Dataset Information

Predictive Modeling of Opioid Overdose Using Linked Statewide Medical and Criminal Justice Data.

ABSTRACT:

Importance

Responding to the opioid crisis requires tools to identify individuals at risk of overdose. Given the expansion of illicit opioid deaths, it is essential to consider risk factors across multiple service systems.

Objective

To develop a predictive risk model to identify opioid overdose using linked clinical and criminal justice data.

Design, setting, and participants

A cross-sectional sample was created using 2015 data from 4 Maryland databases: all-payer hospital discharges, the prescription drug monitoring program (PDMP), public-sector specialty behavioral treatment, and criminal justice records for property or drug-associated offenses. Maryland adults aged 18 to 80 years with records in any of 4 databases were included, excluding individuals who died in 2015 or had a non-Maryland zip code. Logistic regression models were estimated separately for risk of fatal and nonfatal opioid overdose in 2016. Model performance was assessed using bootstrapping. Data analysis took place from February 2018 to November 2019.

Exposures

Controlled substance prescription fills and hospital, specialty behavioral health, or criminal justice encounters.

Main outcomes and measures

Fatal opioid overdose defined by the state medical examiner and 1 or more nonfatal overdoses treated in Maryland hospitals during 2016.

Results

There were 2 294 707 total individuals in the sample, of whom 42.3% were male (n = 970 019) and 53.0% were younger than 50 years (647 083 [28.2%] aged 18-34 years and 568 160 [24.8%] aged 35-49 years). In 2016, 1204 individuals (0.05%) in the sample experienced fatal opioid overdose and 8430 (0.37%) experienced nonfatal opioid overdose. In adjusted analysis, the factors mostly strongly associated with fatal overdose were male sex (odds ratio [OR], 2.40 [95% CI, 2.08-2.76]), diagnosis of opioid use disorder in a hospital (OR, 2.93 [95% CI, 2.17-3.80]), release from prison in 2015 (OR, 4.23 [95% CI, 2.10-7.11]), and receiving opioid addiction treatment with medication (OR, 2.81 [95% CI, 2.20-3.86]). Similar associations were found for nonfatal overdose. The area under the curve for fatal overdose was 0.82 for a model with hospital variables, 0.86 for a model with both PDMP and hospital variables, and 0.89 for a model that further added behavioral health and criminal justice variables. For nonfatal overdose, the area under the curve using all variables was 0.85.

Conclusions and relevance

In this analysis, fatal and nonfatal opioid overdose could be accurately predicted with linked administrative databases. Hospital encounter data had higher predictive utility than PDMP data. Model performance was meaningfully improved by adding PDMP records. Predictive models using linked databases can be used to target large-scale public health programs.

SUBMITTER: Saloner B

PROVIDER: S-EPMC7315388 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Health system data incompletely capture the social risk factors for drug overdose. This study aimed to improve the accuracy of a machine-learning algorithm to predict opioid overdose risk by integrating human services and criminal justice data with health claims data to capture the social determinants of overdose risk. This prognostic study included Medicaid beneficiaries (n = 237,259) in Allegheny County, Pennsylvania enrolled between 2015 and 2018, randomly divided into training, testing, and validation samples. We measured 290 potential predictors (239 derived from Medicaid claims data) in 30-day periods, beginning with the first observed Medicaid enrollment date during the study period. Using a gradient boosting machine, we predicted a composite outcome (i.e., fatal or nonfatal opioid overdose constructed using medical examiner and claims data) in the subsequent month. We compared prediction performance between a Medicaid claims only model to one integrating human services and criminal justice data with Medicaid claims (i.e., integrated model) using several metrics (e.g., C-statistic, number needed to evaluate [NNE] to identify one overdose). Beneficiaries were stratified into risk-score decile subgroups. The samples (training = 79,087, testing = 79,086, validation = 79,086) had similar characteristics (age = 38±18 years, female = 56%, white = 48%, having at least one overdose = 1.7% during study period). Using the validation sample, the integrated model slightly improved on the Medicaid claims only model (C-statistic = 0.885; 95%CI = 0.877-0.892 vs. C-statistic = 0.871; 95%CI = 0.863-0.878), with small corresponding improvements in the NNE and positive predictive value. Nine of the top 30 most important predictors in the integrated model were human services and criminal justice variables. Using the integrated model, approximately 70% of individuals with overdoses were members of the top risk decile (overdose rates in the subsequent month = 47/10,000 beneficiaries). Few individuals in the bottom 9 deciles had overdose episodes (0-12/10,000). Machine-learning algorithms integrating claims and social service and criminal justice data modestly improved opioid overdose prediction among Medicaid beneficiaries for a large U.S. county heavily affected by the opioid crisis.

Project description:Background and aimsDespite the high prevalence of substance use among people in the US criminal justice system, little is known about the incidence of overdose mortality by use patterns, drug convictions and supervision setting. We examined the associations between these characteristics and overdose mortality.DesignRetrospective cohort study.Setting and participantsIndividuals sentenced to prison, jail, probation or jail plus probation for a felony conviction in Michigan, USA from 2003 to 2006.MeasurementsUsing the National Death Index, we assessed overdose mortality to December 2012. We calculated overdose mortality rates by pre-sentence opioid use, drug convictions and supervision setting. Multivariable analyses were conducted using competing risks regression with time-varying covariates.FindingsAmong 140 266 individuals followed over a mean of 7.84 years [standard deviation (SD) = 1.52], 14.9% of the 1131 deaths were due to overdose (102.8 per 100 000 person-years). Over the follow-up, more than half of overdose deaths occurred in the community (57.7%), nearly a third (28.8%) on probation and 12.8% on parole. The adjusted risk of overdose death was lower on probation [hazard ratio (HR) = 0.71, 95% confidence interval (CI) = 0.60, 0.85] than in the community without probation or parole (HR = 1.00) but not significantly different on parole (HR = 1.13, 95% CI = 0.87, 1.47). Pre-sentence daily opioid use (HR = 3.54, 95% CI = 3.24, 3.87) was associated with an increased risk. Drug possession (HR = 1.11, 95% CI = 0.93, 1.31) and delivery convictions (HR = 0.92, 95% CI = 0.77, 1.09) were not significantly associated with overdose mortality.ConclusionsBased on the absolute or relative risk, parole, probation and community settings are appropriate settings for enhanced overdose prevention interventions. Ensuring that individuals with pre-sentence opioid use have access to harm reduction and drug treatment services may help to prevent overdose among people involved with the criminal justice system.

Project description:Extended-release naltrexone, a sustained-release monthly injectable formulation of the full mu-opioid receptor antagonist, is effective for the prevention of relapse to opioid dependence. Data supporting its effectiveness in U.S. criminal justice populations are limited.In this five-site, open-label, randomized trial, we compared a 24-week course of extended-release naltrexone (Vivitrol) with usual treatment, consisting of brief counseling and referrals for community treatment programs, for the prevention of opioid relapse among adult criminal justice offenders (i.e., persons involved in the U.S. criminal justice system) who had a history of opioid dependence and a preference for opioid-free rather than opioid maintenance treatments and who were abstinent from opioids at the time of randomization. The primary outcome was the time to an opioid-relapse event, which was defined as 10 or more days of opioid use in a 28-day period as assessed by self-report or by testing of urine samples obtained every 2 weeks; a positive or missing sample was computed as 5 days of opioid use. Post-treatment follow-up occurred at weeks 27, 52, and 78.A total of 153 participants were assigned to extended-release naltrexone and 155 to usual treatment. During the 24-week treatment phase, participants assigned to extended-release naltrexone had a longer median time to relapse than did those assigned to usual treatment (10.5 vs. 5.0 weeks, P<0.001; hazard ratio, 0.49; 95% confidence interval [CI], 0.36 to 0.68), a lower rate of relapse (43% vs. 64% of participants, P<0.001; odds ratio, 0.43; 95% CI, 0.28 to 0.65), and a higher rate of opioid-negative urine samples (74% vs. 56%, P<0.001; odds ratio, 2.30; 95% CI, 1.48 to 3.54). At week 78 (approximately 1 year after the end of the treatment phase), rates of opioid-negative urine samples were equal (46% in each group, P=0.91). The rates of other prespecified secondary outcome measures--self-reported cocaine, alcohol, and intravenous drug use, unsafe sex, and reincarceration--were not significantly lower with extended-release naltrexone than with usual treatment. Over the total 78 weeks observed, there were no overdose events in the extended-release naltrexone group and seven in the usual-treatment group (P=0.02).In this trial involving criminal justice offenders, extended-release naltrexone was associated with a rate of opioid relapse that was lower than that with usual treatment. Opioid-use prevention effects waned after treatment discontinuation. (Funded by the National Institute on Drug Abuse; ClinicalTrials.gov number, NCT00781898.).