An optimal multi-disease prediction framework using hybrid machine learning techniques
The profusion of big data aids in the prediction of many lifestyle diseases in healthcare informatics research. In this paper, we outline a multi-disease prediction strategy for intelligent decision support using ensemble learning. The proposed work leverages genetic algorithm-based recursive feature elimination and AdaBoost to predict two prominent life-style diseases.
This experimental study is based on the Cleveland and Pima datasets collected from the University of California, Irvine repository. Alongside the AdaBoost algorithm, various benchmark machine learning techniques are trained and validated using selected features under a k-fold cross-validation setting.
The performance of the proposed work is evaluated on the scales of accuracy, precision, sensitivity, specificity, and F-measure.
The results reveal the effectiveness of our proposed methodology in predicting multiple diseases in comparison to other benchmark methods.