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{208607,
        author = {Prasad Gadge and Tejaswini KoliZ and Amey Thite and Arvind Rebari and Ashwini Sanjay Gagare},
        title = {ClinBridge: An AI-Assisted Framework for Structured Clinical Referral and Handover Using Intelligent Information Extraction and SBAR Generation},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {no},
        pages = {595-602},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=208607},
        abstract = {Clinical referral and handover communication is often unstructured, incomplete, duplicated, or internally inconsistent, forcing the receiving clinician to manually reconstruct the patient story before any decision can be made. 
This paper presents ClinBridge, a proposed AI-assisted framework for structured detection of referral-quality problems and generation of a clinician-reviewed handover. The system accepts an incoming referral document, extracts clinical information using a large language model constrained to a strict schema, and passes the result through a deterministic validation layer that checks completeness, flags cross-document inconsistencies, and computes an explainable Referral Quality Score. Instead of returning only a summarized narrative, the proposed system stores field-level evidence source text, page, and confidence and produces a missing-information label, a conflict label where relevant, and a Situation-Background-Assessment-Recommendation (SBAR) draft in which every sentence is marked as documented fact, extracted value, or AI-generated inference. 
The paper reviews existing research on structured handover communication, LLM-based clinical extraction, and FHIR/ABDM interoperability, describes the proposed architecture and workflow, and discusses an evaluation framework using field-level precision, recall, F1-score, conflict-detection accuracy, and workflow-usefulness metrics. The work is intended as a practical research direction for referral-quality screening that keeps the clinician as the final decision-maker, without assuming or claiming autonomous diagnostic or treatment-decision capability.},
        keywords = {Clinical Handover, Deterministic Validation, FHIR, Healthcare AI, Human-in-the-Loop, Information Extraction, Large Language Models, Referral Quality, SBAR, Responsible AI.},
        month = {September},
        }