NSIDDx: A Design Framework for Neuro-Symbolic, Practitioner-First Differential Diagnosis in Low-Resource Settings

Excerpt

arXiv:2609.00256v2 Announce Type: replace Abstract: LLM-based diagnostic systems achieve high semantic accuracy on benchmarks, but open-ended evaluation on clinically uncommon presentations reveals a systematic gap between headline accuracy and verifiable clinical reliability. We evaluate an LLM+rare-disease-RAG pipeline across two cohorts and show that the paradigm produces confident outputs that are frequently unverifiable and systematically resistant to clinician interrogation. We present NSI