Author(s): Pradeep Kumar Shukla, Prabhat Pandey and Aarti Pandey

Abstract: The medical informatic recommender system (MIRS) is now increasingly prominent in the healthcare sector to improve medical recommendations. The MIRS offers enhanced adaptability compared to earlier frameworks in the exact same field, such as medical professional systems. It provides more personalized advice and helps patients better understand their health concerns. These innovations elevate the experience of patients, improved medical results, and encourage healthier habits. They support medical personnel in forecasting and handling diseases. The disease recommendation system serves as an application of the MIRS that providing recommendations for diseases based on observed symptoms. This article addresses the services of disease recommendation systems within the realm of medical informatics and introduces the DMIRS model for symptom-based disease recommendations. The suggested framework addresses issues related to patient confidentiality, consultation duration for physicians, medical inaccuracies, and challenges associated with laboratory testing. The DMIRS uses web page-based interface that emphasized collaborative remote sensing through machine learning and a statistical modeling approach. The DMIRS model enhances the effectiveness, precision, and processing rate of classification algorithms, while also addressing their most challenging performance situations. The model presented forth utilized a label encoder, probability distribution, and a stratified data splitting process as its foundational phase. The experimental research demonstrates that the suggested DMIRS model enhances disease recommendations through predictive and classification modeling.

DOI: 10.33545/26633582.2025.v7.i2d.250

Pages: 345-350 | Views: 71 | Downloads: 26

Download Full Article: Click Here