ADHD-MedEffects

Private MedHELM binary task: given a pediatric ADHD medication-follow-up note, say whether it documents side-effect inquiry.

Also known as: shc_sei_med, SEI, side effects inquiry

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
Subcategorypediatric ADHD clinical-note classification: medication side-effect inquiry
Page statusactive
Metricexact_match
Directionhigher_is_better
Unit%
Dataset size915
PublisherStanford University School of Medicine (Packard Children's Health Alliance / Stanford Medicine Children's Health); packaged in MedHELM by Stanford CRFM

What it measures

ADHD-MedEffects (HELM scenario shc_sei_med) tests whether a model can read an English pediatric primary-care note and decide if the clinician documented a side effects inquiry (SEI) after prescribing ADHD medication. SEI means the note records current side effects or an explicit ask about them. It does not include only planning to monitor later or counselling about possible future effects. The notes come from Packard Children's Health Alliance visits of children aged 6-11 years, 2015-2022, who had at least one ADHD medication prescription. Encounters include in-person, telehealth, and telephone notes.

Task format

Binary A/B classification over a clinical note plus a question; English text; HELM multiple-choice joint adaptation.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub