Disease Prediction System using Machine Learning

Abstract

This paper presents a medical-history-based potential disease prediction algorithm designed to assist in intelligent medical decision-making. Leveraging healthcare big data and deep learning, the proposed method aims to identify diseases that may be overlooked due to a patient\'s limited medical knowledge. Inspired by recommendation systems, the model applies deep learning to analyze historical medical records and predict possible diseases. It combines high-order and low-order relations between medical data using a machine learning approach, resulting in improved prediction accuracy.

Introduction

The rapid digitization of healthcare has generated massive Electronic Medical Records (EMRs) and diverse health-related data, creating Healthcare Big Data. This data includes clinical records, diagnostic imaging, insurance claims, biomedical research, environmental and behavioral information. Proper analysis of this data can improve disease diagnosis, treatment efficiency, service quality, and personalized medical recommendations.

A key application is potential disease prediction, which helps identify conditions a patient might develop but is unaware of, enabling proactive healthcare and timely interventions. Traditional models—collaborative filtering, content-based, and hybrid approaches—struggle with high-dimensional, sparse data and fail to capture complex, nonlinear relationships between diseases.

The proposed system treats disease prediction like a recommendation problem, using machine learning and attention mechanisms to weigh relevant past diseases, combined with Naive Bayes and Random Forest algorithms to predict the probability of future conditions. This approach supports early detection, personalized prevention, and informed decision-making for patients and healthcare providers.

Conclusion

The proposed algorithm successfully integrates the strengths of machine learning mechanisms to create a robust system for predicting potential diseases based on a patient\'s medical history. The results show that this approach significantly outperforms traditional methods in terms of prediction accuracy and ranking quality. The model’s ability to account for both high- and low-order relations enhances its real-world applicability in medical decision-making.

References

[1] N. Zeng, Z. Wang, Y. Li, M. Du, and X. Liu, ?A hybrid ekf and switching pso algorithm for joint state and parameter estimation of lateral flow immunoassay models,? IEEE/ACM Transactions on Computational Biology and Bioinformatics, vol. 9, no. 2, pp. 321–329, 2011. [2] N. Zeng, Z. Wang, Y. Li, M. Du, and X. Liu, ?Inference of nonlinear state space models for sandwich-type lateral flow immunoassay using extended kalman filtering,? IEEE Transactions on Biomedical Engineering, vol. 58, no. 7, pp. 1959–1966, 2011. [3] P. E. Johansson, G. I. Petersson, and G. C. Nilsson, ?Personal digital assistant with a barcode reader—a medical decision support system for nurses in home care,? International journal of medical informatics, vol. 79, no. 4, pp. 232–242, 2010. [4] R. Baeza-Yates, B. Ribeiro-Neto, et al., Modern information retrieval, vol. 463. ACM press New York, 1999. [5] H.-L. Xu, X. Wu, X.-D. Li, and B.-P. Yan, ?Comparison study of internet recommendation system,? Journal of software, vol. 20, no. 2, pp. 350–362, 2009. [6] F. Xue, X. He, X. Wang, J. Xu, K. Liu, and R. Hong, ?Deep item-based collaborative filtering for top-n recommendation,? ACM Transactions on Information Systems (TOIS), vol. 37, no. 3, p. 33, 2019. [7] E. Christakopoulou and G. Karypis, ?Hoslim: Higher-order sparse linear method for top-n recommender systems,? in Pacific-Asia Conference on Knowledge Discovery and Data Mining, pp. 38–49, Springer, 2014. [8] X. He, Z. He, J. Song, Z. Liu, Y.-G. Jiang, and T.-S. Chua, ?Nais: Neural attentive item similarity model for recommendation,? IEEE Transactions on Knowledge and Data Engineering, vol. 30, no. 12, pp. 2354–2366, 2018.

Copyright

Copyright © 2026 Date Sahil Dagadu, Wagadare Om Tukaram, Mayur Santosh Lagad, Sarthak Shantaram Agale, Nawale S.K.. 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.