Efficient Disease Diagnosis Platform: Multi-Model Solution for Early Health Condition Detection

• Published in: International Conference on Signal Processing and Communication (Online) pp. 363 - 368
• Main Authors: Beniwal, Ruby, Kalra, Shruti, Nisha, K.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 20.02.2025
• Subjects: Accuracy; Breast cancer; Classification algorithms; Convolutional Neural Network (CNN); Convolutional neural networks; Healthcare diagnostics; Machine learning; Multi-disease prediction; Pneumonia; Random forests; Signal processing; Streaming media; Support vector machines; X-ray imaging
• ISSN: 2643-444X
• DOI: 10.1109/ICSC64553.2025.10967730

This paper presents a multi-disease prediction system that leverages machine learning to enable the early diagnosis of five conditions: diabetes, heart disease, Parkinson's, breast cancer, and pneumonia. Unlike single-disease models, this system integrates diverse diagnostic tasks into a unified framework, delivering high accuracy across multiple diseases. Classification algorithms Logistic Regression, Support Vector Machine, Decision Tree, Random Forest, and XGBoostare employed to identify the optimal model for each condition, achieving up to 97.66% accuracy in breast cancer detection. For pneumonia, a 14-layer Convolutional Neural Network (CNN) is used to analyze chest X-ray images effectively. The systems single-user interface facilitates rapid, data-driven predictions, streamlining clinical workflows and supporting proactive disease management.