CLIN-LLM: A safety-constrained hybrid framework for clinical diagnosis and treatment generation

Md Mehedi Hasan, Md Abir Hossain, Farman Hossain Sayem, Bikash Kumar Paul, Ziaur Rahman, Mohammad Shorif Uddin and Rafid Mostafiz

PLOS ONE, 2026, vol. 21, issue 8, 1-29

Abstract: Accurate symptom-to-disease classification and clinically-grounded treatment recommendations remain challenging, particularly in heterogeneous patient settings with high diagnostic risk. Existing large language model (LLM)-based systems often lack medical grounding and fail to quantify uncertainty, resulting in unsafe outputs. We propose CLIN-LLM, a safety-constrained hybrid pipeline that integrates multimodal patient encoding, uncertainty-calibrated disease classification, and retrieval-augmented treatment generation. Our framework fine-tunes BioBERT on 1,200 clinical cases from the Symptom2Disease dataset and incorporates Focal Loss with Monte Carlo Dropout to generate confidence-aware predictions from free-text symptoms and structured vital signs. Low-certainty cases (18%) are automatically flagged for expert review, ensuring human oversight. For treatment generation, CLIN-LLM employs Biomedical Sentence-BERT to retrieve top-k relevant dialogues from the 260,000-sample MedDialog corpus. The retrieved evidence and patient context are fed into a fine-tuned FLAN-T5 model for personalized treatment generation, followed by post-processing with RxNorm for antibiotic stewardship and drug–drug interaction (DDI) screening. CLIN-LLM achieves 98% accuracy and F1 score, outperforming ClinicalBERT by 7.1% (p

Date: 2026
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0348611 (text/html)
https://journals.plos.org/plosone/article/file?id= ... 48611&type=printable (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:plo:pone00:0348611

DOI: 10.1371/journal.pone.0348611

Access Statistics for this article

More articles in PLOS ONE from Public Library of Science
Bibliographic data for series maintained by plosone ().