April 2, 2024Journal of Intelligent & Fuzzy Systems

Hyperparameter optimization approaches to improve the performance of machine learning models for cardiovascular risk prediction

View Full Paper

Ask AI

Bookmark

Authors

ESEduardo Sánchez-JiménezDalhousie University ACAlejandra Cuevas-ChávezCentro Científico Tecnológico - Tucumán YHYasmín HernándezCentro Nacional de Investigación y Desarrollo Tecnológico

Discussion

Member takes

Implication

Comparative analysis demonstrates improved cardiovascular risk classification in the Framingham cohort, highlighting the utility of Bayesian hyperparameter tuning.

Key Points

Support vector machine and XGBoost algorithms reach ninety-five percent accuracy, and Bayesian optimization delivers superior overall precision and specificity.
Tuned support vector machine achieves 96.40% recall alongside a 93.86% F-score, outperforming alternative classifiers across evaluated cardiovascular outcomes.
Benchmark on the Framingham dataset couples genetic algorithm and particle swarm optimization, highlighting tuning strategies to refine predictive performance.

Cite This Study

Sánchez-Jiménez et al. (2024) studied this question.

synapsesocial.com/papers/68e70c4bb6db643587685ac1 https://doi.org/10.3233/jifs-219376

View Full Paper

Ask AI

Bookmark

Implication

Comparative analysis demonstrates improved cardiovascular risk classification in the Framingham cohort, highlighting the utility of Bayesian hyperparameter tuning.

Hyperparameter optimization approaches to improve the performance of machine learning models for cardiovascular risk prediction

Discussion

Member takes

Implication

Key Points

Cite This Study

Hyperparameter optimization approaches to improve the performance of machine learning models for cardiovascular risk prediction

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider