Patient surveys boost prediction of opioid use disorder diagnoses
Patient-Reported Survey Data Improve Prediction of Opioid Use Disorder
Machine Learning
Summary
Doctors often use electronic health records (EHRs) to predict who might develop opioid use disorder (OUD), but these records may miss important patient details. The authors studied over 267,000 patients with opioid exposure and found that adding patient survey answers improved prediction accuracy. This means surveys can catch information that EHRs miss, helping identify patients at risk of OUD earlier. They also noticed survey availability varied by time and patient status, showing the importance of collecting these patient-reported data.
What this means in practice
- •For healthcare data teams: Improve opioid use disorder prediction models by integrating patient survey data alongside electronic health records.
- •For health insurance companies: Enhance risk assessment strategies to identify patients at potential risk of opioid use disorder using combined EHR and survey data.
Authors
Xiyue Jiang, Zihan Ding, Grace Han, Yinan Liu, Richard N. Rosenthal, Fusheng Wang
Abstract
Electronic health records (EHRs) may incompletely capture patient-reported factors associated with opioid use disorder (OUD). We evaluated whether survey data improve prediction of a first recorded OUD diagnosis among 267,747 All of Us participants with documented opioid exposure, including 15,287 OUD cases. We compared EHR-only and EHR+survey models across 6-, 12-, and 24-month look-back windows using logistic regression, random forest, XGBoost, LightGBM, multilayer perceptron, LSTM, GRU, and Transformer. Survey augmentation improved PR-AUC across all 24 model-window combinations by 0.0087-0.0505; the best 24-month LightGBM model improved from 0.6219 to 0.6603. Survey coverage increased with longer windows and differed by OUD status (24 months: 21.7% OUD-positive vs. 60.7% OUD-negative). Permutation analysis ranked survey features as the second most important information domain at 24 months in both evaluated models. Patient-reported data provide complementary predictive signals beyond structured EHRs while highlighting the importance of survey availability.