Linnaeus University

Patient-safety reasoning requires linking clinical narratives, medications, laboratory findings and adverse events, and a language model alone can produce plausible but unsupported conclusions. The same MIMIC-III/IV cases ran under four conditions with one LLaMA 2 7B model and one prompt: model only, plus retrieval-augmented generation, plus a patient-safety knowledge graph and ontology, and both. The full framework reached F1 0.89 for concept extraction, 0.046 above baseline; removing the knowledge graph cost the most, with F1 0.047, AUROC 0.084 and AUPRC 0.110, while removing retrieval gave an F1 difference of 0.029 whose interval crossed zero.

Patient-safety reasoning requires linking clinical narratives, medications, laboratory findings and adverse events, and a language model alone can produce plausible but unsupported conclusions. The same MIMIC-III/IV cases ran under four conditions with one LLaMA 2 7B model and one prompt: model only, plus retrieval-augmented generation, plus a patient-safety knowledge graph and ontology, and both. The full framework reached F1 0.89 for concept extraction, 0.046 above baseline; removing the knowledge graph cost the most, with F1 0.047, AUROC 0.084 and AUPRC 0.110, while removing retrieval gave an F1 difference of 0.029 whose interval crossed zero.

A patient-safety reasoning system combines a knowledge graph, retrieval-augmented generation and a LLaMA model to extract safety concepts from MIMIC-III and MIMIC-IV records and produce traceable explanations. The complete system reached an F1 of 0.89 for concept extraction; removing the knowledge graph lowered F1 by 0.047, AUROC by 0.084 and AUPRC by 0.110, all significant. Removing retrieval or LoRA adaptation gave smaller, non-significant drops, and retrieval relevance was confirmed only qualitatively by experts.

A patient-safety reasoning system combines a knowledge graph, retrieval-augmented generation and a LLaMA model to extract safety concepts from MIMIC-III and MIMIC-IV records and produce traceable explanations. The complete system reached an F1 of 0.89 for concept extraction; removing the knowledge graph lowered F1 by 0.047, AUROC by 0.084 and AUPRC by 0.110, all significant. Removing retrieval or LoRA adaptation gave smaller, non-significant drops, and retrieval relevance was confirmed only qualitatively by experts.