• Akshay Oza
• Aniket Jadhao
• Shivraj Ugale
• Shreyash Chaukhande
• Karuna Borhade

Increasing incidence of different diseases emphasizes the need to develop accurate predictions. Such models assist in detecting issues earlier and initiating treatment sooner. In this post, the performance of six machine learning models: Logistic Regression, Random Forest, Support Vector Machine (SVM), Decision Tree, & Gradient Boosting in predicting various diseases is analyzed. Clinical & demographic info from patients suffering from an in depth dataset, & many other diseases. The models used were trained and tested using a method known as 10-fold cross validation. We evaluated the performance of these algorithms using various performance indicators such as accuracy, precision, recall, & F1-score. Processing this data revealed the Gradient Boosting algorithm to yield the highest accuracy, which was 93.2%. Additioanlly, Random Forest & SVM exhibited close to similar good performances This almost shows that we train machine learning algorithms to predict many diseases or conditions. These outcomes imply Gradient Boosting, Random forest & SVM is an appropriate disease prediction technique and can be helpful for developing reliable clinical based predictive models.

Multiple disease prediction, machine learning, logistic regression, random forest, SVM, decision tree, gradient boosting.

"MediXpert : Multiple Disease Diagnosis System", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 10, page no.c492-c499, October-2025, Available :http://www.jetir.org/papers/JETIR2510265.pdf

"MediXpert : Multiple Disease Diagnosis System", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 10, page no. ppc492-c499, October-2025, Available at : http://www.jetir.org/papers/JETIR2510265.pdf