arxiv.org/abs/2403.15408. Acesso em: 6 maio 2026.
KUMAR, R.; AGGARWAL, Y.; NIGAM, V. K. Heart rate dynamics in the prediction of coronary artery disease and myocardial infarction using artificial neural network and support vector machine. Journal of Applied Biomedicine, České Budějovice, v. 20, n. 2, p. 70-79, 2022. DOI: 10.32725/jab.2022.008.
LEE, H. et al. Real-time machine learning model to predict in-hospital cardiac arrest using heart rate variability in ICU. npj Digital Medicine, Londres, v. 6, n. 1, 2023. DOI: 10.1038/s41746-023-00960-2
LIU, N. et al. Beatquency domain and machine learning improve prediction of cardiovascular death after acute coronary syndrome. Scientific Reports, Londres, v. 6, 2016. DOI: 10.1038/srep34545.
MARTINEZ-ALANIS, J. et al. Prediction of Sudden Cardiac Death Risk with a Support Vector Machine Based on Heart Rate Variability and Heartprint Indices. Sensors, Basileia, v. 20, n. 19, 2020. DOI: 10.3390/s20195483.
MELILLO, P. et al. Automatic prediction of cardiovascular and cerebrovascular events using heart rate variability analysis. PLoS ONE, San Francisco, v. 10, n. 3, 2015. DOI: 10.1371/journal.pone.0118504.
NAYAK, A. et al. A Review of Methods and Applications for a Heart Rate Variability Analysis. Algorithms, Basileia, v. 16, n. 9, 2023. DOI: 10.3390/a16090433.
SHAFFER, F.; GINSBERG, J. P. An Overview of Heart Rate Variability Metrics and Norms. Frontiers in Public Health, Lausanne, v. 5, 2017. DOI: 10.3389/fpubh.2017.00258.
SHAH, S. et al. Heart rate variability as a marker of cardiovascular dysautonomia in post-COVID-19 syndrome using artificial intelligence. International Journal of Psychophysiology, Amsterdã, v. 175, 2022. DOI: 10.1016/j.ipej.2022.01.004.
SILVA-FILHO, A. G. et al. A Machine Learning model of the combination of normalized SD1 and SD2 indexes from 24h-Heart Rate Variability as a predictor of myocardial infarction. arXiv, Ithaca, 2021. Disponível em: https://arxiv.org/abs/2102.09410. Acesso em: 6 maio 2026.
SONG, M. H. et al. Usefulness of the heart-rate variability complex for predicting cardiac mortality after acute myocardial infarction. BMC Cardiovascular Disorders, Londres, v. 14, 2014. DOI: 10.1186/1471-2261-14-59.
TASMURZAYEV, N. et al. A wearable IoT-based measurement system for real-time cardiovascular risk prediction using heart rate variability. Eng, Basileia, v. 6, n. 10, 2025. DOI: 10.3390/eng6100259.
VAN ES, R. et al. Effect of urban environment on cardiovascular health: a feasibility pilot study using machine learning to predict heart rate variability in patients with heart failure. European Heart Journal Digital Health, Oxford, v. 5, n. 5, 2024. DOI:10.1093/ehjdh/ztae050.
WANG, L. et al. Heart diseases recognition model based on HRV feature extraction over 12-lead ECG signals. Sensors, Basileia, v. 24, n. 16, 2024. DOI: 10.3390/s24165296.
YADAV, I. et al. Heart rate variability as a predictor of mortality in heart failure: a systematic review and meta-analysis. Cureus, Palo Alto, v. 17, n. 12, 2025. DOI: 10.7759/cureus.99120.
ZHANG, Y. et al. Efficient and Direct Inference of Heart Rate Variability using Both Signal Processing and Machine Learning. arXiv, Ithaca, 2023. Disponível em: https://arxiv.org/abs/2303.13637. Acesso em: 1 maio 2026.
ACCARDO, A. et al. Detection of subjects with ischemic heart disease by using machine learning technique based on heart rate total variability parameters. Physiological Measurement, Bristol, v. 41, n. 11, 2020. DOI: 10.1088/1361-6579/abc321.
BRINZA, C. et al. Measuring heart rate variability in patients admitted with ST-elevation myocardial infarction for the prediction of subsequent cardiovascular events: a systematic review. Medicina, Basileia, v. 57, n. 10, 2021. DOI: 10.3390/medicina57101021.
