Multi-Disease Prediction Using Machine Learning: A Web-Based Diagnostic Support System for Diabetes, Heart Disease, and Parkinson\'s Disease

An Intelligent Web-Based Heart Disease Prediction System Using Random Forest Classifier with Machine Learning Analysis

Disease is one of the leading causes of death worldwide, making early and accurate diagnosis critically important for saving millions of lives each year. This project presents an intelligent machine learning-based web application that predicts the presence or absence of heart disease in patients based on 13 key medical parameters such as age, cholesterol level, blood pressure, chest pain type, and maximum heart rate. The system employs a Random Forest Classifier trained on the Cleveland Heart Disease dataset sourced from the UCI Machine Learning Repository. Six machine learning algorithms were implemented and rigorously compared including Logistic Regression, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Gradient Boosting, XGBoost, and Random Forest Classifier. The Random Forest algorithm achieved the best performance with a test accuracy of 87.80% and an outstanding AUC score of 0.9550. The trained model is deployed as an interactive web application using the Streamlit framework, allowing healthcare professionals to input patient data and receive instant predictions along with risk percentages and treatment recommendations. This system serves as a reliable and cost-effective decision-support tool to assist doctors in early detection and timely intervention for heart disease. Keywords: Random Forest Classifier, Logistic Regression, Support Vector Machine, K-Nearest Neighbors, XGBoost, Gradient Boosting, StandardScaler, Streamlit, Python, Heart Disease Prediction, Machine Learning, AUC Score, Confusion Matrix

Analysis of the Accuracy of Machine Learning Models Using the Confusion Matrix Method for the Naive Bayes and CatBoost Algorithms in Diagnosing Diabetes

Diabetes is a chronic metabolic disease characterized by high blood glucose levels that can lead to severe complications affecting various organs. The increasing prevalence of diabetes requires an accurate and efficient diagnostic approach to support early detection and medical decision-making. The development of machine learning technology provides opportunities to assist disease diagnosis by analyzing patient health data and identifying patterns associated with diabetes conditions. This study aims to compare the accuracy performance of the Naive Bayes and CatBoost algorithms in diagnosing diabetes using the confusion matrix evaluation method. The research method consists of several stages, including data collection, data preprocessing, model selection, model training, and model evaluation. The dataset used was obtained from Kaggle, consisting of 768 records with nine attributes, including pregnancies, glucose level, blood pressure, skin thickness, insulin, body mass index, diabetes pedigree function, age, and outcome classification. The models were trained using 80% training data and 20% testing data. The evaluation results showed that the Naive Bayes algorithm achieved an accuracy of 79%, while the CatBoost algorithm obtained a higher accuracy of 81%. These findings indicate that CatBoost provides better classification performance compared to Naive Bayes for diabetes diagnosis in this dataset. Therefore, CatBoost can be considered a more effective machine learning approach to support diabetes prediction. Future research is recommended to utilize larger datasets, optimize model parameters, and explore other advanced algorithms to improve diagnostic accuracy.

Machine Learning–based Multi-Disease Prediction

This paper proposes a machine learning–based multi-disease prediction system that integrates disease-specific classifiers within a unified, real-time clinical decision-support platform. The framework employs Support Vector Machine (RBF) for diabetes prediction, Support Vector Machine (linear) for heart disease, Decision Tree for chronic kidney disease (CKD), and Logistic Regression for cancer prediction, with each classifier selected according to the statistical characteristics of its respective dataset. The system is implemented using a Streamlit-based web interface, enabling efficient real-time prediction with interpretable outputs. Experimental evaluation demonstrates strong predictive performance, achieving accuracies ranging from 85.71% to 94.30% and AUC-ROC values between 0.91 and 0.97 across the four disease modules, representing a 7.2 percentage-point improvement over comparable unified prediction systems reported in the literature. The modular architecture provides scalability, low computational complexity, and rapid inference, making it suitable for pre-diagnostic screening in clinical environments. The proposed framework offers an effective and practical solution for early chronic disease detection while supporting future expansion. Planned enhancements include the integration of deep learning models for medical imaging and electronic health records, Explainable Artificial Intelligence (XAI) techniques such as SHAP and LIME, wearable and IoT-based continuous health monitoring, federated learning for privacy-preserving distributed model training, and prospective clinical validation through hospital information system integration. These developments are expected to improve prediction accuracy, interpretability, scalability, and clinical applicability for next-generation intelligent healthcare systems.

Machine Learning Algorithms in Predicting Multi-Diseases

Most current clinical decision support with health care and machine learning are developed for a single disease and are therefore not integrated into the workflows when the patient needs to be assessed for multiple diseases. We present a single prediction architecture aimed at solving diabetes, heart disease and Parkinson's in a single integrated pipeline to overcome this limitation. However, less than 1,300 original records are provided by the three publicly available UCI benchmark sources, which is not enough to allow stable multi-model training, so we created a 50,000 -sample research dataset using merely statistical augmentation with a distribution-aware approach inside the training fold, without using real patients; this is not a 50,000 sample set of distinct real patients, it was only created for the purpose of controlled benchmarking. All the performance statistics mentioned in this document are taken from the original benchmark records that were held out, and not modified during the augmentation process. Four of these classifiers (Support Vector Machine (SVM), Decision Tree (DT), Artificial Neural Network (ANN) and Random Forest (RF)) were trained and evaluated using a common and strictly controlled experimental setup. For the three tasks, RF outperformed all the other algorithms with accuracies of $\mathbf{9 1. 9 \%,\ 8 9. 3 \%}$, and $\mathbf{9 6. 2 \%}$, and with a mean AUC-ROC of 0.955. Repeated stratified splits and paired significance tests ($p<0.05$) show that these numbers are constant between runs. One path that can be taken toward deployment is demonstrated with a Flask based web prototype. The numbers listed here are representative of a research prototype only and should not be used as evidence of clinical readiness.

Diabetes Prediction Using Machine Learning Model: A comparative Approach

Diabetes Prediction System Using Machine Learning

Healthcare is one of the most significant application domains of Machine Learning, where early disease prediction can help improve patient outcomes and support clinical decision-making. This dissertation presents a Diabetes Prediction and Analysis System Using Machine Learning that predicts the likelihood of a disease based on various patient health parameters and medical records. The system utilizes a healthcare dataset containing attributes such as glucose level, blood pressure, body mass index (BMI), insulin level, age, and other relevant medical factors. The collected data is pre-processed through missing value handling, feature normalization, and data partitioning to enhance prediction performance. Multiple Machine Learning algorithms, including Support Vector Machine (SVM), K-Nearest Neighbours (KNN), Decision Tree, and Random Forest, are employed to develop predictive models. The performance of these models is evaluated using metrics such as accuracy, precision, recall, F1-score, and confusion matrix. Comparative analysis is carried out to identify the most suitable algorithm for disease prediction. The implementation of the proposed system is carried out in MATLAB, utilizing its Machine Learning and data analysis tools for model training, testing, performance evaluation, and result visualization. Experimental results demonstrate that Machine Learning techniques can effectively predict disease occurrence with high accuracy, thereby assisting healthcare professionals in early diagnosis and treatment planning. The proposed system provides an efficient and reliable approach for disease prediction and analysis, contributing to improved healthcare management and decision support.