Abstract
Dementia and heart failure are growing global health issues, exacerbated by aging populations and disparities in care access. Diagnosing these conditions often requires advanced equipment or tests with limited availability. A reliable tool distinguishing between the two conditions is essential, enabling more accurate diagnoses and reducing misclassifications and inappropriate referrals. This study proposes a novel measurement, the optimized weighted objective distance (OWOD), a modified version of the weighted objective distance, for the classification of dementia and heart failure. The OWOD is designed to enhance model generalization through a data-driven approach. By enhancing objective class generalization, applying multi-feature distance normalization, and identifying the most significant features for classification-together with newly integrated blood biomarker features-the OWOD could strengthen the classification of dementia and heart failure. A combination of risk factors and proposed blood biomarkers (derived from 10,000 electronic health records at Chiang Rai Prachanukroh Hospital, Chiang Rai, Thailand), comprising 20 features, demonstrated the best OWOD classification performance. For model evaluation, the proposed OWOD-based classification method attained an accuracy of 95.45%, a precision of 96.14%, a recall of 94.70%, an F1-score of 95.42%, and an area under the receiver operating characteristic curve of 97.10%, surpassing the results obtained using other machine learning-based classification models (gradient boosting, decision tree, neural network, and support vector machine).