Opioid Risk Prediction

Cross-source consensus on Opioid Risk Prediction from 1 sources and 4 claims.

1 sources · 4 claims

Uses

The primary prediction target was a 30-day composite of opioid-related ED visit, hospitalisation, or death after each opioid dispensation. — Impact of COVID-19-related data drift on machine-learning prognostic models predicting 30-day opioid-related emergency department visits, hospitalisation or mortality: a population-level administrative data study in Alberta, Canada
The unit of analysis was each opioid dispensation event rather than each patient. — Impact of COVID-19-related data drift on machine-learning prognostic models predicting 30-day opioid-related emergency department visits, hospitalisation or mortality: a population-level administrative data study in Alberta, Canada
The adverse opioid outcome was rare and class-imbalanced, with positive cases weighted more heavily during training. — Impact of COVID-19-related data drift on machine-learning prognostic models predicting 30-day opioid-related emergency department visits, hospitalisation or mortality: a population-level administrative data study in Alberta, Canada
Adverse opioid outcomes occurred in only about 2–3% of dispensations, creating overfitting risks. — Impact of COVID-19-related data drift on machine-learning prognostic models predicting 30-day opioid-related emergency department visits, hospitalisation or mortality: a population-level administrative data study in Alberta, Canada