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.

Impact of 30-day prescribed opioid dose trajectory on fatal overdose risk: A population-based, statewide cohort study.

BACKGROUND: Both increases and decreases in patients' prescribed daily opioid dose have been linked to increased overdose risk, but associations between 30-day dose trajectories and subsequent overdose risk have not been systematically examined. OBJECTIVE: To examine the associations between 30-day prescribed opioid dose trajectories and fatal opioid overdose risk during the subsequent 15 days. DESIGN: Statewide cohort study using linked prescription drug monitoring program and death certificate data. We constructed a multivariable Cox proportional hazards model that accounted for time-varying prescription-, prescriber-, and pharmacy-level factors. PARTICIPANTS: All patients prescribed an opioid analgesic in California from March to December, 2013 (5,326,392 patients). MAIN MEASURES: Dependent variable: fatal drug overdose involving opioids. Primary independent variable: a 16-level variable denoting all possible opioid dose trajectories using the following categories for current and 30-day previously prescribed daily dose: 0-29, 30-59, 60-89, or ≥90 milligram morphine equivalents (MME). KEY RESULTS: Relative to patients prescribed a stable daily dose of 0-29 MME, large (≥2 categories) dose increases and having a previous or current dose ≥60 MME per day were associated with significantly greater 15-day overdose risk. Patients whose dose decreased from ≥90 to 0-29 MME per day had significantly greater overdose risk compared to both patients prescribed a stable daily dose of ≥90 MME (aHR 3.56, 95%CI 2.24-5.67) and to patients prescribed a stable daily dose of 0-29 MME (aHR 7.87, 95%CI 5.49-11.28). Patients prescribed benzodiazepines also had significantly greater overdose risk; being prescribed Z-drugs, carisoprodol, or psychostimulants was not associated with overdose risk. CONCLUSIONS: Large (≥2 categories) 30-day dose increases and decreases were both associated with increased risk of fatal opioid overdose, particularly for patients taking ≥90 MME whose opioids were abruptly stopped. Results align with 2022 CDC guidelines that urge caution when reducing opioid doses for patients taking long-term opioid for chronic pain.

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.

Outcome class imbalance and rare events: An underappreciated complication for overdose risk prediction modeling.

BACKGROUND AND AIMS: Low outcome prevalence, often observed with opioid-related outcomes, poses an underappreciated challenge to accurate predictive modeling. Outcome class imbalance, where non-events (i.e. negative class observations) outnumber events (i.e. positive class observations) by a moderate to extreme degree, can distort measures of predictive accuracy in misleading ways, and make the overall predictive accuracy and the discriminatory ability of a predictive model appear spuriously high. We conducted a simulation study to measure the impact of outcome class imbalance on predictive performance of a simple SuperLearner ensemble model and suggest strategies for reducing that impact. DESIGN, SETTING, PARTICIPANTS: Using a Monte Carlo design with 250 repetitions, we trained and evaluated these models on four simulated data sets with 100 000 observations each: one with perfect balance between events and non-events, and three where non-events outnumbered events by an approximate factor of 10:1, 100:1, and 1000:1, respectively. MEASUREMENTS: We evaluated the performance of these models using a comprehensive suite of measures, including measures that are more appropriate for imbalanced data. FINDINGS: Increasing imbalance tended to spuriously improve overall accuracy (using a high threshold to classify events vs non-events, overall accuracy improved from 0.45 with perfect balance to 0.99 with the most severe outcome class imbalance), but diminished predictive performance was evident using other metrics (corresponding positive predictive value decreased from 0.99 to 0.14). CONCLUSION: Increasing reliance on algorithmic risk scores in consequential decision-making processes raises critical fairness and ethical concerns. This paper provides broad guidance for analytic strategies that clinical investigators can use to remedy the impacts of outcome class imbalance on risk prediction tools.

Invited Commentary: On the Mathematization of Epidemiology as a Socially Engaged Quantitative Science.

Ensuring that patients with opioid use disorder (OUD) have access to optimal medication therapies is a critical challenge in substance use epidemiology. Rudolph et al. (Am J Epidemiol. 2023;XXX(X):XXXX-XXXX) demonstrated that sophisticated data-adaptive statistical techniques can be used to learn optimal, individualized treatment rules that can aid providers in choosing a medication treatment modality for a particular patient with OUD. This important work also highlights the effects of the mathematization of epidemiologic research. Here, we define mathematization and demonstrate how it operates in the context of effectiveness research on medications for OUD using the paper by Rudolph et al. as a springboard. In particular, we address the normative dimension of mathematization and how it tends to resolve a fundamental tension in epidemiologic practice between technical sophistication and public health considerations in favor of more technical solutions. The process of mathematization is a fundamental part of epidemiology; we argue not for eliminating it but for balancing mathematization and technical demands equally with practical and community-centric public health needs.

Divergence Between Individual- and Neighborhood-Level Fatal Overdose Burden: A Population-Based Statewide Study.

OBJECTIVES: To compare the characteristics of individual overdose decedents in Rhode Island, 2016-2020 to the neighborhoods where fatal overdoses occurred over the same time period. METHODS: We conducted a retrospective analysis of fatal overdoses occurring between January 1, 2016 and June 30, 2020. Using individual- and neighborhood-level data, we conducted descriptive analyses to explore the characteristics of individuals and neighborhoods most affected by overdose. RESULTS: Most overdose decedents during the study period were non-Hispanic White. Across increasingly more White and non-Hispanic neighborhoods, rates of fatal overdose per 100,000 person-years decreased. An opposite pattern was observed across quintiles of average neighborhood poverty. CONCLUSIONS: Rates of fatal overdose were higher in less White, more Hispanic, and poorer neighborhoods, suggesting modest divergence between the characteristics of individuals and the neighborhoods most severely affected. These impacts may not be uniform across space and may accrue differentially to more disadvantaged and racially/ethnically diverse neighborhoods.

Use of a Doubly Robust Machine-Learning-Based Approach to Evaluate Body Mass Index as a Modifier of the Association Between Fruit and Vegetable Intake and Preeclampsia.

The Dietary Guidelines for Americans rely on summaries of the effect of dietary pattern on disease risk, independent of other population characteristics. We explored the modifying effect of prepregnancy body mass index (BMI; weight (kg)/height (m)2) on the relationship between fruit and vegetable density (cup-equivalents/1,000 kcal) and preeclampsia using data from a pregnancy cohort study conducted at 8 US medical centers (n = 9,412; 2010-2013). Usual daily periconceptional intake of total fruits and total vegetables was estimated from a food frequency questionnaire. We quantified the effects of diets with a high density of fruits (≥1.2 cups/1,000 kcal/day vs. <1.2 cups/1,000 kcal/day) and vegetables (≥1.3 cups/1,000 kcal/day vs. <1.3 cups/1,000 kcal/day) on preeclampsia risk, conditional on BMI, using a doubly robust estimator implemented in 2 stages. We found that the protective association of higher fruit density declined approximately linearly from a BMI of 20 to a BMI of 32, by 0.25 cases per 100 women per each BMI unit, and then flattened. The protective association of higher vegetable density strengthened in a linear fashion, by 0.3 cases per 100 women for every unit increase in BMI, up to a BMI of 30, where it plateaued. Dietary patterns with a high periconceptional density of fruits and vegetables appear more protective against preeclampsia for women with higher BMI than for leaner women.

Adverse Cardiovascular Events Following Severe Maternal Morbidity.

Severe maternal morbidity (SMM) affects 50,000 women annually in the United States, but its consequences are not well understood. We aimed to estimate the association between SMM and risk of adverse cardiovascular events during the 2 years postpartum. We analyzed 137,140 deliveries covered by the Pennsylvania Medicaid program (2016-2018), weighted with inverse probability of censoring weights to account for nonrandom loss to follow-up. SMM was defined as any diagnosis on the Centers for Disease Control and Prevention list of SMM diagnoses and procedures and/or intensive care unit admission occurring at any point from conception through 42 days postdelivery. Outcomes included heart failure, ischemic heart disease, and stroke/transient ischemic attack up to 2 years postpartum. We used marginal standardization to estimate average treatment effects. We found that SMM was associated with increased risk of each adverse cardiovascular event across the follow-up period. Per 1,000 deliveries, relative to no SMM, SMM was associated with 12.1 (95% confidence interval (CI): 6.2, 18.0) excess cases of heart failure, 6.4 (95% CI: 1.7, 11.2) excess cases of ischemic heart disease, and 8.2 (95% CI: 3.2, 13.1) excess cases of stroke/transient ischemic attack at 26 months of follow-up. These results suggest that SMM identifies a group of women who are at high risk of adverse cardiovascular events after delivery. Women who survive SMM may benefit from more comprehensive postpartum care linked to well-woman care.

Can Ensemble Machine Learning Improve the Accuracy of Severe Maternal Morbidity Screening in a Perinatal Database?

BACKGROUND: Severe maternal morbidity (SMM) is an important maternal health indicator, but existing tools to identify SMM have substantial limitations. Our objective was to retrospectively identify true SMM status using ensemble machine learning in a hospital database and to compare machine learning algorithm performance with existing tools for SMM identification. METHODS: We screened all deliveries occurring at Magee-Womens Hospital, Pittsburgh, PA (2010-2011 and 2013-2017) using the Centers for Disease Control and Prevention list of diagnoses and procedures for SMM, intensive care unit admission, and/or prolonged postpartum length of stay. We performed a detailed medical record review to confirm case status. We trained ensemble machine learning (SuperLearner) algorithms, which "stack" predictions from multiple algorithms to obtain optimal predictions, on 171 SMM cases and 506 non-cases from 2010 to 2011, then evaluated the performance of these algorithms on 160 SMM cases and 337 non-cases from 2013 to 2017. RESULTS: Some SuperLearner algorithms performed better than existing screening criteria in terms of positive predictive value (0.77 vs. 0.64, respectively) and balanced accuracy (0.99 vs. 0.86, respectively). However, they did not perform as well as the screening criteria in terms of true-positive detection rate (0.008 vs. 0.32, respectively) and performed similarly in terms of negative predictive value. The most important predictor variables were intensive care unit admission and prolonged postpartum length of stay. CONCLUSIONS: Ensemble machine learning did not globally improve the ascertainment of true SMM cases. Our results suggest that accurate identification of SMM likely will remain a challenge in the absence of a universal definition of SMM or national obstetric surveillance systems.

Pregnancy weight gain in twin gestations and maternal and child health outcomes at 5 years.

OBJECTIVE: Current guidelines for maternal weight gain in twin pregnancy were established in the absence of evidence on its longer-term consequences for maternal and child health. We evaluated the association between weight gain in twin pregnancies and the risk of excess maternal postpartum weight increase, childhood obesity, and child cognitive ability. METHODS: We used 5-year follow-up data from 1000 twins born to 450 mothers in the Early Childhood Longitudinal Study-Birth Cohort, a nationally representative U.S. cohort of births in 2001. Pregnancy weight gain was standardized into gestational age- and prepregnancy body mass index (BMI)-specific z-scores. Excess postpartum weight increase was defined as ≥10 kg increase from prepregnancy weight. We defined child overweight/obesity as BMI ≥ 85th percentile, and low reading and math achievement as scores one standard deviation below the mean. We used survey-weighted multivariable modified Poisson models with a log link to relate gestational weight gain z-score with each outcome. RESULTS: Excess postpartum weight increase occurred in 40% of mothers. Approximately 28% of twins were affected by overweight/obesity, and 16 and 14% had low reading and low math scores. There was a positive linear relationship between pregnancy weight gain and both excess postpartum weight increase and childhood overweight/obesity. Compared with a gestational weight gain z-score 0 SD (equivalent to 20 kg at 37 weeks gestation), a weight gain z-score of +1 SD (27 kg) was associated with 6.3 (0.71, 12) cases of excess weight increase per 1000 women and 4.5 (0.81, 8.2) excess cases of child overweight/obesity per 100 twins. Gestational weight gain was not related to kindergarten academic readiness. CONCLUSIONS: The high prevalence of excess postpartum weight increase and childhood overweight/obesity within the recommended ranges of gestational weight gain for twin pregnancies suggests that these guidelines could be inadvertently contributing to longer-term maternal and child obesity.

Machine learning as a strategy to account for dietary synergy: an illustration based on dietary intake and adverse pregnancy outcomes.

BACKGROUND: Conventional analytic approaches for studying diet patterns assume no dietary synergy, which can lead to bias if incorrectly modeled. Machine learning algorithms can overcome these limitations. OBJECTIVES: We estimated associations between fruit and vegetable intake relative to total energy intake and adverse pregnancy outcomes using targeted maximum likelihood estimation (TMLE) paired with the ensemble machine learning algorithm Super Learner, and compared these with results generated from multivariable logistic regression. METHODS: We used data from 7572 women in the Nulliparous Pregnancy Outcomes Study: monitoring mothers-to-be. Usual daily periconceptional intake of total fruits and total vegetables was estimated from an FFQ. We calculated the marginal risk of preterm birth, small-for-gestational-age (SGA) birth, gestational diabetes, and pre-eclampsia according to density of fruits and vegetables (cups/1000 kcal) ≥80th percentile compared with <80th percentile using multivariable logistic regression and Super Learner with TMLE. Models were adjusted for confounders, including other Healthy Eating Index-2010 components. RESULTS: Using logistic regression, higher fruit and high vegetable densities were associated with 1.1% and 1.4% reductions in pre-eclampsia risk compared with lower densities, respectively. They were not associated with the 3 other outcomes. Using Super Learner with TMLE, high fruit and vegetable densities were associated with fewer cases of preterm birth (-4.0; 95% CI: -4.9, -3.0 and -3.7; 95% CI: -5.0, -2.3), SGA (-1.7; 95% CI: -2.9, -0.51 and -3.8; 95% CI: -5.0, -2.5), and pre-eclampsia (-3.2; 95% CI: -4.2, -2.2 and -4.0; 95% CI: -5.2, -2.7) per 100 births, respectively, and high vegetable densities were associated with a 0.9% increase in risk of gestational diabetes. CONCLUSIONS: The differences in results between Super Learner with TMLE and logistic regression suggest that dietary synergy, which is accounted for in machine learning, may play a role in pregnancy outcomes. This innovative methodology for analyzing dietary data has the potential to advance the study of diet patterns.

Placental Mechanics in the Zika-Microcephaly Relationship.

How the Zika virus (ZIKV) accesses the embryo remains unknown. In this issue, Quicke et al. (2016) use an in vitro model of the human placenta to show that placental macrophages are more permissive to ZIKV infection than trophoblasts, which may be refractory to infection (Bayer et al., 2016).