Analysis of Data Mining Techniques for Disease Prediction System

Read full text Summarise with VIRAT
Authors: Madhur Shrivastava, Prashant Singh solanki
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The introduction of advanced data mining techniques to disease prediction systems enables healthcare professionals to discover hidden medical patterns which exist in their research databases. This research presents a thorough comparison analysis of four principal architectures—Support Vector Machines (SVM), Random Forest (RF), XGBoost, and Convolutional Neural Networks (CNN)—assessed within a 2026 multi-modal clinical context. Our research investigates how advanced preprocessing methods and feature selection techniques affect model performance through a Knowledge Discovery in Databases (KDD) approach. The results show that CNNs achieve high image diagnostic accuracy through their image-based testing (Recall = 0.97) while XGBoost ensemble methods produce the highest accuracy results for predicting multiple health conditions from structured data (Accuracy = 94.2%). We address the "Black Box" problem through our use of Explainable AI (XAI) systems. The study establishes that hybrid security-preserving future medical prediction systems will become essential because they balance computational efficiency with human understanding and ethical supervision.

Fields of Study & Subjects

Artificial Intelligence in Healthcare Data Mining and Machine Learning Applications Machine Learning in Healthcare

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
31 March 2026
Language
EN