Multimodal deep learning for chronic kidney disease prediction: leveraging feature selection algorithms and ensemble models

Abstract

ABSTRACTThis research presents an advanced approach to enhance disease diagnosis using imbalanced medical datasets. Feature selection techniques, LASSO and Relief, are applied to identify relevant features from the UCI dataset and missing values are handled appropriately. To address the class imbalance, SMOTEENN is used, creating a new combined dataset with selected features. Three deep learning models, FNNs, LSTMs, and GBMs, are employed and trained on the combined dataset, achieving remarkable accuracy (1.0). Evaluating the models on LASSO and Relief datasets independently, FNN/MLP obtains perfect accuracy, GBM performs well (0.9888 on LASSO and 1.0 on Relief), and LSTM shows good results (0.9663 on LASSO and 1.0 on Relief). This study demonstrates the effectiveness of combining LASSO and Relief for feature selection and highlights the impact of SMOTEENN on model performance. The achieved accuracy with all models on the combined dataset showcases deep learning's potential for accurate disease diagnosis even with imbalanced data, offering promising insights for robust medical diagnosis systems.KEYWORDS: Chronic kidney diseaseMultimodal deep learningLASSOReliefSMOTEENN Disclosure statementNo potential conflict of interest was reported by the author(s).Additional informationNotes on contributorsN. J. SubashiniN. J. Subashini is a Research scholar in Networking and Communications department, SRM Institute of Science and Technology. Her research interests include Data Mining, Artificial Intelligence, Deep Learning and Machine Learning.K. VenkateshK. Venkatesh is Associate Professor in Networking and Communications department, SRM Institute of Science and Technology. His research interests include Networking, Cloud Computing, Data Mining, Artificial Intelligence, and Machine Learning. He is the Program Coordinator for B. Tech CSE specialization with a focus on Computer Networking. Additionally, he serves as an Alumni Coordinator in the Department of Networking and Communications. He is a Cisco certified CCNA Lead Instructor and Academy Contact for SRM Institute of Science and Technology, formerly known as SRM University, Networking Academy.