Machine learning-based risk prediction for major adverse cardiovascular events in a Brazilian hospital: Development, external validation, and interpretability

Autor(es):Mostrar menos -

Shimizu, Gilson Yuuji ; Schrempf, Michael ; Romao, Elen Almeida ; Jauk, Stefanie ; Kramer, Diether ; Rainer, Peter P. ; Cardeal da Costa, Jose Abrao ; de Azevedo-Marques, Joao Mazzoncini ; Scarpelini, Sandro ; Suzuki, Katia Mitiko Firmino ; Cesar, Hilton Vicente ; de Azevedo-Marques, Paulo Mazzoncini

• Tipo de documento: Artigo Científico
• Fonte: PLoS One; v. 19, n. 10, p. 23-pg., 2024-10-11.

Resumo

Background Studies of cardiovascular disease risk prediction by machine learning algorithms often do not assess their ability to generalize to other populations and few of them include an analysis of the interpretability of individual predictions. This manuscript addresses the development and validation, both internal and external, of predictive models for the assessment of risks of major adverse cardiovascular events (MACE). Global and local interpretability analyses of predictions were conducted towards improving MACE's model reliability and tailoring preventive interventions.Methods The models were trained and validated on a retrospective cohort with the use of data from Ribeir & atilde;o Preto Medical School (RPMS), University of S & atilde;o Paulo, Brazil. Data from Beth Israel Deaconess Medical Center (BIDMC), USA, were used for external validation. A balanced sample of 6,000 MACE cases and 6,000 non-MACE cases from RPMS was created for training and internal validation and an additional one of 8,000 MACE cases and 8,000 non-MACE cases from BIDMC was employed for external validation. Eight machine learning algorithms, namely Penalized Logistic Regression, Random Forest, XGBoost, Decision Tree, Support Vector Machine, k-Nearest Neighbors, Naive Bayes, and Multi-Layer Perceptron were trained to predict a 5-year risk of major adverse cardiovascular events and their predictive performance was evaluated regarding accuracy, ROC curve (receiver operating characteristic), and AUC (area under the ROC curve). LIME and Shapley values were applied towards insights about model interpretability.Findings Random Forest showed the best predictive performance in both internal validation (AUC = 0.871 (0.859-0.882); Accuracy = 0.794 (0.782-0.808)) and external one (AUC = 0.786 (0.778-0.792); Accuracy = 0.710 (0.704-0.717)). Compared to LIME, Shapley values suggest more consistent explanations on exploratory analysis and importance of features.Conclusions Among the machine learning algorithms evaluated, Random Forest showed the best generalization ability, both internally and externally. Shapley values for local interpretability were more informative than LIME ones, which is in line with our exploratory analysis and global interpretation of the final model. Machine learning algorithms with good generalization and accompanied by interpretability analyses are recommended for assessments of individual risks of cardiovascular diseases and development of personalized preventive actions. (AU)

• Processo FAPESP: 21/06137-4 - Prevendo eventos cardiovasculares usando aprendizado de máquina
• Beneficiário: Paulo Mazzoncini de Azevedo Marques
• Modalidade de apoio: Auxílio à Pesquisa - Regular
• Processo FAPESP: 22/16683-9 - Aprendizado federado para validação de modelos de aprendizado de máquina treinados em diferentes redes de hospitais
• Beneficiário: Gilson Yuuji Shimizu
• Modalidade de apoio: Bolsas no Brasil - Pós-Doutorado
• Processo FAPESP: 23/01695-4 - Validação e melhoria de modelos de aprendizado de máquina para previsão de eventos cardiovasculares
• Beneficiário: Hilton Vicente César
• Modalidade de apoio: Bolsas no Brasil - Programa Capacitação - Treinamento Técnico