skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


  • NSF Public Access
  • Search Results
  • Development and evaluation of a machine learning model to predict acute care for opioid use disorder among Medicaid enrollees engaged in a community‐based treatment program

This content will become publicly available on April 29, 2026

Title: Development and evaluation of a machine learning model to predict acute care for opioid use disorder among Medicaid enrollees engaged in a community‐based treatment program
Abstract AimsTo develop machine‐learning algorithms for predicting the risk of a hospitalization or emergency department (ED) visit for opioid use disorder (OUD) (i.e. OUD acute events) in Pennsylvania Medicaid enrollees in the Opioid Use Disorder Centers of Excellence (COE) program and to evaluate the fairness of model performance across racial groups. MethodsWe studied 20 983 United States Medicaid enrollees aged 18 years or older who had COE visits between April 2019 and March 2021. We applied multivariate logistic regression, least absolute shrinkage and selection operator models, random forests, and eXtreme Gradient Boosting (XGB), to predict OUD acute events following the initial COE visit. Our models included predictors at the system, patient, and regional levels. We assessed model performance using multiple metrics by racial groups. Individuals were divided into a low, medium and high‐risk group based on predicted risk scores. ResultsThe training (n = 13 990) and testing (n = 6993) samples displayed similar characteristics (mean age 38.1 ± 9.3 years, 58% male, 80% White enrollees) with 4% experiencing OUD acute events at baseline. XGB demonstrated the best prediction performance (C‐statistic = 76.6% [95% confidence interval = 75.6%–77.7%] vs. 72.8%–74.7% for other methods). At the balanced cutoff, XGB achieved a sensitivity of 68.2%, specificity of 70.0%, and positive predictive value of 8.3%. The XGB model classified the testing sample into high‐risk (6%), medium‐risk (30%), and low‐risk (63%) groups. In the high‐risk group, 40.7% had OUD acute events vs. 16.5% and 5.0% in the medium‐ and low‐risk groups. The high‐ and medium‐risk groups captured 44% and 26% of individuals with OUD events. The XGB model exhibited lower false negative rates and higher false positive rates in racial/ethnic minority groups than White enrollees. ConclusionsNew machine‐learning algorithms perform well to predict risks of opioid use disorder (OUD) acute care use among United States Medicaid enrollees and improve fairness of prediction across racial and ethnic groups compared with previous OUD‐related models.  more » « less
Award ID(s):
2310217
PAR ID:
10607872
Author(s) / Creator(s):
; ; ; ; ; ;
Publisher / Repository:
Society for the Study of Addiction
Date Published:
Journal Name:
Addiction
ISSN:
0965-2140
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; ; (, PLOS ONE)
    West, Brooke (Ed.)
    Objectives An Opioid Treatment Desert is an area with limited accessibility to medication-assisted treatment and recovery facilities for Opioid Use Disorder. We explored the concept of Opioid Treatment Deserts including racial differences in potential spatial accessibility and applied it to one Midwestern urban county using high resolution spatiotemporal data. Methods We obtained individual-level data from one Emergency Medical Services (EMS) agency (Columbus Fire Department) in Franklin County, Ohio. Opioid overdose events were based on EMS runs where naloxone was administered from 1/1/2013 to 12/31/2017. Potential spatial accessibility was measured as the time (in minutes) it would take an individual, who may decide to seek treatment after an opioid overdose, to travel from where they had the overdose event, which was a proxy measure of their residential location, to the nearest opioid use disorder (OUD) treatment provider that provided medically-assisted treatment (MAT). We estimated accessibility measures overall, by race and by four types of treatment providers (any type of MAT for OUD, Buprenorphine, Methadone, or Naltrexone). Areas were classified as an Opioid Treatment Desert if the estimate travel time to treatment provider (any type of MAT for OUD) was greater than a given threshold. We performed sensitivity analysis using a range of threshold values based on multiple modes of transportation (car and public transit) and using only EMS runs to home/residential location types. Results A total of 6,929 geocoded opioid overdose events based on data from EMS agencies were used in the final analysis. Most events occurred among 26–35 years old (34%), identified as White adults (56%) and male (62%). Median travel times and interquartile range (IQR) to closest treatment provider by car and public transit was 2 minutes (IQR: 3 minutes) and 17 minutes (IQR: 17 minutes), respectively. Several neighborhoods in the study area had limited accessibility to OUD treatment facilities and were classified as Opioid Treatment Deserts. Travel time by public transit for most treatment provider types and by car for Methadone-based treatment was significantly different between individuals who were identified as Black adults and White adults based on their race. Conclusions Disparities in access to opioid treatment exist at the sub-county level in specific neighborhoods and across racial groups in Columbus, Ohio and can be quantified and visualized using local public safety data (e.g., EMS runs). Identification of Opioid Treatment Deserts can aid multiple stakeholders better plan and allocate resources for more equitable access to MAT for OUD and, therefore, reduce the burden of the opioid epidemic while making better use of real-time public safety data to address a public health epidemic that has turned into a public safety crisis. 
    more » « less
  2. ; (, Current Sleep Medicine Reports)
    Abstract Purpose of ReviewWe highlight evidence within the last 5 years of racial and ethnic differences in sleep-memory associations and explore potential causes and treatments of poor sleep in minoritized racial and ethnic groups. Recent FindingsEmerging research suggests that memory performance in Black adults may be more sensitive to sleep quality than in White adults. Sleep quality and sleep duration are also associated with memory performance in other minoritized racial and ethnic groups, including Asian and Hispanic adults. However, comparisons between groups are scarce. SummaryPoor sleep is associated with poor memory outcomes in minoritized racial and ethnic groups. Social determinants of health, including racism-related stress, discrimination, and neighborhood conditions, may contribute to these associations. More experimental and epidemiology research is needed to fully understand the relationship between sleep and memory performance in minoritized racial and ethnic groups. We conclude with suggested future directions for sleep and memory research. 
    more » « less
  3. ; ; ; ; ; (, npj Digital Medicine)
    Abstract Opioid use disorder is one of the most pressing public health problems of our time. Mobile health tools, including wearable sensors, have great potential in this space, but have been underutilized. Of specific interest are digital biomarkers, or end-user generated physiologic or behavioral measurements that correlate with health or pathology. The current manuscript describes a longitudinal, observational study of adult patients receiving opioid analgesics for acute painful conditions. Participants in the study are monitored with a wrist-worn E4 sensor, during which time physiologic parameters (heart rate/variability, electrodermal activity, skin temperature, and accelerometry) are collected continuously. Opioid use events are recorded via electronic medical record and self-report. Three-hundred thirty-nine discreet dose opioid events from 36 participant are analyzed among 2070 h of sensor data. Fifty-one features are extracted from the data and initially compared pre- and post-opioid administration, and subsequently are used to generate machine learning models. Model performance is compared based on individual and treatment characteristics. The best performing machine learning model to detect opioid administration is a Channel-Temporal Attention-Temporal Convolutional Network (CTA-TCN) model using raw data from the wearable sensor. History of intravenous drug use is associated with better model performance, while middle age, and co-administration of non-narcotic analgesia or sedative drugs are associated with worse model performance. These characteristics may be candidate input features for future opioid detection model iterations. Once mature, this technology could provide clinicians with actionable data on opioid use patterns in real-world settings, and predictive analytics for early identification of opioid use disorder risk. 
    more » « less
  4. ; ; ; ; ; ; ; ; ; ; et al (, JAMA Network Open)
    ImportanceBody mass index (BMI; calculated as weight in kilograms divided by height in meters squared) is a commonly used estimate of obesity, which is a complex trait affected by genetic and lifestyle factors. Marked weight gain and loss could be associated with adverse biological processes. ObjectiveTo evaluate the association between BMI variability and incident cardiovascular disease (CVD) events in 2 distinct cohorts. Design, Setting, and ParticipantsThis cohort study used data from the Million Veteran Program (MVP) between 2011 and 2018 and participants in the UK Biobank (UKB) enrolled between 2006 and 2010. Participants were followed up for a median of 3.8 (5th-95th percentile, 3.5) years. Participants with baseline CVD or cancer were excluded. Data were analyzed from September 2022 and September 2023. ExposureBMI variability was calculated by the retrospective SD and coefficient of variation (CV) using multiple clinical BMI measurements up to the baseline. Main Outcomes and MeasuresThe main outcome was incident composite CVD events (incident nonfatal myocardial infarction, acute ischemic stroke, and cardiovascular death), assessed using Cox proportional hazards modeling after adjustment for CVD risk factors, including age, sex, mean BMI, systolic blood pressure, total cholesterol, high-density lipoprotein cholesterol, smoking status, diabetes status, and statin use. Secondary analysis assessed whether associations were dependent on the polygenic score of BMI. ResultsAmong 92 363 US veterans in the MVP cohort (81 675 [88%] male; mean [SD] age, 56.7 [14.1] years), there were 9695 Hispanic participants, 22 488 non-Hispanic Black participants, and 60 180 non-Hispanic White participants. A total of 4811 composite CVD events were observed from 2011 to 2018. The CV of BMI was associated with 16% higher risk for composite CVD across all groups (hazard ratio [HR], 1.16; 95% CI, 1.13-1.19). These associations were unchanged among subgroups and after adjustment for the polygenic score of BMI. The UKB cohort included 65 047 individuals (mean [SD] age, 57.30 (7.77) years; 38 065 [59%] female) and had 6934 composite CVD events. Each 1-SD increase in BMI variability in the UKB cohort was associated with 8% increased risk of cardiovascular death (HR, 1.08; 95% CI, 1.04-1.11). Conclusions and RelevanceThis cohort study found that among US veterans, higher BMI variability was a significant risk marker associated with adverse cardiovascular events independent of mean BMI across major racial and ethnic groups. Results were consistent in the UKB for the cardiovascular death end point. Further studies should investigate the phenotype of high BMI variability. 
    more » « less
  5. ; ; ; ; ; (, Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies)
    Opioid use disorder is a medical condition with major social and economic consequences. While ubiquitous physiological sensing technologies have been widely adopted and extensively used to monitor day-to-day activities and deliver targeted interventions to improve human health, the use of these technologies to detect drug use in natural environments has been largely underexplored. The long-term goal of our work is to develop a mobile technology system that can identify high-risk opioid-related events (i.e., development of tolerance in the setting of prescription opioid use, return-to-use events in the setting of opioid use disorder) and deploy just-in-time interventions to mitigate the risk of overdose morbidity and mortality. In the current paper, we take an initial step by asking a crucial question: Can opioid use be detected using physiological signals obtained from a wrist-mounted sensor? Thirty-six individuals who were admitted to the hospital for an acute painful condition and received opioid analgesics as part of their clinical care were enrolled. Subjects wore a noninvasive wrist sensor during this time (1-14 days) that continuously measured physiological signals (heart rate, skin temperature, accelerometry, electrodermal activity, and interbeat interval). We collected a total of 2070 hours (≈ 86 days) of physiological data and observed a total of 339 opioid administrations. Our results are encouraging and show that using a Channel-Temporal Attention TCN (CTA-TCN) model, we can detect an opioid administration in a time-window with an F1-score of 0.80, a specificity of 0.77, sensitivity of 0.80, and an AUC of 0.77. We also predict the exact moment of administration in this time-window with a normalized mean absolute error of 8.6% and R2 coefficient of 0.85. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email