APRENDIZADO DE MÁQUINA NA DETECÇÃO DE DOENÇA ARTERIAL CORONARIANA: UMA REVISÃO TÉCNICO-CIENTÍFICA
DOI:
https://doi.org/10.56238/arev7n10-039Palavras-chave:
Aprendizado de Máquina, Doença Arterial Coronariana, AteroscleroseResumo
As doenças cardiovasculares continuam sendo a principal causa de morte em todo o mundo, tornando os avanços na prevenção essenciais. Esta revisão resume o trabalho recente sobre aprendizado de máquina (ML) aplicado a dados clínicos estruturados para detectar ou prever doença arterial coronariana (DAC). Esta revisão narrativa foi conduzida sob a estrutura PRISMA 2020. Buscas no PubMed, IEEE Xplore e SciELO (janeiro de 2020 a abril de 2025) renderam 3.780 registros. Após triagem e avaliação do texto completo, 10 artigos foram incluídos: sete estudos primários e três revisões. Os tamanhos das amostras variaram de 303 a 70.000 indivíduos. Algoritmos e conjuntos baseados em árvore apresentaram as melhores pontuações, com precisão entre 0,82 e 0,99 e AUROC de 0,86 a 0,96. A explicabilidade com SHAP foi aplicada em quatro estudos, e um emparelhou SHAP com LIME. Um artigo adicionou a contribuição de um cardiologista ao ciclo de decisão, aumentando a precisão de 0,7829 para 0,8302. Apenas um artigo avaliou seus modelos em conjuntos de dados externos e observou quedas de desempenho. A calibração raramente foi abordada. Apenas uma investigação relatou uma pontuação de Brier de 0,14 e uma inclinação de 0,93. Modelos de ML treinados exclusivamente com variáveis demográficas, laboratoriais e clínicas coletadas rotineiramente demonstram forte capacidade de classificação para DAC, apoiando seu uso como auxiliar de triagem não invasiva e suporte à decisão. Ensaios prospectivos, validação externa e relatórios detalhados de calibração são necessários antes da adoção clínica.
Downloads
Referências
American Psychological Association. (2020). Publication manual of the American Psychological Association (7th ed.). https://doi.org/10.1037/0000165-000 DOI: https://doi.org/10.1037/0000165-000
Azari Jafari, S., & et al. (2022). Unsupervised phenotyping of coronary artery disease. Journal of Biomedical Informatics, 127, 104002. https://doi.org/10.1016/j.jbi.2022.104002 DOI: https://doi.org/10.1016/j.jbi.2022.104002
Chen, R., Zhang, Y., He, M., & et al. (2024). Continuous cardiovascular-risk monitoring with wearable sensors and deep neural networks: A prospective cohort study. IEEE Journal of Biomedical and Health Informatics, 28(1), 45–55. https://doi.org/10.1109/JBHI.2023.3311623
D’Agostino, R. B., Sr., Vasan, R. S., Pencina, M. J., & et al. (2008). General cardiovascular risk profile for use in primary care: The Framingham Heart Study. Circulation, 117(6), 743–753. https://doi.org/10.1161/CIRCULATIONAHA.107.699579 DOI: https://doi.org/10.1161/CIRCULATIONAHA.107.699579
Esteva, A., Robicquet, A., Ramsundar, B., & et al. (2019). A guide to deep learning in healthcare. Nature Medicine, 25(1), 24–29. https://doi.org/10.1038/s41591-018-0316-z DOI: https://doi.org/10.1038/s41591-018-0316-z
European Parliament. (2024). EU Artificial Intelligence Act: Final compromise text. https://eur-lex.europa.eu/eli/reg/2024/1689/oj
Goff, D. C., Jr., Lloyd-Jones, D. M., Bennett, G., & et al. (2014). 2013 ACC/AHA guideline on the assessment of cardiovascular risk. Circulation, 129(Suppl. 2), S49–S73. https://doi.org/10.1161/01.cir.0000437741.48606.98 DOI: https://doi.org/10.1161/01.cir.0000437741.48606.98
Jose, R., Thomas, A., Guo, J., Steinberg, R., & Toma, M. (2024). Evaluating machine-learning models for prediction of coronary artery disease. Global Translational Medicine, 3(1), Article e2669. https://doi.org/10.36922/gtm.2669 DOI: https://doi.org/10.36922/gtm.2669
Kakadiaris, I. A., Vrigkas, M., & et al. (2018). Machine learning outperforms ACC/AHA CVD risk calculator in MESA. Journal of the American Heart Association, 7(22), Article e009476. https://doi.org/10.1161/JAHA.118.009476 DOI: https://doi.org/10.1161/JAHA.118.009476
Kang, Y., Guo, N., Cheng, G., & et al. (2022). Deep-learning-based quantitative coronary CT angiography for prediction of obstructive disease: Multicenter validation. Radiology, 304(2), 303–312. https://doi.org/10.1148/radiol.2021212667
Ling, H., Guo, Z. Y., Tan, L. L., Guan, R. C., Chen, J. B., & Song, C. L. (2021). Machine learning in diagnosis of coronary artery disease. Chinese Medical Journal, 134(4), 401–403. https://doi.org/10.1097/CM9.0000000000001202 DOI: https://doi.org/10.1097/CM9.0000000000001202
Liu, T., Krentz, A., Lu, L., & Curcin, V. (2024). Machine-learning-based prediction models for cardiovascular disease risk using electronic health records: Systematic review and meta-analysis. European Heart Journal - Digital Health, 6(1), 7–22. https://doi.org/10.1093/ehjdh/ztae080 DOI: https://doi.org/10.1093/ehjdh/ztae080
Lundberg, S. M., Nair, B., Voglino, J., & et al. (2018). Explainable machine-learning predictions for the prevention of hypoxaemia during surgery. Nature Biomedical Engineering, 2(10), 749–760. https://doi.org/10.1038/s41551-018-0304-0 DOI: https://doi.org/10.1038/s41551-018-0304-0
Mitchell, T. (1997). Machine learning. McGraw-Hill.
Muhammad, D., Ahmed, I., Ahmad, M. O., & Bendechache, M. (2024). Randomized explainable machine-learning models for efficient medical diagnosis. IEEE Journal of Biomedical and Health Informatics. Advance online publication. https://doi.org/10.1109/JBHI.2024.3401234 DOI: https://doi.org/10.1109/JBHI.2024.3491593
Omkari, D. Y., & Shaik, K. (2024). An integrated two-layered voting framework for coronary artery disease prediction using machine-learning classifiers. IEEE Access, 12, 56275–56290. https://doi.org/10.1109/ACCESS.2024.3389707 DOI: https://doi.org/10.1109/ACCESS.2024.3389707
Panch, T., Mattie, H., & Celi, L. A. (2019). The inconvenient truth about artificial intelligence in healthcare. NPJ Digital Medicine, 2, Article 77. https://doi.org/10.1038/s41746-019-0155-4 DOI: https://doi.org/10.1038/s41746-019-0155-4
Provost, C., Broughan, J., McCombe, G., & et al. (2025). Artificial-intelligence models for cardiovascular-disease risk prediction in primary and ambulatory care: A scoping review. medRxiv. https://doi.org/10.1101/2025.03.21.25324379 DOI: https://doi.org/10.1101/2025.03.21.25324379
Rasmy, L., Xiang, Y., Xie, Z., Tao, C., & Zhi, D. (2021). Med-BERT: Pre-trained contextualized embeddings on large-scale structured EHRs for disease prediction. NPJ Digital Medicine, 4, Article 86. https://doi.org/10.1038/s41746-021-00455-y DOI: https://doi.org/10.1038/s41746-021-00455-y
Rehman, S. U., Anwar, S. M., & Khawaja, B. A. (2022). Benchmarking k-nearest neighbors and logistic regression against ensemble methods for CAD detection. IEEE Journal of Biomedical and Health Informatics, 26(8), 4021–4031. https://doi.org/10.1109/JBHI.2022.3162345
Saeedbakhsh, S., Sattari, M., Mohammadi, M., Najafian, J., & Mohammadi, F. (2023). Diagnosis of coronary artery disease based on machine-learning algorithms: Support vector machine, artificial neural network and random forest. Advanced Biomedical Research, 12, Article 51. https://doi.org/10.4103/abr.abr_383_21 DOI: https://doi.org/10.4103/abr.abr_383_21
Samaras, A. D., Moustakidis, S., Apostolopoulos, I. D., Papandrianos, N., & Papageorgiou, E. (2023). Classification models for assessing coronary artery disease instances using clinical and biometric data: An explainable man-in-the-loop approach. Scientific Reports, 13, Article 6668. https://doi.org/10.1038/s41598-023-33500-9 DOI: https://doi.org/10.1038/s41598-023-33500-9
Silva, C. A. O., Morillo, C. A., Leite-Castro, C., González-Otero, R., Bessani, M., González, R., & et al. (2022). Machine learning for atrial fibrillation risk prediction in patients with sleep apnea and coronary artery disease. Frontiers in Cardiovascular Medicine, 9, Article 1050409. https://doi.org/10.3389/fcvm.2022.1050409 DOI: https://doi.org/10.3389/fcvm.2022.1050409
Van Calster, B., McLernon, D. J., Van Smeden, M., & et al. (2019). Calibration: The Achilles heel of predictive analytics. BMC Medicine, 17, Article 230. https://doi.org/10.1186/s12916-019-1466-7 DOI: https://doi.org/10.1186/s12916-019-1466-7
Wang, J., Xue, Q., Zhang, C. W. J., Wong, K. K. L., & Liu, Z. (2024). Explainable coronary artery disease prediction model based on AutoGluon from AutoML framework. Frontiers in Cardiovascular Medicine, 11, Article 1360548. https://doi.org/10.3389/fcvm.2024.1360548 DOI: https://doi.org/10.3389/fcvm.2024.1360548
World Health Organization. (2021a). Cardiovascular diseases (CVDs): Fact sheet. https://www.who.int/news-room/fact-sheets/detail/cardiovascular-diseases
World Health Organization. (2021b). Ethics and governance of artificial intelligence for health. https://iris.who.int/bitstream/handle/10665/341996/9789240029200-eng.pdf
Wynants, L., Van Calster, B., Collins, G. S., & Riley, R. D. (2020). Prediction models for diagnosis and prognosis of COVID-19 infection: Systematic review and critical appraisal. BMJ, 369, Article m1328. https://doi.org/10.1136/bmj.m1328 DOI: https://doi.org/10.1136/bmj.m1328
Yu, M., & et al. (2022). Reinforcement learning for dynamic treatment regimes in cardiovascular care. Frontiers in Cardiovascular Medicine, 9, Article 1012456. https://doi.org/10.3389/fcvm.2022.1012456
Zhang, Y., Chen, G., Xu, Z., & et al. (2024). FedCVD: A federated learning benchmark for cardiovascular disease detection. arXiv. https://doi.org/10.48550/arXiv.2411.07050
