Leakage-Safe benchmarking of tempered fractional optimization and swarm-driven feature construction for heart disease prediction on structured clinical data

Prediction of heart disease from structured clinical data requires both predictive performance and methodological rigor. This paper presents a leakage-safe benchmark of tempered fractional optimization and swarm-driven feature construction for heart disease prediction. The proposed framework combines a tempered fractional gradient-based logistic learner with particle swarm optimization (PSO)-driven nonlinear feature construction and is evaluated against tuned strong baselines, including elastic-net logistic regression, Extra Trees, histogram-based gradient boosting, XGBoost, LightGBM, and a stacking ensemble. The experimental protocol nests preprocessing, hyperparameter tuning, and PSO construction strictly within training data to avoid leakage. Across 15 repeated stratified hold-out splits, the proposed TFGD_PSO consistently improves over plain TFGD. However, the stacking ensemble achieves the strongest overall performance (mean ROC-AUC 0.9318 ± 0.0146, mean F1-score 0.8917 ± 0.0210, mean MCC 0.7564 ± 0.0463), while Extra Trees reaches the highest mean PR-AUC. TFGD_PSO remains competitive and computationally attractive. The study provides a rigorous benchmark showing that PSO-enhanced tempered fractional learning improves over plain tempered fractional optimization, while tuned tree-based ensembles remain the strongest predictors for this dataset. We deliberately frame the PSO contribution conservatively: the improvement over plain TFGD is small in absolute terms, so we quantify it with paired tests, Holm–Bonferroni correction, and Cohen's d effect sizes, and we discuss explicitly the regimes in which the additional swarm-search cost is, and is not, justified. To support a transparent comparison, we report a complete ten-metric evaluation suite, an ablation analysis isolating the contribution of the PSO module, a time-and-memory efficiency analysis, and a comparison against recent studies on the same dataset.