Transparency-First Medical Language Models: Datasheets, Model Cards, and End-to-End Data Provenance for Clinical NLP
This addresses transparency issues for clinical NLP practitioners, but is incremental as it builds on existing transparency frameworks.
The authors tackled the lack of transparency in clinical language models by introducing TeMLM, a set of artifacts for data provenance and auditing, and demonstrated it on a synthetic dataset with ProtactiniumBERT achieving results for PHI de-identification and ICD-9 code extraction.
We introduce TeMLM, a set of transparency-first release artifacts for clinical language models. TeMLM unifies provenance, data transparency, modeling transparency, and governance into a single, machine-checkable release bundle. We define an artifact suite (TeMLM-Card, TeMLM-Datasheet, TeMLM-Provenance) and a lightweight conformance checklist for repeatable auditing. We instantiate the artifacts on Technetium-I, a large-scale synthetic clinical NLP dataset with 498,000 notes, 7.74M PHI entity annotations across 10 types, and ICD-9-CM diagnosis labels, and report reference results for ProtactiniumBERT (about 100 million parameters) on PHI de-identification (token classification) and top-50 ICD-9 code extraction (multi-label classification). We emphasize that synthetic benchmarks are valuable for tooling and process validation, but models should be validated on real clinical data prior to deployment.