An Automated Symptom to Care Framework for Predictive Diagnosis and Health Recommendation

The disease prediction system developed in this study demonstrates the effective application of ma-chine learning techniques for providing healthcare assistance based on user-input symptoms. The sys-tem efficiently processes user-provided symptoms, transforms them into a structured format, and pre-dicts the most probable disease using trained ma-chine learning models. In addition to prediction, the system provides supplementary recommendations, including medications, precautions, and dietary sug-gestions, thereby enhancing its utility as a decision-support tool. Experimental evaluation indicates that the system performs reliably across a wide range of valid inputs and produces consistent prediction results. It also effectively handles incomplete or invalid inputs by generating appropriate error messages, ensuring a smooth and user-friendly interaction. Furthermore, the system exhibits stability under edge-case sce-narios, demonstrating robustness and suitability for real-world applications. These results confirm that the proposed system successfully achieves its pri-mary objective of assisting users in early-stage disease identification. Despite its promising performance, there remains significant scope for future improvements. One po-tential enhancement is the integration of real-time doctor consultation features, enabling users to seek professional medical advice for validation and fur-ther guidance. Additionally, expanding and refining the dataset by incorporating a larger number of diseases, updated clinical data, and region-specific health conditions can further improve prediction accuracy and system reliability. The system can also be extended into a mobile application to improve accessibility and provide on-the-go healthcare support. Advanced features such as voice-based symptom input, chatbot-assisted in-teraction, and personalized health monitoring can be integrated to enhance user experience. Moreover, the adoption of advanced machine learning and deep learning models may further improve predictive per-formance and enable the system to handle complex symptom-disease relationships more effectively. In conclusion, the proposed system establishes a strong foundation for an intelligent healthcare support platform. With continuous improvements and technological advancements, it has the potential to evolve into a scalable and widely accessible so-lution that contributes significantly to early disease detection and improved health awareness.

[1]     S. Uddin, A. Khan, M. E. Hossain, and M. A. Moni, “Compar-ing different supervised machine learning algorithms for disease prediction,” BMC Medical Informatics and Decision Making, vol. 19, no. 1, pp. 1–16, 2019. [2]     P. S. Kohli and S. Arora, “Application of machine learning in disease prediction,” in Proc. IEEE International Conference on Computing, Communication and Automation (ICCCA), 2018, pp. 1–6. [3]     K. Pingale, S. Surwase, V. Kulkarni, S. Sarage, and A. Karve, “Disease prediction using machine learning,” International Re-search Journal of Engineering and Technology (IRJET), vol. 6, no. 12, 2019. [4]     Dahiwade, G. Patle, and E. Meshram, “Designing disease prediction model using machine learning approach,” in Proc. IEEE International Conference on Computing, Communication and Control (ICCMC), 2019, pp. 1–5. [5]     S. Grampurohit and C. Sagarnal, “Disease prediction using ma-chine learning algorithms,” in Proc. International Conference for Emerging Technology (INCET), 2020, pp. 1–6. [6]     R. H. Chauhan, D. N. Naik, R. A. Halpati, S. J. Patel, and A. D. Prajapati, “Disease prediction using machine learning,” IRJET, vol. 7, no. 5, 2020. [7]     S. Balasubramanian and B. Subramanian, “Symptom-based disease prediction in medical system using K-means,” Inter-national Journal of Advances in Computer Science and Tech-nology, vol. 8, no. 3, 2019. [8]     “Decision Tree Based Health Prediction System,” International Journal for Research in Applied Science and Engineering Technology (IJRASET), vol. 8, no. 6, 2020. [9]     Shilimkar, “Disease prediction using machine learning,” Inter-national Journal of Scientific Research in Science and Technol-ogy (IJSRST), vol. 8, no. 3, pp. 657–662, 2021. [10]     N. Kosarkar, A. Kothule, M. Gaikwad, S. Dongre, and N. Bhu-yar, “Disease prediction using machine learning,” in Proc. IEEE International Conference on Emerging Trends in Engineering & Technology – Signal and Information Processing (ICETET-SIP), 2022, pp. 1–5.