MMCRAG-Resp: a multi-modal corrective retrieval-augmented generation framework for explainable respiratory disease reasoning.

Background: Standard Retrieval-Augmented Generation (RAG) systems only use semantic similarity to retrieve information, and since this method is quite limiting, it may find clinically irrelevant evidence and produce outputs that are unsafe or hallucinated. This drawback is particularly important in respiratory care, where the diagnosis relies heavily on very accurate physiological indicators such as spirometry patterns and symptom profiles. Methods: We propose MMCRAG-Resp., a clinically grounded, physiology-aware corrective RAG framework for respiratory intelligence. The system harmonizes 17,516 patient records from three heterogeneous public datasets (Respiratory Sound Database, NHANES spirometry, and clinical guidelines) through a unified respiratory ontology. Multi-modal embeddings (acoustic, spirometric, and textual) are fused into 144-dimensional vectors and indexed in FAISS. A novel Respiratory Relevance Score (RRS) combining spirometric pattern agreement (weight 0.45), symptom overlap (0.30), and embedding similarity (0.25) gates evidence quality before LLM consumption via a three-path correction policy. A locally deployed small language model (Ollama; llama3.2, Mistral-7B-Instruct) generates evidence-constrained, fully traceable clinical explanations without GPU requirements. Results: Evaluated on 200 held-out test queries drawn from the harmonized corpus, MMCRAG-Resp achieved a Clinical Precision@10 of 0.81, a Hallucination Rate of 0.11 (71% relative reduction over Vanilla RAG), a Spirometry Alignment Score of 0.79, and an Evidence Citation Rate of 0.87. Ablation studies confirmed that spirometry-first scoring contributes the largest single-component gain. All pairwise comparisons with baselines were statistically significant ( Conclusion: MMCRAG-Resp is, to the best of our knowledge, the first system combining multi-modal respiratory evidence retrieval, physiologically-grounded corrective RAG, and privacy-preserving local LLM inference in a single deployable clinical reasoning framework. The approach advances safe, explainable AI-assisted respiratory decision support.