Enhancing Healthcare through Multi Disease Prediction using Machine Learning

Abstract

This study presents a unified machine learning-based system for predicting multiple diseases diabetes, Parkinson’s disease, and heart disease through a single interface. Support Vector Machine (SVM) is used for diabetes and Parkinson’s prediction, while Logistic Regression handles heart disease classification. The models are trained on publicly available datasets and integrated into an interactive web app using Streamlit. This approach enhances diagnostic efficiency, supports early detection, and provides a scalable solution to assist clinical decision-making.

Introduction

Modern healthcare increasingly relies on intelligent technologies like machine learning (ML) for early and accurate diagnosis. This project introduces a unified, web-based application that uses ML models to predict the likelihood of three major diseases—diabetes, Parkinson’s disease, and heart disease—through a single interface. The goal is to enhance early detection, ease of access, and healthcare efficiency for users and clinicians alike.

Key Highlights:

Problem Addressed

• Existing systems usually detect only one disease at a time and lack comprehensive functionality.

• Many suffer from limited data preprocessing, low accuracy, and lack user-friendly design.

Proposed Solution

• A multi-disease prediction tool using machine learning, deployed via Streamlit for accessibility.

• Support Vector Machine (SVM) is used for diabetes and Parkinson’s predictions; Logistic Regression is used for heart disease.

• The system supports advanced preprocessing (handling missing data, feature scaling/selection) for better performance.

System Features:

1. Data Handling: Uses publicly available datasets with thorough preprocessing.

2. Model Training: Models are trained and evaluated using accuracy metrics.

3. Model Saving: Trained models are stored with pickle for reuse.

4. Web Interface: Built with Streamlit, enabling easy user input and real-time predictions.

5. Unified Prediction: Users can get predictions for all three diseases through one platform.

Literature Survey Summary:

• Swaroop Sana (2024): Validates combining SVM and logistic regression in accessible health prediction tools.

• Xie et al. (2021): Discusses deep learning’s diagnostic strengths and real-world challenges like data privacy.

• Chen et al. (2020): Explores ML’s potential for large-scale health data, emphasizing data quality and secure computation.

• Choi et al. (2016): Introduces RNN-based "Doctor AI" for sequential medical predictions.

Conclusion

This project successfully demonstrates the development of a machine learning-based system capable of predicting multiple diseases diabetes, Parkinson’s disease, and heart disease using a unified platform. By applying Support Vector Machine (SVM) and Logistic Regression algorithms, the system offers reliable and accurate predictions. The use of a Streamlit-based interface allows for easy interaction, making the system accessible even to non-technical users. Overall, this approach improves early detection of diseases and supports quicker medical intervention, making it a valuable tool in modern healthcare. There are several opportunities to enhance this disease prediction system in future versions. Additional diseases can be integrated into the platform, making it more comprehensive. The system can also be improved by incorporating real-time patient data from wearable devices or medical records. Using advanced algorithms like deep learning could further improve accuracy. In addition, deploying the model on cloud platforms will allow for wider access and better scalability, making it usable in hospitals, clinics, and rural health centers.

References

[1] Sana, S., & Swaroop. (2024). Implementation of a Multi-Disease Prediction System Using Machine Learning Techniques. International Research Journal of Modernization in Engineering Technology and Science, ISSN: 2582-5208. https://doi.org/10.56726/IRJMETS49550 [2] Xie, S., Yu, Z., & Lv, Z. (2021). A Survey on Deep Learning Methods for Multi-Disease Prediction. Computer Modeling in Engineering & Sciences, 128(2), 489–522. [3] Chen, M., Hao, Y., Cai, Y., Wang, Y., & Song, J. (2020). Utilizing Big Health Data for Disease Prediction Using Machine Learning Approaches. IEEE Access, 7, 44669–44678. [4] Choi, E., Bahadori, M. T., Schuetz, A., Stewart, W. F., & Sun, J. (2016). Doctor AI: Applying Recurrent Neural Networks to Predict Clinical Events. Journal of Machine Learning Research, 17(1), 3011–3030. [5] Rajpurkar, P., Irvin, J., Ball, R. L., Zhu, K., Yang, B., Mehta, H., ... & Ng, A. Y. (2018). Evaluating the CheXNeXt Algorithm for Chest Radiograph Diagnosis Using Deep Learning in Comparison to Radiologists. PLOS Medicine, 15(11), e1002686. [6] Singh, K., Sharma, A., Verma, A., Maurya, R., & Perwej, Y. (2024). Development of a Machine Learning-Based System for Predicting Multiple Diseases. International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 10, 673–684. https://doi.org/10.32628/CSEIT24103217

Copyright

Copyright © 2025 Anjali U. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.