Key result
Neural Networks predicted heart disease with the highest accuracy (100%), outperforming Decision Trees (99.62%) and Naive Bayes (90.74%) when using 15 input attributes.
Why the study?
Does adding obesity and smoking to 13 standard attributes improve the accuracy of heart disease prediction using data mining techniques?
Does adding obesity and smoking to 13 standard attributes improve the accuracy of heart disease prediction using data mining techniques?
Absolute Event Rate: 100% vs 99.62%
Adding obesity and smoking to standard clinical attributes improves the accuracy of machine learning models, particularly Neural Networks, in predicting heart disease.
No takes yet. Share an insight, caveat, or question.
Supports expanded-attribute ML models for heart disease prediction; leaves open prospective validation before clinical use.
S.Dangare et al. (2012) studied Heart disease. Data mining classification techniques (Neural Networks, Decision Trees, Naive Bayes) vs. Comparison among techniques was evaluated on Prediction accuracy. Neural Networks predicted heart disease with the highest accuracy (100%), outperforming Decision Trees (99.62%) and Naive Bayes (90.74%) when using 15 input attributes.
Synapse has enriched 2 closely related papers on similar clinical questions. Consider them for comparative context: