Multi-Disease prediction system using Logistic Regression and SVM in an AI web platform

Abstract

The rapid advancement of artificial
intelligence in healthcare has enabled the
development of intelligent systems capable
of predicting multiple diseases efficiently
and accurately. This project presents a
Multi-Disease Prediction System
implemented using Logistic Regression
and Support Vector Machine (SVM)
algorithms within an AI-powered web
platform. The system is designed to assist
in the early detection of various diseases
such as diabetes, heart disease, and liver
disorders by analyzing user-provided
medical data.
The proposed model utilizes supervised
machine learning techniques where
historical medical datasets are
preprocessed, normalized, and used to
train both Logistic Regression and SVM
classifiers. Logistic Regression is
employed for its simplicity and
interpretability in binary classification
tasks, while SVM is used for its robustness
in handling high-dimensional data and its
ability to find optimal decision boundaries.
The performance of both models is
evaluated using metrics such as accuracy,
precision, recall, and F1-score, ensuring
reliable predictions.