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.

The impact of preexisting psychiatric disorders and antidepressant use on COVID-19 related outcomes: a multicenter study.

Pre-existing mental disorders are linked to COVID-19-related outcomes. However, the findings are inconsistent and a thorough analysis of a broader spectrum of outcomes such as COVID-19 infection severity, morbidity, and mortality is required. We investigated whether the presence of psychiatric diagnoses and/or the use of antidepressants influenced the severity of the outcome of COVID-19. This retrospective cohort study evaluated electronic health records from the INSIGHT Clinical Research Network in 116,498 individuals who were diagnosed with COVID-19 between March 1, 2020, and February 23, 2021. We examined hospitalization, intubation/mechanical ventilation, acute kidney failure, severe sepsis, and death as COVID-19-related outcomes. After using propensity score matching to control for demographics and medical comorbidities, we used contingency tables to assess whether patients with (1) a history of psychiatric disorders were at higher risk of more severe COVID-19-related outcomes and (2) if use of antidepressants decreased the risk of more severe COVID-19 infection. Pre-existing psychiatric disorders were associated with an increased risk for hospitalization, and subsequent outcomes such as acute kidney failure and severe sepsis, including an increased risk of death in patients with schizophrenia spectrum disorders or bipolar disorders. The use of antidepressants was associated with significantly reduced risk of sepsis (p = 0.033), death (p = 0.026). Psychiatric disorder diagnosis prior to a COVID-19-related healthcare encounter increased the risk of more severe COVID-19-related outcomes as well as subsequent health complications. However, there are indications that the use of antidepressants might decrease this risk. This may have significant implications for the treatment and prognosis of patients with COVID-19.

ODMAP: Stakeholder Perspectives on a Novel Public Health and Public Safety Overdose Surveillance System.

This pilot study explores the utilization of the Overdose Detection Mapping Application Program (ODMAP) as a tool for enhancing collaboration between the public health and public safety sectors to address the overdose epidemic in the United States. Through qualitative interviews with ODMAP users, key themes emerged, including the role of data sharing in facilitating collaboration, challenges posed by divergent data privacy standards, and the need for clearer guidance on cross-sector data sharing. Findings highlight ODMAP's potential to integrate data for targeted interventions at individual and population levels. Future research directions include overcoming data sharing barriers, strategically utilizing data across sectors, and rigorously evaluating the impact of cross-sector partnerships on overdose morbidity and mortality. Overall, this study underscores the importance of ODMAP in fostering coordinated responses to the overdose crisis and provides valuable insights for improving overdose surveillance and intervention efforts.

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.

Racial differences in COVID-19 severity associated with history of substance use disorders and overdose: Findings from multi-site electronic health records in New York City.

Substance use disorders (SUD) are associated with increased risk of worse COVID-19 outcomes. Likewise, racial/ethnic minority patients experience greater risk of severe COVID-19 disease compared to white patients. Providers should understand the role of race and ethnicity as an effect modifier on COVID-19 severity among individuals with SUD. This retrospective cohort study assessed patient race/ethnicity as an effect modifier of the risk of severe COVID-19 disease among patients with histories of SUD and overdose. We used merged electronic health record data from 116,471 adult patients with a COVID-19 encounter between March 2020 and February 2021 across five healthcare systems in New York City. Exposures were patient histories of SUD and overdose. Outcomes were risk of COVID-19 hospitalization and subsequent COVID-19-related ventilation, acute kidney failure, sepsis, and mortality. Risk factors included patient age, sex, and race/ethnicity, as well as medical comorbidities associated with COVID-19 severity. We tested for interaction between SUD and patient race/ethnicity on COVID-19 outcomes. Findings showed that Non-Hispanic Black, Hispanic/Latino, and Asian/Pacific Islander patients experienced a higher prevalence of all adverse COVID-19 outcomes compared to non-Hispanic white patients. Past-year alcohol (OR 1.24 [1.01-1.53]) and opioid use disorders (OR 1.91 [1.46-2.49]), as well as overdose history (OR 4.45 [3.62-5.46]), were predictive of COVID-19 mortality, as well as other adverse COVID-19 outcomes. Among patients with SUD, significant differences in outcome risk were detected between patients of different race/ethnicity groups. Findings indicate that providers should consider multiple dimensions of vulnerability to adequately manage COVID-19 disease among populations with SUDs.

Identifying Predictors of Opioid Overdose Death at a Neighborhood Level With Machine Learning.

Predictors of opioid overdose death in neighborhoods are important to identify, both to understand characteristics of high-risk areas and to prioritize limited prevention and intervention resources. Machine learning methods could serve as a valuable tool for identifying neighborhood-level predictors. We examined statewide data on opioid overdose death from Rhode Island (log-transformed rates for 2016-2019) and 203 covariates from the American Community Survey for 742 US Census block groups. The analysis included a least absolute shrinkage and selection operator (LASSO) algorithm followed by variable importance rankings from a random forest algorithm. We employed double cross-validation, with 10 folds in the inner loop to train the model and 4 outer folds to assess predictive performance. The ranked variables included a range of dimensions of socioeconomic status, including education, income and wealth, residential stability, race/ethnicity, social isolation, and occupational status. The R2 value of the model on testing data was 0.17. While many predictors of overdose death were in established domains (education, income, occupation), we also identified novel domains (residential stability, racial/ethnic distribution, and social isolation). Predictive modeling with machine learning can identify new neighborhood-level predictors of overdose in the continually evolving opioid epidemic and anticipate the neighborhoods at high risk of overdose mortality.

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.

Primary care provider perspectives on and utilization of a mandatory prescription drug monitoring program in New York City.

BACKGROUND: The ways in which prescription drug monitoring programs (PDMPs) have been integrated into primary care practice remain understudied, and research into physician utilization of PDMPs in states where PDMP use is mandated remains scant. OBJECTIVES: To characterize primary care physician perspectives on and utilization of a mandatory PDMP in New York City. METHODS: We conducted face-to-face, in-depth interviews with primary care physicians who reported that they currently prescribed opioid analgesic medication. We used a thematic analytic approach to characterize physician perspectives on the PDMP mandate and physician integration of mandatory PDMP use into primary care practice. RESULTS: Primary care providers demonstrated a continuum of PDMP utilization, ranging from consistent use to the specifications of the mandate to inconsistent use to no use. Providers reported a range of perspectives on the purpose and function of the PDMP mandate, as well as a lack of clarity about the mandate and its enforcement. CONCLUSION: Findings suggest a need for increased clinical and public health education about the use of PDMPs as clinical tools to identify and treat patients with potential substance use disorders in primary care.

The New York City Prescriber Notification Program: Assessing the Feasibility of a Patient Overdose Death Notification Pilot.

Opioid analgesics and benzodiazepines remain substantial contributors to unintentional drug overdose deaths in the United States. To promote judicious prescribing and improve care for patients with substance use disorders, the New York City Department of Health and Mental Hygiene piloted the Prescriber Notification Program, an educational initiative to deliver targeted public health messaging to providers who had prescribed opioid analgesics and/or benzodiazepines to patients who died from overdose in New York City. This article reports on provider responses to receipt of patient death notifications and program feasibility. Findings demonstrate that a majority of prescribers were not aware of patient deaths prior to receiving notification letters. Public health authorities considering prescriber notification systems should address barriers to implementation and sustainability-in particular, consistent and routine access to and linkage of overdose mortality and prescription monitoring data-as part of planning such programs.

Association of substance use disorders and drug overdose with adverse COVID-19 outcomes in New York City: January-October 2020.

BACKGROUND: Evidence suggests that individuals with history of substance use disorder (SUD) are at increased risk of COVID-19, but little is known about relationships between SUDs, overdose and COVID-19 severity and mortality. This study investigated risks of severe COVID-19 among patients with SUDs. METHODS: We conducted a retrospective review of data from a hospital system in New York City. Patient records from 1 January to 26 October 2020 were included. We assessed positive COVID-19 tests, hospitalizations, intensive care unit (ICU) admissions and death. Descriptive statistics and bivariable analyses compared the prevalence of COVID-19 by baseline characteristics. Logistic regression estimated unadjusted and sex-, age-, race- and comorbidity-adjusted odds ratios (AORs) for associations between SUD history, overdose history and outcomes. RESULTS: Of patients tested for COVID-19 (n = 188 653), 2.7% (n = 5107) had any history of SUD. Associations with hospitalization [AORs (95% confidence interval)] ranged from 1.78 (0.85-3.74) for cocaine use disorder (COUD) to 6.68 (4.33-10.33) for alcohol use disorder. Associations with ICU admission ranged from 0.57 (0.17-1.93) for COUD to 5.00 (3.02-8.30) for overdose. Associations with death ranged from 0.64 (0.14-2.84) for COUD to 3.03 (1.70-5.43) for overdose. DISCUSSION: Patients with histories of SUD and drug overdose may be at elevated risk of adverse COVID-19 outcomes.

Diversity and Political Leaning: Considerations for Epidemiology.

The positive effects of increased diversity and inclusion in scientific research and practice are well documented. In this issue, DeVilbiss et al. (Am J Epidemiol. 2020;189(10):998-1010) present findings from a survey used to collect information to characterize diversity among epidemiologists and perceptions of inclusion in the epidemiologic profession. They capture identity across a range of personal characteristics, including race, gender, socioeconomic background, sexual orientation, religion, and political leaning. In this commentary, we assert that the inclusion of political leaning as an axis of identity alongside the others undermines the larger project of promoting diversity and inclusion in the profession and is symptomatic of the movement for "ideological diversity" in higher education. We identify why political leaning is not an appropriate metric of diversity and detail why prioritizing ideological diversity counterintuitively can work against equity building initiatives. As an alternative to ideological diversity, we propose that epidemiologists take up an existing framework for research and practice that centers the voices and perspectives of historically marginalized populations in epidemiologic work.

Substance Use Stigma, Primary Care, and the New York State Prescription Drug Monitoring Program.

Prescription drug monitoring programs (PDMPs) are databases that track controlled substances at the provider, patient, and pharmacy levels. While these databases are widely available at the state level throughout the United States, several jurisdictions in recent years have mandated the use of these systems by health care providers. This study explores the implementation of mandatory PDMP technology in primary care practice and the effects on treatment of people with possible substance use disorders. Findings are based on 53 in-depth interviews with primary care providers in New York City, collected shortly following the passage of legislation mandating use of a PDMP by health care providers in New York State. Findings suggest that use of the PDMP highlighted tensions between provider stigma toward substance use disorders and the clinical care of people who use drugs, challenging their stereotypes and biases. The parallel clinical and law enforcement purposes of PDMP technology placed providers in dual roles as clinicians and enforcers and encouraged the punitive treatment of patients. Finally, PDMP technology standardized the clinical assessment process toward a "diagnosis first" approach, consistent with prior scholarship on the implementation of emerging medical technologies.

Delivering Opioid Overdose Prevention in Bars and Nightclubs: A Public Awareness Pilot in New York City.

Drug seizure data indicate the presence of fentanyl in the cocaine supplies nationally and in New York City (NYC). In NYC, 39% of cocaine-only involved overdose deaths in 2017 also involved fentanyl, suggesting that fentanyl in the cocaine supply is associated with overdose deaths. To raise awareness of fentanyl overdose risk among people who use cocaine, the NYC Department of Health and Mental Hygiene pilot tested an awareness campaign in 23 NYC nightlife venues. Although 87% of venue owners/managers were aware of fentanyl, no participating venues had naloxone on premises prior to the intervention. The campaign's rapid dissemination reached people at potential risk of opioid overdose in a short period of time following the identification of fentanyl in the cocaine supply. Public health authorities in states with high rates of opioid-involved overdose death should consider similar campaigns to deliver overdose prevention education in the context of a drug supply containing fentanyl.

Relay: A Peer-Delivered Emergency Department-Based Response to Nonfatal Opioid Overdose.

Relay, a peer-delivered response to nonfatal opioid overdoses, provides overdose prevention education, naloxone, support, and linkage to care to opioid overdose survivors for 90 days after an overdose event. From June 2017 to December 2018, Relay operated in seven New York City emergency departments and enrolled 649 of the 876 eligible individuals seen (74%). Preliminary data show high engagement, primarily among individuals not touched by harm reduction or naloxone distribution networks. Relay is a novel and replicable response to the opioid epidemic.

Alternative kinship structures, resilience and social support among immigrant trans Latinas in the USA.

Latinas comprise the largest racial/ethnic group of trans women (male-to-female transgender people) in New York City, where HIV seroprevalence among trans Latinas has been found to be as high as 49%. Despite this population's high risk of HIV, little is known about resilience among trans Latinas that may provide protective health factors. Six focus groups and one in-depth interview were conducted with 34 low-income trans/gender-variant people of colour who attended transgender support groups at harm reduction programmes in New York City. This paper reports on data from 13 participants who identified as immigrant trans Latinas. Focus groups were coded and analysed using thematic qualitative methods. The majority of immigrants were undocumented but reported having robust social support. Unique characteristics of immigrant trans Latinas included alternative kinship structures and sources of income. Social creativity was used to develop achievable ways in which to improve their health outcomes. Resilience was evident in informal kinship dynamics, formal support groups, gender-transition, educational access and skills training and substance use reduction. Individual-level resilience increased as a result of strong community-level resilience.

Underutilization of medications to treat opioid use disorder: What role does stigma play?

There is consensus in the scientific literature that the opioid agonist medications methadone and buprenorphine are the most effective treatments for opioid use disorder. Despite increasing opioid overdose deaths in the United States, these medications remain substantially underutilized. For no other medical conditions for which an effective treatment exists is that treatment used so infrequently. In this commentary, we discuss the potential role of stigma in the underutilization of these opioid agonist medications for addiction treatment. We outline stigma toward medications for addiction treatment and suggest that structural and policy barriers to methadone and buprenorphine may contribute to this stigma. We offer pragmatic public health solutions to reduce stigma and expand access to these effective treatments.

Reassessment of insulin dosing guidelines in continuous subcutaneous insulin infusion treated type 1 diabetes.

It is a daunting task to initiate or evaluate continuous subcutaneous insulin infusion, pump, dosing in a patient with type 1 diabetes. Choosing a low dose may lead to hyperglycemia or, too high, hypoglycemia. Mathematical dosing guidelines were used with the first human insulin injection in 1922. Since that time, they have been enlarged and modified. The current widely published guidelines were developed from retrospective evaluations of pump-downloads in patients without specified diet conditions or timed glucose testing. When diet is controlled and glucose testing is timed to evaluate post-meal excursions and during sleep, recent prospective studies found that these current dosing recommendations for basal insulin were too high and for bolus insulin too low. Further, simple mathematical interrelationships were published that kept the right proportions between the bolus dosing factors and the basal dose.

NYC RxStat: Stakeholder perspectives on a national model public health and public safety partnership to reduce overdose deaths.

NYC RxStat, the United States' first public health and public safety partnership aiming to reduce overdose deaths, began in 2012 and established a national model for cross-sector partnerships. The partnership aimed to integrate data-driven policing with actionable public health interventions and surveillance to develop and implement cross-sector overdose responses. With federal support, jurisdictions nationally have implemented public health and public safety partnerships modeled on RxStat. To inform partnership replication efforts, we conducted a stakeholder evaluation of RxStat. We conducted in-depth, semi-structured interviews with 25 current and former RxStat stakeholders. Interviews probed stakeholder perceptions of RxStat's successes, challenges, and opportunities for growth. Interview data were iteratively coded and thematically analyzed. Stakeholders reported certainty about the need for cross-sector collaboration and described cross-disciplinary tensions, challenges to collaboration and implementation, and opportunities for partnership optimization and growth. Findings informed 12 strategies to improve RxStat and partnerships in its model, organized into three opportunity areas: (1) ensure stakeholder and agency accountability; (2) build secure and mutually beneficial data systems; and (3) structure partnerships to facilitate equitable collaboration. Cross-sector partnerships offer a promising strategy to integrate the public health and safety sectors, but disciplinary tensions in approach may hamper implementation. Findings can inform efforts to implement and scale cross-sector partnerships.