# CLIN-LLM: A Safety-Constrained Hybrid Framework for Clinical Diagnosis and Treatment Generation

arXiv: https://arxiv.org/abs/2510.22609 · HTML: https://mlsanity.com/paper/2510.22609/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 54 references that are in the map.
- First posted on arXiv 26 Oct 2025.

## Builds on (most cited first, 18 of 18)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019)
- [Publicly Available Clinical BERT Embeddings](https://mlsanity.com/paper/1904.03323/) (2019)
- [MedDialog: Two Large-scale Medical Dialogue Datasets](https://mlsanity.com/paper/2004.03329/) (2020)
- [Large language models in healthcare and medical domain: A review](https://mlsanity.com/paper/2401.06775/) (2023)
- [Almanac: Retrieval-Augmented Language Models for Clinical Medicine](https://mlsanity.com/paper/2303.01229/) (2023)
- [Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generation](https://mlsanity.com/paper/2408.04187/) (2024)
- [A Survey on Medical Large Language Models: Technology, Application, Trustworthiness, and Future Directions](https://mlsanity.com/paper/2406.03712/) (2024)
- [Going Deep in Medical Image Analysis: Concepts, Methods, Challenges and Future Directions](https://mlsanity.com/paper/1902.05655/) (2019)
- [Opportunities and Challenges of Deep Learning Methods for Electrocardiogram Data: A Systematic Review](https://mlsanity.com/paper/2001.01550/) (2019)
- [Uncertainty-Aware Large Language Models for Explainable Disease Diagnosis](https://mlsanity.com/paper/2505.03467/) (2025)
- [Tool Calling: Enhancing Medication Consultation via Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2404.17897/) (2024)
- [Clinical Insights: A Comprehensive Review of Language Models in Medicine](https://mlsanity.com/paper/2408.11735/) (2024)
- [MedBioLM: Optimizing Medical and Biological QA with Fine-Tuned Large Language Models and Retrieval-Augmented Generation](https://mlsanity.com/paper/2502.03004/) (2025)
- [Retrieval-Augmented and Knowledge-Grounded Language Models for Faithful Clinical Medicine](https://mlsanity.com/paper/2210.12777/) (2022)
- [Deciphering Diagnoses: How Large Language Models Explanations Influence Clinical Decision Making](https://mlsanity.com/paper/2310.01708/) (2023)
- [Evaluating the Effectiveness of the Foundational Models for Q&A Classification in Mental Health care](https://mlsanity.com/paper/2406.15966/) (2024)
- [An Advanced NLP Framework for Automated Medical Diagnosis with DeBERTa and Dynamic Contextual Positional Gating](https://mlsanity.com/paper/2502.07755/) (2025)

## Built on by (most cited first, 3 of 3)

- [TheraAgent: Self-Improving Therapeutic Agent for Precise and Comprehensive Treatment Planning](https://mlsanity.com/paper/2605.05963/) (2026)
- [How Compliant is Sepsis Treatment? An Expert-Guided Neuro-symbolic Pipeline for Generating Clinical Compliance Insights](https://mlsanity.com/paper/2608.13617/) (2026)
- [Toward System One Clinical Intelligence: Parameter-Efficient Fine-Tuning and Counterfactual Explainability of Decision Foundation Models](https://mlsanity.com/paper/2610.15029/) (2026)

## Abstract (arXiv)

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. The framework fine-tunes BioBERT on 1,200 clinical cases from the Symptom2Disease dataset and incorporates Focal Loss with Monte Carlo Dropout to enable confidence-aware predictions from free-text symptoms and structured vitals. 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 < 0.001), with 78% top-5 retrieval precision and a clinician-rated validity of 4.2 out of 5. Unsafe antibiotic suggestions are reduced by 67% compared to GPT-5. These results demonstrate CLIN-LLM's robustness, interpretability, and clinical safety alignment. The proposed system provides a deployable, human-in-the-loop decision support framework for resource-limited healthcare environments. Future work includes integrating imaging and lab data, multilingual extensions, and clinical trial validation.