TY  - JOUR
AU  - Wadhwan, Ankita 
AU  - Chawla, Priyanka 
AU  - Kaur, Sandeep 
AU  - Mittal, Usha 
PY  - 2025
TI  - IntelliHealth: A Machine Learning Driven Disease Detectionand Diet recommendation System
JF  - Journal of Computer Science
VL  - 21
IS  - 6
DO  - 10.3844/jcssp.2025.1251.1265
UR  - https://thescipub.com/abstract/jcssp.2025.1251.1265
AB  - People all around the world are afflicted with various ailments. An accurate diagnosis can lower the risk of significant health problems developing, but an inaccurate diagnosis could have adverse implications. In this study, an ensemble-based strategy "IntelliHealth" has been presented to identify disorders of the thyroid, liver, and breast cancer using three machine learning (ML) approaches consisting of Support Vector Machine (SVM), Decision Tree (DT), and Random Forest (RF). The datasets for this research work are acquired from Kaggle. The experimental results show that the ML based ensemble model provides the highest level of disease prediction accuracy. This model is 93% accurate for liver, 99% accurate for breast cancer, and 100% accurate for diabetes and thyroid. Also, in this study, a web-based application is developed that uses proposed ensemble for quickly predicting diseases based on the patient's profile and recommends a diet plan.