James L. Huang

Background: Opioid use disorder (OUD) remains a critical public health crisis in the United States. Despite widespread policy and clinical interventions, early identification of individuals at risk for developing OUD remains challenging due to limitations in traditional screening approaches and a lack of individualized risk stratification methods. Machine learning (ML) methods offer an opportunity to develop timely, high-performing, and explainable predictive models that can enhance OUD prevention strategies in clinical settings. Objective: This study aims to develop and validate an ML model using electronic health record (EHR) data to predict the 3-month risk of incident OUD among adults initiating opioid therapy and to stratify patients into clinically actionable risk groups. Methods: This prognostic modeling study used 2017‐2022 OneFlorida+ EHR data to develop and validate ML algorithms predicting 3-month incident OUD risk. We included 182,083 adults (≥18 y) without cancer, overdose, or OUD or hospice history who received ≥1 outpatient, noninjectable opioid prescription. Using 183 predictors measured in sequential 3-month intervals, we developed an elastic net, least absolute shrinkage and selection operator, gradient boosting machine (GBM), and random forest models on randomly split training, testing, and validation sets. Model performance was assessed using C-statistics, predictive values, and number needed to evaluate, with patients stratified into risk deciles for clinical applicability. Model explainability was assessed using Shapley additive explanations, and fairness was evaluated using standard metrics. We externally validated the best-performing model using an independent cohort from the 2018‐2020 UPMC (formerly University of Pittsburgh Medical Center) health system. Results: In the validation sample (n=60,694), GBM (C-statistics=0.879, 95% CI 0.874‐0.884) and elastic net (C-statistics=0.872, 95% CI 0.867‐0.877) outperformed least absolute shrinkage and selection operator (C-statistics=0.846, 95% CI 0.840‐0.851) and random forest (C-statistics=0.798, 95% CI 0.792‐0.804), with GBM model requiring the fewest predictors (n=75) for predicting 3-month incident OUD. Using the GBM algorithm to predict the subsequent 3-month OUD risk, the top decile subgroup had a positive predictive value of 3.26%, a negative predictive value of 99.8%, and a number needed to evaluate of 31. The top decile (n=6696) captured ~68% of patients with OUD. Shapley additive explanations analysis identified age, number of outpatient visits, history of back and other pain conditions, comorbidity burden, and opioid prescribing patterns as the strongest predictors of incident OUD. Fairness assessment showed an acceptable false negative rate parity across race, age, and sex. In external validation on the UPMC cohort, the GBM model maintained good discrimination (C-statistics=0.756, 95% CI 0.750‐0.762) and effective risk stratification. Conclusions: An ML algorithm predicting incident OUD derived from OneFlorida+ EHR data performed well in external validation with data using UPMC. The algorithm might be valuable for incident OUD risk prediction and stratification across health systems, with potential to inform early intervention.

Introduction: Early detection and intervention are crucial for reducing the impacts of depression and associated healthcare costs. Few studies have used electronic health records (EHR) and machine learning (ML) with a longitudinal design to predict depression onset. We developed and validated ML algorithms using EHR to identify patients at high risk for the onset of diagnosis-based major depressive disorder (MDD) in primary care settings. Methods: Using a prognostic modeling approach with retrospective cohort study design, we identified patient visits in primary care settings for individuals aged ≥18 years from the Accelerating Data Value Across a National Community Health Center Network Clinical Research Network 2015–2021 data. We measured 267 features at six-month intervals starting six months prior to the first encounter. We developed algorithms using Least Absolute Shrinkage and Selection Operator (LASSO), random forest, and XGBoost with 10-fold cross validation. Using hold-out testing data, we measured prediction performance (e.g., C-statistics), stratified patients into decile risk subgroups, and assessed model biases. Results: Among eligible 1,965,399 individuals (mean age = 43.52 ± 16.04 years; male = 35%; African American = 20%) with 4,985,280 person-periods, the MDD onset rate was 1% during the study period. XGBoost performed similarly to other models and had the fewest predictors, (C-statistic = 0.763, 95% CI = [0.760, 0.767]). XGBoost had a 66.78% sensitivity, 74.19% specificity, and 2.55% positive predictive value at the balanced threshold identified using Youdan Index. The top three risk decile subgroups captured ∼70% of MDD cases, without significant racial or sex biases. Conclusions: An ML algorithm using EHR data can effectively identify individuals at high risk of depression onset within the subsequent six months, without exacerbating racial or sex biases, providing a valuable tool for targeted early interventions.

Background and aims: One‐third of opioid (OPI) overdose deaths involve concurrent benzodiazepine (BZD) use. Little is known about concurrent opioid and benzodiazepine use (OPI–BZD) most associated with overdose risk. We aimed to examine associations between OPI–BZD dose and duration trajectories, and subsequent OPI or BZD overdose in US Medicare.Design: Retrospective cohort study.Setting: US Medicare.Participants: Using a 5% national Medicare data sample (2013–16) of fee‐for‐service beneficiaries without cancer initiating OPI prescriptions, we identified 37 879 beneficiaries (age ≥ 65 = 59.3%, female = 71.9%, white = 87.6%, having OPI overdose = 0.3%).Measurements: During the 6 months following OPI initiation (i.e. trajectory period), we identified OPI–BZD dose and duration patterns using group‐based multi‐trajectory models, based on average daily morphine milligram equivalents (MME) for OPIs and diazepam milligram equivalents (DME) for BZDs. To label dose levels in each trajectory, we defined OPI use as very low (< 25 MME), low (25–50 MME), moderate (51–90 MME), high (91–150 MME) and very high (>150 MME) dose. Similarly, we defined BZD use as very low (< 10 DME), low (10–20 DME), moderate (21–40 DME), high (41–60 DME) and very high (> 60 DME) dose. Our primary analysis was to estimate the risk of time to first hospital or emergency department visit for OPI overdose within 6 months following the trajectory period using inverse probability of treatment‐weighted Cox proportional hazards models.Findings: We identified nine distinct OPI–BZD trajectories: group A: very low OPI (early discontinuation)–very low declining BZD (n = 10 598; 28.0% of the cohort); B: very low OPI (early discontinuation)–very low stable BZD (n = 4923; 13.0%); C: very low OPI (early discontinuation)–medium BZD (n = 4997; 13.2%); D: low OPI–low BZD (n = 5083; 13.4%); E: low OPI–high BZD (n = 3906; 10.3%); F: medium OPI–low BZD (n = 3948; 10.4%); G: very high OPI–high BZD (n = 1371; 3.6%); H: very high OPI–very high BZD (n = 957; 2.5%); and I: very high OPI–low BZD (n = 2096; 5.5%). Compared with group A, five trajectories (32.3% of the study cohort) were associated with increased 6‐month OPI overdose risks: E: low OPI–high BZD [hazard ratio (HR) = 3.27, 95% confidence interval (CI) = 1.61–6.63]; F: medium OPI–low BZD (HR = 4.04, 95% CI = 2.06–7.95); G: very high OPI–high BZD (HR = 6.98, 95% CI = 3.11–15.64); H: very high OPI–very high BZD (HR = 4.41, 95% CI = 1.51–12.85); and I: very high OPI–low BZD (HR = 6.50, 95% CI = 3.15–13.42).Conclusions: Patterns of concurrent opioid and benzodiazepine use most associated with overdose risk among fee‐for‐service US Medicare beneficiaries initiating opioid prescriptions include very high‐dose opioid use (MME > 150), high‐dose benzodiazepine use (DME > 40) or medium‐dose opioid with low‐dose benzodiazepine use.