What question did this study set out to answer?

Identify key clinical risk factors for cardiovascular disease and compare the diagnostic performance of eight machine learning algorithms.

August 20, 2026PLoS ONEOpen Access

Comparative analysis of machine learning techniques for cardiovascular disease prediction

View Full Paper

Ask AI

Bookmark

Authors

MUMd. Mahfuz UddinUniversity of Rajshahi MBMd. BinyaminMawlana Bhashani Science and Technology University MFMd. Muhtasim Munif FahimUniversity of Rajshahi

Discussion

Member takes

Implication

Predictive modeling study demonstrates LightGBM achieves optimal cardiovascular risk detection, indicating potential value as an algorithmic decision-support tool.

Key Points

Identify key clinical risk factors for cardiovascular disease and compare the diagnostic performance of eight machine learning algorithms.
Evaluated eight machine learning models (Logistic Regression, Decision Tree, Random Forest, SVM, XGBoost, LogitBoost, Gradient Boosting, and LightGBM) on the open-access Kaggle Cardiovascular Disease dataset across 5-, 10-, 15-, and 20-fold cross-validation.
Identified and ranked key predictive features using Boruta, Regularized Random Forest, Recursive Feature Elimination, and LASSO methods.
LightGBM achieved the best overall balanced performance with an AUC of 0.800 (95% CI: 0.792–0.807), a sensitivity of 0.791, and an F1-score of 0.77 under 5-fold cross-validation.
LogitBoost attained the highest accuracy (0.814) and specificity (0.911) in 20-fold cross-validation, but showed lower sensitivity (0.628).
Systolic blood pressure, age, and cholesterol levels were consistently selected as the strongest predictors, with all variables except gender showing significant differences between CVD and non-CVD cohorts (p < 0.001).

Cite This Study

Uddin et al. (2026) studied this question.

synapsesocial.com/papers/6a86b56c8a91293e6a1ccd2b https://doi.org/10.1371/journal.pone.0356170

View Full Paper

Ask AI

Bookmark

Implication

Predictive modeling study demonstrates LightGBM achieves optimal cardiovascular risk detection, indicating potential value as an algorithmic decision-support tool.

Comparative analysis of machine learning techniques for cardiovascular disease prediction

Discussion

Member takes

Implication

Key Points

Cite This Study

Comparative analysis of machine learning techniques for cardiovascular disease prediction

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider