Two questions: who has a substance use disorder in the record, and what should decision support look like?
Our phenotyping work identifies substance use disorder in electronic health records accurately enough to support multi-site research. Our decision support work tests interface designs empirically rather than by intuition.
Projects
- NIH/NIDA DP1DA056667, Avenir Award (PI: Jeffery)
- NIH/NIDA R03 (PI: Niarchou)
Completed
SPECTACULAR
- Betty Irene Moore Fellowship for Nurse Leaders and Innovators (Jeffery, 2022 cohort)
Software
We release the code behind our papers so other teams can reproduce and extend the work.
sudregex
Regex-driven extraction for clinical text, with configurable negation scope, substance-context gating, and false-positive pruning. Reports match counts, not just flags. Runs on pandas locally or distributed on Spark and Databricks.
pip install sudregexabc_regex
Automates the Addiction Behaviors Checklist over clinical notes with regular expressions. The published code for our 2025 JAMA Psychiatry study.
Snorkel Interactive
Research teams interested in using it can contact us for access.