Key result
Augmenting a deep neural network with eight deterministic clinical indicators did not consistently improve heart disease prediction over clinical features alone.
Why the study?
Performance claims of heart disease prediction models combining machine learning with structured clinical knowledge on small benchmark datasets are difficult to interpret when feature construction, data partitioning, and metric calculations are not fully reproducible.
Does deterministic feature augmentation with eight clinically motivated indicators improve heart disease prediction performance of a deep neural network compared to using the 13 original clinical predictors alone on the UCI Statlog (Heart) dataset?
Does deterministic feature augmentation with eight clinically motivated indicators improve heart disease prediction performance of a deep neural network compared to using the 13 original clinical predictors alone on the UCI Statlog (Heart) dataset?
Answers are grounded in this paper and cite their sources.
Adding eight deterministic, clinically motivated engineered features to the 13 original clinical predictors in the UCI Statlog (Heart) dataset did not reliably improve deep neural network heart disease prediction performance, highlighting the need for rigorous ablation and cross-validation in small benchmark datasets.
Heart disease prediction models increasingly combine machine learning with structured clinical knowledge and explainable artificial intelligence. However, performance claims on small benchmark datasets can be difficult to interpret when feature construction, data partitioning, and metric calculations are not fully reproducible. This study evaluates 13 clinical predictors and eight deterministic, clinically motivated indicators using the UCI Statlog (Heart) dataset (270 records). A fixed stratified 80:20 train–test split (seed 42) was used, with five-fold stratified cross-validation restricted to the 216-record training partition. The indicators were derived directly from the original predictors; the original OWL/SWRL ontology, terminology mappings, source code, and historical prediction artifacts were unavailable. The experiment therefore evaluates deterministic feature augmentation, not formal ontology reasoning. On the 54-record test set, the clinical-only DNN achieved 83.33% accuracy, 80.00% precision, 83.33% recall, 81.63% F1-score, and 0.867 ROC-AUC. The augmented DNN achieved 79.63% accuracy, 72.41% precision, 87.50% recall, 79.25% F1-score, and 0.879 ROC-AUC. These single-split differences are descriptive and should not be interpreted as evidence of improvement: all five cross-validation mean metrics favoured the clinical-only model. The original SHAP figure could not be validated against the reported input features and was removed; no quantitative SHAP findings are claimed in this revision. The results support cautious evaluation of deterministic feature engineering and do not establish clinical effectiveness or the independent value of ontology reasoning.
No takes yet. Share an insight, caveat, or question.
Priyadharshini et al. (2026) studied Heart disease (n=270). Deep neural network augmented with eight deterministic clinically motivated engineered indicators (21 total features) vs. Clinical-feature-only deep neural network (13 original Statlog clinical predictors) was evaluated on Heart disease classification accuracy on the 54-record held-out test set. Augmenting a deep neural network with eight deterministic clinical indicators did not consistently improve heart disease prediction over clinical features alone.
Synapse has enriched 10 related papers. Consider them for comparative context: