MIMIC-IV Billing Code (MedHELM)

MedHELM's gated MIMIC-IV task: extract ICD-10 codes from an English discharge note and score micro-F1 against gold codes.

Also known as: MIMIC-IV Billing Code, mimiciv_icd10

unassessed

This page is a discovery lead. Nobody has yet assessed it against the catalogue contract, so it carries no disposition. Absence of evidence here is not evidence of staleness.
Categorydomain
SubcategoryICD-10 billing-code extraction from discharge notes
Page statusactive
Metricmimiciv_billing_code_f1 (micro-F1 over extracted ICD-10 codes)
Directionhigher_is_better
PublisherStanford CRFM and collaborators (MedHELM); notes from MIMIC-IV

What it measures

This id is HELM's mimiciv_billing_code scenario, not MIMIC-IV-BHC summarization and not MedConceptsQA. The model reads an English clinical note (column text) and must list ICD-10 billing codes (column target). HELM extracts code-shaped tokens from the generation and compares them to gold as a multi-label set. Inputs are English clinical text. Outputs are code strings.

Task format

Zero-shot generation. Instruction: "Given the following clinical note, identify all relevant ICD-10 codes." Input noun Note, output noun Predicted ICD-10 Codes, max_tokens 256, max_train_instances 0. Some MedHELM gated entries raise num_output_tokens to 4000. The scenario tags every row as TEST_SPLIT.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub