aceModel-Dependent Prompt-Component Ablation for Medical LLM Decision Support: Application to ENT Biologics Screening
Large language models (LLMs) show promise for clinical decision support, but privacy constraints and unreliable free-text decisions limit deployment. We present Medotor, a locally deployed system for screening patients with chronic rhinosinusitis with nasal polyps (CRSwNP) for biologic therapy, and evaluate prompt design on 163 retrospective cases (132 eligible and 31 ineligible). Five models were tested on the same patients under five variants: a minimal prompt (P0), the full role/safety/structured nine-point p…
In screening 163 sinus-disease cases, the best balanced accuracy was only 0.720, and a longer full prompt sharply degraded one local model, producing 84 undecidable outputs.
The knowledge block was neither personalized nor updated between patients, no standard-RAG arm was run, and hallucination labels were qualitative, so the study cannot show hallucination reduction or MemoRAG superiority.
Evidence
- Peer-reviewedIEEE Journal of Biomedical and Health Informatics2026-11-02
How should this claim be treated?
Truvace Impact Record TRV-2026-2340, v1: “Model-Dependent Prompt-Component Ablation for Medical LLM Decision Support: Application to ENT Biologics Screening.” Truvace, 2026-11-03. /record/TRV-2026-2340 (accessed at citation time). sha256 d1ef2c852046f56b…
Calibration history
Every change to this record since certification, in the open. None yet — the reading has held since it entered the record.
Certified into the record
How to verify without trusting this page
Fetch the canonical text of any version from /api/record/TRV-2026-2340 and hash it yourself — for example shasum -a 256 on the saved canonical field. The result must equal content_hash, and each version’s text ends with prev:followed by the prior version’s hash (version 1 chains to 64 zeros). If a single character of any version had been altered since certification, the chain would not reproduce.