Data driven healthcare insurance system using machine learning and blockchain technologies

Irum Matloob; Shoab Khan; Bushra Bashir; Rukaiya Rukaiya; Javed Ali Khan; Hessa Alfraihi

doi:10.7717/peerj-cs.2980

Data driven healthcare insurance system using machine learning and blockchain technologies

PeerJ Comput Sci. 2025 Jul 30:11:e2980. doi: 10.7717/peerj-cs.2980. eCollection 2025.

Authors

Irum Matloob¹, Shoab Khan², Bushra Bashir¹, Rukaiya Rukaiya³, Javed Ali Khan⁴, Hessa Alfraihi⁵

Affiliations

¹ Department of Software Engineering, Fatima Jinnah Women University, Rawalpindi, Pakistan.
² National University of Science and Technology, Islamabad, Pakistan.
³ Sir Syed University of Engineering and Technology, Islamabad, Pakistan.
⁴ Department of Computer Science, University of Hertfordshire, Hatfield, Hertfordshire, United Kingdom.
⁵ Department of Information Systems, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia.

Abstract

Healthcare recommendations and insurance have recently been one of the most emerging research areas in health informatics. The fraud in health insurance is becoming increasingly common day by day. To handle healthcare insurance fraud, there is an urgent need for an intelligent system that cannot only identify and monitor doctors' and hospitals' behavior regarding the health services they provide to patients but can also recommend doctors and hospitals to insured employees based on the quality of services they provided previously. This system creates patient and doctor profiles separately, based on their rating. The proposed system combines singular value decomposition (SVD), K-nearest neighbors based collaborative filtering (KNN-based CF), item-based collaborative filtering (Item-based CF), content-based filtering using term frequency-inverse document frequency (TF-IDF), and K-means clustering and probability distributions to recommend doctors and insurance plans. The system measures similarity scores between patients and doctors using cosine similarity, which helps to determine similarity scores and refine the recommendations. This study also uses blockchain technology to automate insurance claims reimbursement. The results are validated using real data from the employees of a local hospital. The system provides recommendations with a root mean square error (RMSE) value of 0.478 and a mean absolute error (MAE) value of 0.0422. The insurance plans developed using the proposed system have reduced the overall expenditure of the local hospital, with a reduction in total expenses. Blockchain technology further helps prevent healthcare fraud. In the proposed system, a healthcare insurance claims reimbursement system is built using smart contract technology on the Ethereum blockchain, ensuring security & transparency and lowering the number of healthcare frauds. The system includes roles for the insurance company, healthcare provider, and patients. It also provides a platform for claim submission, approval, or refusal. In Pakistan, no such system existed before recommending doctors from different hospitals based on their professional conduct or the good health services they provide.

Keywords: Applied machine learning; Artificial intelligence; Blockchain; Fraud detection; Health informatics; Security and privacy.