Machine Learning KNIME Based Diseases Prediction for Healthcare Analytics

This study explores an innovative application of the KNIME Analytics Platform to create a predictive model for various diseases, including diabetes, heart conditions, asthma, kidney disorders, and skin cancer. The dataset, obtained from Kaggle, provides a comprehensive collection of patient data essential for accurate predictions. The research focused on designing a robust predictive framework utilizing machine learning techniques such as Random Forest, Naive Bayes, and Logistic Regression. To improve model effectiveness, advanced data preprocessing and feature engineering methods were implemented. The primary aim was to develop a reliable system for predicting multiple diseases based on patient attributes, supporting the development of tools for better medical decision-making and patient management. This work underscores the potential of KNIME as a flexible analytics tool, demonstrating its effectiveness in advancing disease prediction and enhancing healthcare strategies.