EUVIMEDAtrasti EUVIMED
Video/AudioStudienprotokoll

Interoperable Web Platform Based on Large Language Models for Medical Data Analysis: A Protocol for Clinical Decision Support

Marcello Carvalho Dos Reis, Rafaelly Rios Dos Santos, Daniel Santos da Silva, Pedro Lino Azevedo Landim, Victor Hugo Costa de Albuquerque

Journal of Visualized Experiments · 2026

DOI: 10.3791/72085 ↗

At a glance

Video/Audio in Journal of Visualized Experiments, 2026. Written by Marcello Carvalho Dos Reis and 4 co-authors. Institution: Graduate Program in Teleinformatics Engineering, Federal University of Ceará. Major MEDLINE topics: Decision Support Systems, Clinical, Internet, Health Information Interoperability.

SantraukaSubjectsBibliografiniai duomenysCiteRelated studies

Abstract (original language)

Clinical decision-making is frequently hindered by fragmented electronic health records and limited interoperability among heterogeneous healthcare information systems. This article presents a step-by-step protocol for implementing an interoperable web platform that integrates clinical data via the Fast Healthcare Interoperability Resources (FHIR) standard, along with Retrieval-Augmented Generation (RAG), Large Language Models (LLMs), and a multi-agent clinical reasoning framework to support medical data analysis and clinical decision support. The protocol describes the complete workflow, including computational environment configuration, clinical dataset preprocessing, FHIR-based data integration, vector database construction, retrieval configuration, prompt engineering, multi-agent orchestration, and system evaluation. Representative results demonstrate the platform's ability to generate clinically relevant and contextually consistent responses while improving semantic interoperability across heterogeneous data sources. System performance was evaluated using complementary quantitative and semantic metrics, including BLEU, ROUGE, BERTScore, and cosine similarity. A qualitative assessment was conducted using publicly available, fully anonymized benchmark healthcare datasets to evaluate the reproducibility of the proposed methodological workflow. The proposed architecture combines standardized healthcare interoperability with retrieval-enhanced language models to improve contextual reasoning, reduce hallucination, and support reproducible AI-assisted clinical workflows. This protocol provides a scalable and reproducible framework for researchers and developers seeking to implement interoperable, privacy-aware, and intelligent healthcare systems for clinical decision support, medical data analysis, and future translational research.

Subjects

MeSH terms (MEDLINE)

Decision Support Systems, ClinicalInternetHealth Information InteroperabilityLarge Language ModelsHumansElectronic Health Records

Authors and institutions

  • Graduate Program in Teleinformatics Engineering, Federal University of Ceará.
  • Graduate Program in Electrical Engineering, Federal University of Ceará.
  • Graduate Program in Teleinformatics Engineering, Federal University of Ceará; victor.albuquerque@ufc.br.

Cite

APA

Reis, M. C. D., Santos, R. R. D., Silva, D. S. D., Landim, P. L. A., & Albuquerque, V. H. C. (2026). Interoperable Web Platform Based on Large Language Models for Medical Data Analysis: A Protocol for Clinical Decision Support. Journal of Visualized Experiments. https://doi.org/10.3791/72085

Vancouver

Reis MCD, Santos RRD, Silva DSD, Landim PLA, Albuquerque VHC. Interoperable Web Platform Based on Large Language Models for Medical Data Analysis: A Protocol for Clinical Decision Support. Journal of Visualized Experiments. 2026. doi:10.3791/72085

BibTeX
@article{Reis2026,
  author = {Reis, Marcello Carvalho Dos and Santos, Rafaelly Rios Dos and Silva, Daniel Santos da and Landim, Pedro Lino Azevedo and Albuquerque, Victor Hugo Costa de},
  title = {Interoperable Web Platform Based on Large Language Models for Medical Data Analysis: A Protocol for Clinical Decision Support},
  journal = {Journal of Visualized Experiments},
  year = {2026},
  doi = {10.3791/72085}
}
Start for free →