EHRSHOT (HELM ehrshot)

HELM's yes/no wrap of Stanford EHRSHOT: predict a future clinical event from EHR codes, scored by exact match, not the paper's AUROC.

Also known as: EHRSHOT, EHRShot

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
Subcategoryyes/no future-event prediction from structured EHR code sequences
Page statusactive
Metricexact_match (HELM); paper reports AUROC and AUPRC
Directionhigher_is_better
Unit%
Dataset size6739
Dataset licenceStanford University Dataset Research Use Agreement
PublisherStanford University (Shah Lab / CRFM MedHELM packaging)

What it measures

This id is HELM's ehrshot scenario, not the original few-shot AUROC benchmark by itself. Each instance is a patient's prior structured EHR codes plus a yes/no question: new diagnosis in a year, abnormal lab if drawn now, long stay, 30-day readmission, or ICU transfer. HELM converts timelines with codes_only and asks the model to answer A/B (yes/no). Inputs are coded events, not clinical notes. English prompts. It is not [ehr_sql](ehr_sql.md).

Task format

Zero-shot joint multiple choice. HELM adapter: "Answer A for yes, B for no", max_train_instances 0, max_tokens 1. Scenario references are the strings yes and no. Lab tasks subsample 10,000 labels. Default max_length 100,000 tokens; longer prompts are dropped.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub