Key result
SVM classifier predicts heart failure survival with ~97% accuracy, outperforming other machine learning models.
Why the study?
Heart failure is a major global health hazard, but predicting it in patients remains difficult and inaccurate.
Do machine learning classifiers accurately predict survival chances in patients with heart failure?
Do machine learning classifiers accurately predict survival chances in patients with heart failure?
A Support Vector Machine model achieved 96.67% accuracy in predicting survival among heart failure patients using a publicly available clinical dataset.
SVM survival prediction merits validation in heart failure; leaves open clinical adoption pending prospective trials.
Heart failure is a major health hazard, and millions all over the world are affected by this chronic syndrome each year. Predicting heart failure in patients is extremely tough and inaccurate. To improve the prediction success rates, the authors developed a machine-learning model with improved accuracy. In this paper, the authors have used the publicly available heart failure clinical records dataset, available on UCI repository, which contains medical particulars of 299 patients with heart failure. The authors have applied four machine learning classifiers: Support Vector Machine (SVM), Random Forest (RF), Decision Tree (DT), and XGBoost to predict the survival chances of patients. SVM achieved the highest accuracy of 96.67% for patient survival prediction in comparison with all the other employed machine learning classification techniques.
No takes yet. Share an insight, caveat, or question.
Sachdeva et al. (2023) studied Heart failure (n=299). Machine learning classifiers (SVM, RF, DT, XGBoost) vs. Comparison among classifiers was evaluated on Patient survival prediction accuracy. A Support Vector Machine (SVM) classifier achieved the highest accuracy of 96.67% for predicting patient survival in heart failure compared to other machine learning techniques.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: