Predicting overdose among individuals prescribed opioids using routinely collected healthcare utilization data

• Published in: PloS one Vol. 15; no. 10; p. e0241083
• Main Authors: Sun, Jenny W., Franklin, Jessica M., Rough, Kathryn, Desai, Rishi J., Hernández-Díaz, Sonia, Huybrechts, Krista F., Bateman, Brian T.
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 20.10.2020; Public Library of Science (PLoS)
• Subjects: Adolescent; Adult; Aged; Algorithms; Analgesics, Opioid - adverse effects; Analysis; Automation; Codes; Computer and Information Sciences; Demographic aspects; Drug dependence; Drug overdose; Drug Overdose - epidemiology; Drug Overdose - etiology; Drug Prescriptions - statistics & numerical data; Epidemiology; Facilities and Services Utilization - statistics & numerical data; Female; Forecasts and trends; Health care; Health risks; Health Services - statistics & numerical data; Health services utilization; Health surveillance; Hospitals; Humans; Insurance Claim Review - statistics & numerical data; Machine learning; Male; Medical care utilization; Medical diagnosis; Medical schools; Medicare; Medicine; Medicine and Health Sciences; Mental health; Middle Aged; Narcotics; Opioid abuse; Opioid-Related Disorders - complications; Opioids; Overdose; Patients; Pharmacoeconomics; Physical Sciences; Poisoning; Practice Patterns, Physicians' - statistics & numerical data; Prescriptions; Public health; Regression analysis; Research and Analysis Methods; Risk Assessment - methods; Risk factors; Risk groups; Statistical analysis; Suicide; United States - epidemiology; Womens health; Young Adult; United States; United States > US
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0241083

With increasing rates of opioid overdoses in the US, a surveillance tool to identify high-risk patients may help facilitate early intervention. To develop an algorithm to predict overdose using routinely-collected healthcare databases. Within a US commercial claims database (2011-2015), patients with ≥1 opioid prescription were identified. Patients were randomly allocated into the training (50%), validation (25%), or test set (25%). For each month of follow-up, pooled logistic regression was used to predict the odds of incident overdose in the next month based on patient history from the preceding 3-6 months (time-updated), using elastic net for variable selection. As secondary analyses, we explored whether using simpler models (few predictors, baseline only) or different analytic methods (random forest, traditional regression) influenced performance. We identified 5,293,880 individuals prescribed opioids; 2,682 patients (0.05%) had an overdose during follow-up (mean: 17.1 months). On average, patients who overdosed were younger and had more diagnoses and prescriptions. The elastic net model achieved good performance (c-statistic 0.887, 95% CI 0.872-0.902; sensitivity 80.2, specificity 80.1, PPV 0.21, NPV 99.9 at optimal cutpoint). It outperformed simpler models based on few predictors (c-statistic 0.825, 95% CI 0.808-0.843) and baseline predictors only (c-statistic 0.806, 95% CI 0.787-0.26). Different analytic techniques did not substantially influence performance. In the final algorithm based on elastic net, the strongest predictors were age 18-25 years (OR: 2.21), prior suicide attempt (OR: 3.68), opioid dependence (OR: 3.14). We demonstrate that sophisticated algorithms using healthcare databases can be predictive of overdose, creating opportunities for active monitoring and early intervention.