PROVIDENT: Development and Validation of a Machine Learning Model to Predict Neighborhood-level Overdose Risk in Rhode Island.

BACKGROUND: Drug overdose persists as a leading cause of death in the United States, but resources to address it remain limited. As a result, health authorities must consider where to allocate scarce resources within their jurisdictions. Machine learning offers a strategy to identify areas with increased future overdose risk to proactively allocate overdose prevention resources. This modeling study is embedded in a randomized trial to measure the effect of proactive resource allocation on statewide overdose rates in Rhode Island (RI). METHODS: We used statewide data from RI from 2016 to 2020 to develop an ensemble machine learning model predicting neighborhood-level fatal overdose risk. Our ensemble model integrated gradient boosting machine and super learner base models in a moving window framework to make predictions in 6-month intervals. Our performance target, developed a priori with the RI Department of Health, was to identify the 20% of RI neighborhoods containing at least 40% of statewide overdose deaths, including at least one neighborhood per municipality. The model was validated after trial launch. RESULTS: Our model selected priority neighborhoods capturing 40.2% of statewide overdose deaths during the test periods and 44.1% of statewide overdose deaths during validation periods. Our ensemble outperformed the base models during the test periods and performed comparably to the best-performing base model during the validation periods. CONCLUSIONS: We demonstrated the capacity for machine learning models to predict neighborhood-level fatal overdose risk to a degree of accuracy suitable for practitioners. Jurisdictions may consider predictive modeling as a tool to guide allocation of scarce resources.

Characterizing opioid overdose hotspots for place-based overdose prevention and treatment interventions: A geo-spatial analysis of Rhode Island, USA.

OBJECTIVE: Examine differences in neighborhood characteristics and services between overdose hotspot and non-hotspot neighborhoods and identify neighborhood-level population factors associated with increased overdose incidence. METHODS: We conducted a population-based retrospective analysis of Rhode Island, USA residents who had a fatal or non-fatal overdose from 2016 to 2020 using an environmental scan and data from Rhode Island emergency medical services, State Unintentional Drug Overdose Reporting System, and the American Community Survey. We conducted a spatial scan via SaTScan to identify non-fatal and fatal overdose hotspots and compared the characteristics of hotspot and non-hotspot neighborhoods. We identified associations between census block group-level characteristics using a Besag-York-Mollié model specification with a conditional autoregressive spatial random effect. RESULTS: We identified 7 non-fatal and 3 fatal overdose hotspots in Rhode Island during the study period. Hotspot neighborhoods had higher proportions of Black and Latino/a residents, renter-occupied housing, vacant housing, unemployment, and cost-burdened households. A higher proportion of hotspot neighborhoods had a religious organization, a health center, or a police station. Non-fatal overdose risk increased in a dose responsive manner with increasing proportions of residents living in poverty. There was increased relative risk of non-fatal and fatal overdoses in neighborhoods with crowded housing above the mean (RR 1.19 [95 % CI 1.05, 1.34]; RR 1.21 [95 % CI 1.18, 1.38], respectively). CONCLUSION: Neighborhoods with increased prevalence of housing instability and poverty are at highest risk of overdose. The high availability of social services in overdose hotspots presents an opportunity to work with established organizations to prevent overdose deaths.

Utilization and disparities in medication treatment for opioid use disorder among patients with comorbid opioid use disorder and chronic pain during the COVID-19 pandemic.

BACKGROUND: The COVID-19 pandemic's impact on utilization of medications for opioid use disorder (MOUD) among patients with opioid use disorder (OUD) and chronic pain is unclear. METHODS: We analyzed New York State (NYS) Medicaid claims from pre-pandemic (August 2019-February 2020) and pandemic (March 2020-December 2020) periods for beneficiaries with and without chronic pain. We calculated monthly proportions of patients with OUD diagnoses in 6-month-lookback windows utilizing MOUD and proportions of treatment-naïve patients initiating MOUD. We used interrupted time series to assess changes in MOUD utilization and initiation rates by medication type and by race/ethnicity. RESULTS: Among 20,785 patients with OUD and chronic pain, 49.3% utilized MOUD (versus 60.3% without chronic pain). The pandemic did not affect utilization in either group but briefly disrupted initiation among patients with chronic pain (ß=-0.009; 95% CI [-0.015, -0.002]). Overall MOUD utilization was not affected by the pandemic for any race/ethnicity but opioid treatment program (OTP) utilization was briefly disrupted for non-Hispanic Black individuals (ß=-0.007 [-0.013, -0.001]). The pandemic disrupted overall MOUD initiation in non-Hispanic Black (ß=-0.007 [-0.012, -0.002]) and Hispanic individuals (ß=-0.010 [-0.019, -0.001]). CONCLUSIONS: Adults with chronic pain who were enrolled in NYS Medicaid before the COVID-19 pandemic had lower MOUD utilization than those without chronic pain. MOUD initiation was briefly disrupted, with disparities especially in racial/ethnic minority groups. Flexible MOUD policy initiatives may have maintained overall treatment utilization, but disparities in initiation and care continuity remain for patients with chronic pain, and particularly for racial/ethnic minoritized subgroups.

Evaluating chronic pain as a risk factor for COVID-19 complications among New York State Medicaid beneficiaries: a retrospective claims analysis.

OBJECTIVE: To assess whether chronic pain increases the risk of COVID-19 complications and whether opioid use disorder (OUD) differentiates this risk among New York State Medicaid beneficiaries. DESIGN, SETTING, AND SUBJECTS: This was a retrospective cohort study of New York State Medicaid claims data. We evaluated Medicaid claims from March 2019 through December 2020 to determine whether chronic pain increased the risk of COVID-19 emergency department (ED) visits, hospitalizations, and complications and whether this relationship differed by OUD status. We included beneficiaries 18-64 years of age with 10 months of prior enrollment. Patients with chronic pain were propensity score-matched to those without chronic pain on demographics, utilization, and comorbidities to control for confounders and were stratified by OUD. Complementary log-log regressions estimated hazard ratios (HRs) of COVID-19 ED visits and hospitalizations; logistic regressions estimated odds ratios (ORs) of hospital complications and readmissions within 0-30, 31-60, and 61-90 days. RESULTS: Among 773 880 adults, chronic pain was associated with greater hazards of COVID-related ED visits (HR = 1.22 [95% CI: 1.16-1.29]) and hospitalizations (HR = 1.19 [95% CI: 1.12-1.27]). Patients with chronic pain and OUD had even greater hazards of hospitalization (HR = 1.25 [95% CI: 1.07-1.47]) and increased odds of hepatic- and cardiac-related events (OR = 1.74 [95% CI: 1.10-2.74]). CONCLUSIONS: Chronic pain increased the risk of COVID-19 ED visits and hospitalizations. Presence of OUD further increased the risk of COVID-19 hospitalizations and the odds of hepatic- and cardiac-related events. Results highlight intersecting risks among a vulnerable population and can inform tailored COVID-19 management.

Translating Predictive Analytics for Public Health Practice: A Case Study of Overdose Prevention in Rhode Island.

Prior applications of machine learning to population health have relied on conventional model assessment criteria, limiting the utility of models as decision support tools for public health practitioners. To facilitate practitioners' use of machine learning as a decision support tool for area-level intervention, we developed and applied 4 practice-based predictive model evaluation criteria (implementation capacity, preventive potential, health equity, and jurisdictional practicalities). We used a case study of overdose prevention in Rhode Island to illustrate how these criteria could inform public health practice and health equity promotion. We used Rhode Island overdose mortality records from January 2016-June 2020 (n = 1,408) and neighborhood-level US Census data. We employed 2 disparate machine learning models, Gaussian process and random forest, to illustrate the comparative utility of our criteria to guide interventions. Our models predicted 7.5%-36.4% of overdose deaths during the test period, illustrating the preventive potential of overdose interventions assuming 5%-20% statewide implementation capacities for neighborhood-level resource deployment. We describe the health equity implications of use of predictive modeling to guide interventions along the lines of urbanicity, racial/ethnic composition, and poverty. We then discuss considerations to complement predictive model evaluation criteria and inform the prevention and mitigation of spatially dynamic public health problems across the breadth of practice. This article is part of a Special Collection on Mental Health.

Neighborhood-level association between release from incarceration and fatal overdose, Rhode Island, 2016-2020.

The association between recent release from incarceration and dramatically increased risk of fatal overdose is well-established at the individual level. Fatal overdose and. arrest/release are spatially clustered, suggesting that this association may persist at the neighborhood level. We analyzed multicomponent data from Rhode Island, 2016-2020, and observed a modest association at the census tract level between rates of release per 1000 population and fatal overdose per 100,000 person-years, adjusting for spatial autocorrelation in both the exposure and outcome. Our results suggest that for each additional person released to a given census tract per 1000 population, there is a corresponding increase in the rate of fatal overdose by 2 per 100,000 person years. This association is more pronounced in suburban tracts, where each additional release awaiting trial is associated with an increase in the rate of fatal overdose of 4 per 100,000 person-years and 6 per 100,000 person-years for each additional release following sentence expiration. This association is not modified by the presence or absence of a licensed medication for opioid use disorder (MOUD) treatment provider in the same or surrounding tracts. Our results suggest that neighborhood-level release rates are moderately informative as to tract-level rates of fatal overdose and underscore the importance of expanding pre-release MOUD access in correctional settings. Future research should explore risk and resource environments particularly in suburban and rural areas and their impacts on overdose risk among individuals returning to the community.

Naloxone expansion is not associated with increases in adolescent heroin use and injection drug use: Evidence from 44 US states.

BACKGROUND: Naloxone distribution is central to ongoing efforts to address the opioid overdose crisis. Some critics contend that naloxone expansion may inadvertently promote high-risk substance use behaviors among adolescents, but this question has not been directly investigated. METHODS: We examined relationships between naloxone access laws and pharmacy naloxone distribution with lifetime heroin and injection drug use (IDU), 2007-2019. Models generating adjusted odds ratios (aOR) and 95% confidence intervals (CI) included year and state fixed effects, controlled for demographics and sources of variation in opioid environments (e.g., fentanyl penetration), as well as additional policies expected to impact substance use (e.g., prescription drug monitoring). Exploratory and sensitivity analyses further examined naloxone law provisions (e.g., third-party prescribing) and applied e-value testing to assess vulnerability to unmeasured confounding. RESULTS: Adoption of any naloxone law was not associated with changes in adolescent lifetime heroin or IDU. For pharmacy dispensing, we observed a small decrease in heroin use (aOR: 0.95 [CI: 0.92, 0.99]) and a small increase in IDU (aOR: 1.07 [CI: 1.02, 1.11]). Exploratory analyses of law provisions suggested that third-party prescribing (aOR: 0.80, [CI: 0.66, 0.96]) and non-patient-specific dispensing models (aOR: 0.78, [CI: 0.61, 0.99]) were associated with decreased heroin use but not decreased IDU. Small e-values associated with the pharmacy dispensing and provision estimates indicate that unmeasured confounding may explain observed findings. CONCLUSION: Naloxone access laws and pharmacy naloxone distribution were more consistently associated with decreases rather than increases in lifetime heroin and IDU among adolescents. Our findings therefore do not support concerns that naloxone access promotes high-risk adolescent substance use behaviors. As of 2019, all US states have adopted legislation to improve naloxone access and facilitate use. However, further removal of adolescent naloxone access barriers is an important priority given that the opioid epidemic continues to affect people of all ages.

Has the treatment gap for opioid use disorder narrowed in the U.S.?: A yearly assessment from 2010 to 2019".

BACKGROUND: The United States overdose crisis continues unabated. Despite efforts to increase capacity for treating opioid use disorder (OUD) in the U.S., how actual treatment receipt compares to need remains unclear. In this cross-sectional study, we estimate progress in addressing the gap between OUD prevalence and OUD treatment receipt at the national and state levels from 2010 to 2019. METHODS: We estimated past-year OUD prevalence rates based on the U.S. National Survey on Drug Use and Health (NSDUH), using adjustment methods that attempt to account for OUD underestimation in national household surveys. We used data from specialty substance use treatment records and outpatient pharmacy claims to estimate the gap between OUD prevalence and number of persons receiving medications for opioid use disorder (MOUD) during the past decade. RESULTS: Adjusted estimates suggest past-year OUD affected 7,631,804 individuals in the U.S. in (2,773 per 100,000 adults 12+), relative to only 1,023,959 individuals who received MOUD (365 per 100,000 adults 12+). This implies approximately 86.6% of individuals with OUD nationwide who may benefit from MOUD treatment do not receive it. MOUD receipt increased across states over the past decade, but most regions still experience wide gaps between OUD prevalence and MOUD receipt. CONCLUSIONS: Despite some progress in expanding access to MOUD, a substantial gap between OUD prevalence and treatment receipt highlights the critical need to increase access to evidence-based services.

Cycles of Chronic Opioid Therapy Following Mandatory Prescription Drug Monitoring Program Legislation: A Retrospective Cohort Study.

BACKGROUND: Mandates for prescriber use of prescription drug monitoring programs (PDMPs), databases tracking controlled substance prescriptions, are associated with reduced opioid analgesic (OA) prescribing but may contribute to care discontinuity and chronic opioid therapy (COT) cycling, or multiple initiations and terminations. OBJECTIVE: To estimate risks of COT cycling in New York City (NYC) due to the New York State (NYS) PDMP mandate, compared to risks in neighboring New Jersey (NJ) counties. DESIGN: We estimated cycling risk using Prentice, Williams, and Peterson gap-time models adjusted for age, sex, OA dose, payment type, and county population density, using a life-table difference-in-differences design. Failure time was duration between cycles. In a subgroup analysis, we estimated risk among patients receiving high-dose prescriptions. Sensitivity analyses tested robustness to cycle volume considering only first cycles using Cox proportional hazard models. PARTICIPANTS: The cohort included 7604 patients dispensed 12,695 prescriptions. INTERVENTIONS: The exposure was the August 2013 enactment of the NYS PDMP prescriber use mandate. MAIN MEASURES: We used monthly, patient-level data on OA prescriptions dispensed in NYC and NJ between August 2011 and July 2015. We defined COT as three sequential months of prescriptions, permitting 1-month gaps. We defined recurrence as re-initiation of COT after at least 2 months without prescriptions. The exposure was enactment of the PDMP mandate in NYC; NJ was unexposed. KEY RESULTS: Enactment of the NYS PDMP mandate was associated with an adjusted hazard ratio (HR) for cycling of 1.01 (95% CI, 0.94-1.08) in NYC. For high-dose prescriptions, the risk was 1.16 (95% CI, 1.01-1.34). Sensitivity analyses estimated an overall risk of 1.01 (95% CI, 0.94-1.11) and high-dose risk of 1.09 (95% CI, 0.91-1.31). CONCLUSIONS: The PDMP mandate had no overall effect on COT cycling in NYC but increased cycling risk among patients receiving high-dose opioid prescriptions by 16%, highlighting care discontinuity.

Utilization of Medications for Opioid Use Disorder Across US States: Relationship to Treatment Availability and Overdose Mortality.

OBJECTIVE: Availability of medications for opioid use disorder (MOUD) remains sparse. To date, there has been no national, state-by-state comparison of patient MOUD utilization relative to treatment availability and burden of overdose deaths. We aimed to quantify, for each state, the number of MOUD patients relative to (1) office-based buprenorphine providers and opioid treatment programs (OTPs) and (2) overdose deaths. METHODS: We conducted a spatial analysis of patients receiving MOUD from OTPs or buprenorphine providers in March 2017 across all 50 states and Washington, DC. For each state, we calculated the number of patients receiving MOUD from OTPs and buprenorphine prescriptions, relative to available OTPs and buprenorphine providers; as well as ratios of number of patients receiving MOUD relative to overdose deaths. RESULTS: In March 2017, 942,368 patients attended an OTP (410,288) or received a buprenorphine prescription (486,318). Patient to OTP ratio was highest in West Virginia, Delaware, Washington, DC, New Jersey, New Hampshire, Connecticut and Ohio, ranging from 91 to 193 patients per OTP in the first quintile to 430 to 648 in the fifth. Patient to buprenorphine provider ratio was highest in Kentucky and West Virginia, ranging from 3 to 7 patients per provider in the first quintile to 19 to 28 in the fifth. Median MOUD patients per overdose death was 21 (IQR:14.9-28.2). Of high overdose states, Washington, DC, New Jersey, and Ohio had the smallest number of patients on MOUD relative to deaths. CONCLUSIONS: High patient volume relative to treatment availability in overdose-burdened areas may indicate strain on MOUD providers and OTPs. Promoting greater utilization while expanding MOUD providers and programs is critical.

Temporal Trends in Opioid Prescribing Practices in Children, Adolescents, and Younger Adults in the US From 2006 to 2018.

Importance: Prescription opioids are involved in more than half of opioid overdoses among younger persons. Understanding opioid prescribing practices is essential for developing appropriate interventions for this population. Objective: To examine temporal trends in opioid prescribing practices in children, adolescents, and younger adults in the US from 2006 to 2018. Design, Setting, and Participants: A population-based, cross-sectional analysis of opioid prescription data was conducted from January 1, 2006, to December 31, 2018. Longitudinal data on retail pharmacy-dispensed opioids for patients younger than 25 years were used in the analysis. Data analysis was performed from December 26, 2019, to July 8, 2020. Main Outcomes and Measures: Opioid dispensing rate, mean amount of opioid dispensed in morphine milligram equivalents (MME) per day (individuals aged 15-24 years) or MME per kilogram per day (age <15 years), duration of prescription (mean, short [≤3 days], and long [≥30 days] duration), high-dosage prescriptions, and extended-release or long-acting (ER/LA) formulation prescriptions. Outcomes were calculated for age groups: 0 to 5, 6 to 9, 10 to 14, 15 to 19, and 20 to 24 years. Joinpoint regression was used to examine opioid prescribing trends. Results: From 2006 to 2018, the opioid dispensing rate for patients younger than 25 years decreased from 14.28 to 6.45, with an annual decrease of 15.15% (95% CI, -17.26% to -12.99%) from 2013 to 2018. The mean amount of opioids dispensed and rates of short-duration and high-dosage prescriptions decreased for all age groups older than 5 years, with the largest decreases in individuals aged 15 to 24 years. Mean duration per prescription increased initially for all ages, but then decreased for individuals aged 10 years or older. The duration remained longer than 5 days across all ages. The rate of long-duration prescriptions increased for all age groups younger than 15 years and initially increased, but then decreased after 2014 for individuals aged 15 to 24 years. For children aged 0 to 5 years dispensed an opioid, annual increases from 2011 to 2014 were noted for the mean amount of opioids dispensed (annual percent change [APC], 10.58%; 95% CI, 1.77% to 20.16%) and rates of long-duration (APC, 30.42%; 95% CI, 14.13% to 49.03%), high-dosage (APC, 31.27%; 95% CI, 16.81% to 47.53%), and ER/LA formulation (APC, 27.86%; 95% CI, 12.04% to 45.91%) prescriptions, although the mean amount dispensed and rate of high-dosage prescriptions decreased from 2014 to 2018. Conclusions and Relevance: These findings suggest that opioid dispensing rates decreased for patients younger than 25 years, with decreasing rates of high-dosage and long-duration prescriptions for adolescents and younger adults. However, opioids remain readily dispensed, and possible high-risk prescribing practices appear to be common, especially in younger children.

Opioid Use Disorder Treatment Facilities With Programs for Special Populations.

INTRODUCTION: Special populations, including veterans, pregnant and postpartum women, and adolescents, benefit from opioid use disorder treatment tailored to their specific needs, but access to such services is poorly described. This study identifies the availability of opioid use disorder treatment facilities that use medications and have special programming and contextualizes facilities amid counties' opioid-related overdose mortality. METHODS: Data were compiled on 15,945 U.S. treatment facilities using medications for opioid use disorder listed in the Behavioral Health Services Treatment Locator in 2018. Facilities with programs tailored to special populations (veterans, pregnant and postpartum women, and adolescents) were identified and geocoded. Counties with such facilities were characterized. Cold spots (county clusters with poor treatment availability) were identified using Getis-Ord Gi* statistics. Data were extracted in October 2018 and analyzed from October 2018 to May 2019. RESULTS: Of all 3,142 U.S. counties, 1,889 (60.1%) had opioid use disorder treatment facilities. Facilities with tailored programs for veterans, pregnant and postpartum women, and adolescents were located in 701 (22.3%), 918 (29.2%), and 1,062 (33.8%) of the counties, respectively. Specific medications provided for opioid use disorder varied, with only a minority of facilities offering methadone (among facilities with tailored programs for veterans, 6.0%; pregnant and postpartum women, 13.2%; adolescents, 1.3%). Many counties reporting opioid-related overdose deaths lacked programs for special populations (veterans, 72.6%; pregnant and postpartum women, 54.8%; adolescents, 30.6%). Cold spots were located throughout the Midwest, U.S. Southeast, and portions of Texas. CONCLUSIONS: Facilities using medications for opioid use disorder with tailored programs for veterans, pregnant and postpartum women, and adolescents are limited. There is a need for improved access to evidence-based programs that address the unique treatment needs of special populations.