A novel hybrid model integrating 1DCNN and WSVM for enhanced chronic disease prediction

Chronic diseases require ongoing care and are often diagnosed late, leading to complications and even death. An effective predictive system for rapid and intelligent diagnosis of these pathologies is crucial. This study proposes a hybrid 1DCNN-LDA-WSVM model that combines a 1D convolutional neural network (CNN), linear discriminant analysis (LDA), and weighted support vector machine (WSVM). This model explores the joint application of 1DCNN and LDA for the extraction and selection of pertinent deep features from datasets. The WSVM is employed as a binary classifier to address the issue of minority class overweighting in SVM modelling. Evaluation across four medical datasets demonstrates enhanced performance with predictive accuracy rates of 95%, 99%, 98%, and 99% on the CHDD, PIDD, WBCD, and CKDD datasets, respectively. These results underscore the model's capability to increase precision in forecasting chronic diseases.