Studies from University School of Information Describe New Findings in Chronic Disease (Particle Swarm Optimization-Based Random Forest Framework for the Classification of Chronic Diseases).

A recent study conducted by researchers at the University School of Information in Delhi, India, has proposed a new approach for classifying chronic diseases (CDs) using a hybrid metaheuristic-based machine learning method. The study addresses the challenges of misdiagnosis due to similar symptoms, lack of clinical experts, and sensitive devices. The approach, called Particle Swarm Optimization with Random Forest (PSORF), combines two components: PSO for obtaining an optimal feature set and optimizing the performance of the RF classifier, and RF classifier for classifying multiple CDs. The study compared the performance of PSORF with other classifiers and found that it achieved the highest mean rank in terms of accuracy, F-measure, and Receiver Operating Characteristics (ROC) across five datasets. [Extracted from the article]