Key result
Multimodal machine learning model achieves ~91% accuracy for diagnosing chronic heart failure.
Why the study?
The study aimed to address chronic heart failure diagnosis using machine learning approaches simulating clinical practice.
Does a machine learning model combining multiple feature categories improve the diagnostic accuracy of chronic heart failure compared to models using limited clinical features?
Does a machine learning model combining multiple feature categories improve the diagnostic accuracy of chronic heart failure compared to models using limited clinical features?
A machine learning model combining clinical, laboratory, and echocardiographic data accurately diagnoses chronic heart failure, potentially streamlining clinical decision-making.
May aid chronic HF diagnosis; leaves open prospective validation before clinical adoption.
The aim of this study was to address chronic heart failure (HF) diagnosis with the application of machine learning (ML) approaches. In the present study, we simulated the procedure that is followed in clinical practice, as the models we built are based on various combinations of feature categories, e.g., clinical features, echocardiogram, and laboratory findings. We also investigated the incremental value of each feature type. The total number of subjects utilized was 422. An ML approach is proposed, comprising of feature selection, handling class imbalance, and classification steps. The results for HF diagnosis were quite satisfactory with a high accuracy (91.23%), sensitivity (93.83%), and specificity (89.62%) when features from all categories were utilized. The results remained quite high, even in cases where single feature types were employed.
No takes yet. Share an insight, caveat, or question.
Plati et al. (2021) studied Chronic Heart Failure (n=422). Machine learning diagnostic model (all feature categories) vs. Machine learning model (clinical features alone) was evaluated on Diagnostic accuracy. A machine learning approach combining clinical, laboratory, and echocardiographic features achieved an accuracy of 91.23% in diagnosing chronic heart failure.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: