Benchmark Almanac

National NLP Clinical Challenges

We track 4 benchmarks that National NLP Clinical Challenges made or helped make.

0 in use 2 with public code 0 with a leaderboard here

Benchmarks

Name Kind Released Best score Status
2022 n2c2/UW Shared Task on Extracting Social Determinants of Health Models identify substance use, employment, and living situations in clinical notes. Organizers score events and their attributes across three tests using notes from two institutions. Medicine Nov 2021 Not in cards
n2c2 2018 Adverse Drug Events and Medication Extraction Models extract drugs and adverse events from discharge summaries. They also identify which drug each event or medication detail belongs to. Medicine Jan 2018 Not in cards
n2c2 2022 Contextualized Medication Event Extraction Models identify medication mentions and determine whether a clinician discusses a change. They classify each change by action, negation, timing, certainty, and who acted. Medicine Nov 2021 Not in cards
n2c2 2022 Progress Note Understanding: Assessment and Plan Reasoning Models read a clinician's assessment and one part of the treatment plan. They choose one of four relationships. Organizers score the labels with macro F1. Medicine Nov 2021 Not in cards