Copyright © 2026 Authors retain the copyright of this article. This article 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.

@article{202275,
        author = {L.Prasika and T. Ponkumaran and N.Sakthi Parameswaran},
        title = {Novel Cognitive Blockchain Based Framework For Mining Electronic Health Records With Secure Patient Centric Communication},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {7861-7882},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=202275},
        abstract = {In the present era, the imperative of digitizing of data has become unavoidable. An extensive volume of unstructured Electronic Health Record (EHR) data remains dormant across the internet. Primarily, this data was housed using conventional storage methods. Despite the advantages offered by traditional storage approaches, they frequently grappled with issues such as data loss, absence of immutability concerning health records, and intricate processes for accessing clinical information. Blockchain, a decentralized peer-to-peer storage mechanism, addressed these flaws. EHR data, comprising rich patient-centric information, offer valuable insights for analytical purposes. However, processing this unstructured data and utilizing it for analysis and prediction poses a serious issue. In this research, a novel patient-centric architecture for decentralized health care management with ethereum blockchain using smart contracts and a novel deep neural architecture to extract the features from the clinical nursing notes and prediction of ICD codes is proposed. In this paper, MIMIC IV database was used for training the models and evaluating them. Clinical BERT model was used for converting words into embeddings provides a significant result in prediction.  The results obtained from the proposed approach demonstrate a higher accuracy rate of 93% in comparison to alternative models for disease prediction.},
        keywords = {Blockchain EHR MIMIC Clinical BERT ICD 10 Code Prediction Ensemble Model},
        month = {May},
        }