Multi-Disease Prediction System Using Machine Learning
- Resource Type
- Conference
- Authors
- Mathews, Jairus; Joseph, John; Reji, Ronald; Kamthe, Abhijeet; Deshmukh, Rupali
- Source
- 2023 6th International Conference on Advances in Science and Technology (ICAST) Advances in Science and Technology (ICAST), 2023 6th International Conference on. :330-334 Dec, 2023
- Subject
- Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Engineering Profession
General Topics for Engineers
Photonics and Electrooptics
Robotics and Control Systems
Signal Processing and Analysis
Transportation
Deep learning
Predictive models
User interfaces
Reliability
Statistics
Diseases
Biomedical imaging
Random forest
CNN
machine learning
disease prediction
Tensorflow
Keras
- Language
The proposed Multi-Disease Prediction System will be a web application for predicting common diseases like diabetes, cancer, and chronic conditions using machine learning. The goal will be to provide easy access to risk analysis and disease awareness through an interactive platform. The system will employ statistical models and deep neural networks trained on medical datasets to predict multiple diseases. Users can input their health data like symptoms and lab tests to get real-time predictions. Disease-specific models are developed using appropriate algorithms and saved via pickling. The malaria and pneumonia models leverage deep learning on imaging data. By making reliable disease prediction accessible the system enables users to get early insights into potential risks. It also provides information on disease causes and prevention to promote proactive health management. The aim is to develop an accurate and convenient application for data-driven disease screening without needing in person clinic visits. This could make personalized health analysis more accessible to the broader population. The models are continuously improved using the latest advancements in AI and ML predictive techniques.