Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM68443
Volume:
10 |
10 |
Oct 2026
Pages:
1-11
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Department of Computer Science
Sri Shakthi Institute Of Engineering And Technology
Department of Computer Science
Sri Shakthi Institute Of Engineering And Technology
Department of Computer Science
Sri Shakthi Institute Of Engineering And Technology
Department of Computer Science
Sri Shakthi Institute Of Engineering And Technology
Department of Computer Science
Sri Shakthi Institute Of Engineering And Technology
Department of Computer Science
Sri Shakthi Institute Of Engineering And Technology
A kiosk interface registers or looks up patients, records consent, collects medical reports and supports English and Tamil interaction. A separate doctor portal provides a review queue, source-linked draft summaries, emergency red-flag alerts and physician attestation. Each extracted field shows its source, confidence and verification state; unreadable content is labelled and directed to the original document. AI output remains a draft and the physician retains final authority. React, Vite, TypeScript, Node.js, Prisma and PostgreSQL support the application, with OCR and local language-model adapters. An audit reports 301 passing tests in 25 files and successful builds for all three workspaces. The same audit finds a disconnected database, unpersisted upload binaries, an unregistered document route and template-based OCR. These results do not establish clinical accuracy or deployment readiness.
KEYWORDS
MEDBRIEF implements an AI-assisted healthcare document management and clinical support prototype that connects kiosk registration, consent, document upload, extraction, draft summarization, emergency alerts and physician review. Its principal objective is not simply to generate a summary, but to make the basis and limits of each clinical field inspectable. Readable fields display source, confidence and verification state, and unreadable inputs retain explicit uncertainty and direct the physician to the original document. The reported tests and builds demonstrate concrete implementation behaviour, but the integration audit shows that passing tests do not prove reliable operation. The database was disconnected, uploaded files were not persisted, the document viewer route was incomplete and OCR remained template-based. MEDBRIEF therefore remains an assistive prototype with synthetic data, and clinical responsibility remains with the treating physician. The integrated Registration to Consent to Document to Summary to Physician Review workflow is the project's strongest practical feature. Its completion depends on resolving persistence, storage, retrieval and OCR before further interface work. Further evaluation should extend this workflow to consented real documents and carefully measured hospital pilots.
[1] P. Lewis et al. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. Advances in Neural Information Processing Systems, 33, 2020, pp. 9459-9474. https://arxiv.org/abs/2005.11401 [2] Z. Ji et al. Survey of Hallucination in Natural Language Generation. ACM Computing Surveys, 55(12), 2023, Article 248. https://doi.org/10.1145/3571730 [3] N. Provos and D. Mazieres. A Future-Adaptable Password Scheme. USENIX Annual Technical Conference, 1999, pp. 81-91. [4] Tesseract OCR contributors. Tesseract User Manual. Official documentation.https://tesseract-ocr.github.io/tessdoc/ [5] Microsoft. Document layout analysis with Document Intelligence. Official documentation. https://learn.microso ft.com/en-us/azure/ai-services/document-intelligence/preb uilt/layout [6] Prisma. Prisma ORM Documentation. Official database toolkit documentation. https://www.prisma.io/docs [7] PostgreSQL Global Development Group. PostgreSQL 16 Documentation. Official database documentation. https://www.postgresql.org/docs/16/ [8] OpenAI. API Reference. Official documentation for the chat completions interface used by OpenAI-compatible adapters. https://platform.openai.com/docs/api-reference [9] Meta Open Source. React Documentation. Official web library documentation. https://react.dev [10] Vite contributors. Vite Guide. Official build tool documentation. https://vite.dev/guide/
Publication Date
10/28/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
1
Total views since publication
PDF Downloads
5
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...