Predicting pediatric severe asthma exacerbations: an administrative claims-based predictive model.

OBJECTIVE: Previous machine learning approaches fail to consider race and ethnicity and social determinants of health (SDOH) to predict childhood asthma exacerbations. A predictive model for asthma exacerbations in children is developed to explore the importance of race and ethnicity, rural-urban commuting area (RUCA) codes, the Child Opportunity Index (COI), and other ICD-10 SDOH in predicting asthma outcomes. METHODS: Insurance and coverage claims data from the Arkansas All-Payer Claims Database were used to capture risk factors. We identified a cohort of 22,631 children with asthma aged 5-18 years with 2 years of continuous Medicaid enrollment and at least one asthma diagnosis in 2018. The goal was to predict asthma-related hospitalizations and asthma-related emergency department (ED) visits in 2019. The analytic sample was 59% age 5-11 years, 39% White, 33% Black, and 6% Hispanic. Conditional random forest models were used to train the model. RESULTS: The model yielded an area under the curve (AUC) of 72%, sensitivity of 55% and specificity of 78% in the OOB samples and AUC of 73%, sensitivity of 58% and specificity of 77% in the training samples. Consistent with previous literature, asthma-related hospitalization or ED visits in the previous year (2018) were the two most important variables in predicting hospital or ED use in the following year (2019), followed by the total number of reliever and controller medications. CONCLUSIONS: Predictive models for asthma-related exacerbation achieved moderate accuracy, but race and ethnicity, ICD-10 SDOH, RUCA codes, and COI measures were not important in improving model accuracy.

Identification of racial/ethnic disparities associated with severe maternal morbidity using the Arkansas All-Payer Claims Database (2013-2017).

OBJECTIVE: To evaluate the effect of maternal characteristics on the odds of severe maternal morbidity (SMM) through 42 days postpartum. STUDY DESIGN: We conducted a retrospective observational study of 77 172 births using birth certificate and insurance claims data from the Arkansas All Payers Claims Database, years 2013-2017, to identify racial disparities associated with SMM for births between April 1, 2014, and November 19, 2017. METHODS: Multiple logistic regression was used to examine the effect of sociodemographic factors and clinical comorbidities on the odds of SMM among non-Hispanic white ("white"), non-Hispanic Black ("Black"), and Hispanic women. RESULTS: The rate of SMM was 227.41 per 10 000 births, with Black women (330 per 10 000 births; 95% CI: 296.16-366.38), having a significantly higher rates than white women (197; 95% CI: 171.72-225.84) and Hispanic women (180; 95% CI: 155.86-207.54). After adjusting for maternal demographics, birth-related clinical variables, and comorbidities, SMM remained higher among Black women (aOR 1.37; 95% CI 1.11-1.70) relative to white women. CONCLUSIONS: Comorbidities, socioeconomic factors, and other factors did not fully explain the Black-white disparities in SMM. Persistent disparities in the rates of SMM throughout 42 days postpartum among Black women relative to white women points to the need for higher quality, more equitable care for women of color in the fist months postpartum.

Cost-benefit analysis of home visiting to reduce infant mortality among preterm infants.

PURPOSE: The Following Baby Back Home (FBBH) visiting program, which is provided by nurse and social worker teams, supports families of low-birthweight preterm infants after discharge from a neonatal intensive care unit. Enrollment in the FBBH program has been documented to reduce the likelihood of infant death. In this study, we conducted a cost-benefit analysis of the FBBH program. DESIGN AND METHODS: Infants enrolled in the FBBH program (N = 416) were identified through administrative records. Infants in the FBBH program were propensity score matched with comparison infants to estimate the difference in healthcare costs in the first year of life. RESULTS: Infants enrolled in the FBBH program incurred similar medical care costs compared to a comparison group. Avoided deaths, program costs, healthcare costs resulted in net economic benefits of the FBBH program to avoid infant death estimate at $83,020, cost per life saved at $3080, and benefit-to-cost ratio at 27.95. CONCLUSIONS: The FBBH program's net economic benefits from avoided deaths suggest a substantial return on investment of resources, yielding benefits in excess of program and healthcare costs. PRACTICE IMPLICATIONS: It is economically beneficial to provide home visiting services to families of low-birthweight babies by a team comprised of a registered nurse and social worker.

Labor market participation and productivity costs for female caregivers of minor male children with Duchenne and Becker muscular dystrophies.

INTRODUCTION/AIMS: Duchenne and Becker muscular dystrophies (DBMD) are X-linked neuromuscular disorders characterized by progressive muscle weakness, leading to decreased mobility and multisystem complications. We estimate productivity costs attributable to time spent by a parent caring for a male child under the age of 18 y with DBMD, with particular focus on female caregivers of boys with Duchenne muscular dystrophy (DMD) who have already lost ambulation. METHODS: Primary caregivers of males with DBMD in the Muscular Dystrophy Surveillance and Research Tracking Network (MD STARnet) were surveyed during 2011-2012 on family quality of life measures, including labor market outcomes. Of 211 respondents, 96 female caregivers of boys with DBMD were matched on state, year of survey, respondent's age, child's age, and number of minor children with controls constructed from Current Population Survey extracts. Regression analysis was used to estimate labor market outcomes and productivity costs. RESULTS: Caregivers of boys with DBMD worked 296 h less per year on average than caregivers of unaffected children, translating to a $8816 earnings loss in 2020 U.S. dollars. Caregivers of boys with DMD with ≥4 y of ambulation loss had a predicted loss in annualized earnings of $23,995, whereas caregivers of boys with DBMD of the same ages who remained ambulatory had no loss of earnings. DISCUSSION: Female caregivers of non-ambulatory boys with DMD face additional household budget constraints through income loss. Failure to include informal care costs in economic studies could understate the societal cost-effectiveness of strategies for managing DMD that might prolong ambulation.

Association of the COVID-19 pandemic and dying at home due to ischemic heart disease.

The coronavirus disease 2019 (COVID-19) pandemic has been associated with a declining volume of patients seen in the emergency department. Despite the need for seeking urgent care for conditions such as myocardial infarction, many people may not seek treatment. This study seeks to measure associations between the COVID-19 pandemic and location of death among individuals who died from ischemic heart disease (IHD). Data obtained from death certificates from the Arkansas Department of Health was used to conduct a difference-in-difference analysis to assess whether decedents of IHD were more likely to die at home during the pandemic (March 2020 through September 2020). The analysis compared location of death for decedents of IHD pre and during the pandemic to location of death for decedents from non-natural causes. Before the pandemic, 50.0% of decedents of IHD died at home compared to 57.9% dying at home during (through September 2020) the pandemic study period (p < .001). There was no difference in the proportion of decedents who died at home from non-natural causes before and during the pandemic study period (55.8% vs. 53.5%; p = .21). After controlling for confounders, there was a 48% increase in the odds of dying at home from IHD during the pandemic study period (p < .001) relative to the change in dying at home due to non-natural causes. During the study period, there was an increase in the proportion of decedents who died at home due to IHD. Despite the ongoing pandemic, practitioners should emphasize the need to seek urgent care during an emergency.

Improving quality of life assessments for high-need adult Medicaid service users with mental health conditions.

PURPOSE: There is a lack of consensus on how to evaluate health and social service programs for people with mental health (MH) conditions. Having service users be the primary decision makers in selecting outcome measures can inform a meaningful evaluation strategy. We sought to identify the quality of life (QoL) survey preferences of high-need adult service users with MH conditions. METHODS: A systematic review identified generic, self-reported QoL surveys with evidence of validity in MH populations of interest. An advisory panel selected the most promising surveys to assess the success of programs like Medicaid for MH service users. Three groups of high-need, adult service users with MH conditions and one group of direct care staff ranked the surveys from the advisory panel, and generated and ranked characteristics that were desirable or undesirable in a QoL survey. RESULTS: Twenty-two surveys met the inclusion criteria. Of the six surveys selected by the advisory panel, groups of service users and direct care staff most preferred the Warwick-Edinburg Mental Well-being Scale (WEMWBS). The WEMWBS best embodied the features prioritized by the groups: to have a user-friendly format and positive focus, to be clearly worded and brief, and to avoid presumptive or unrealistic items. Service user groups appreciated survey topics most amenable to self-report, such as satisfaction with relationships. CONCLUSION: Using QoL surveys that service users prefer can reduce the chance that deteriorating QoL is going unchecked, and increase the chance that decisions based on survey findings are meaningful to service users.

Association of Insurance Status With Treatment and Outcomes in Pediatric Patients With Severe Traumatic Brain Injury.

OBJECTIVE: To determine whether a health insurance disparity exists among pediatric patients with severe traumatic brain injury using the National Trauma Data Bank. DESIGN: Retrospective cohort study. SETTING: National Trauma Data Bank, a dataset containing more than 800 trauma centers in the United States. PATIENTS: Pediatric patients (< 18 yr old) with a severe isolated traumatic brain injury were identified in the National Trauma Database (years 2007-2016). Isolated traumatic brain injury was defined as patients with a head Abbreviated Injury Scale score of 3+ and excluded those with another regional Abbreviated Injury Scale of 3+. INTERVENTIONS: None. MEASUREMENT AND MAIN RESULTS: Procedure codes were used to identify four primary treatment approaches combined into two classifications: craniotomy/craniectomy and external ventricular draining/intracranial pressure monitoring. Diagnostic criteria and procedure codes were used to identify condition at admission, including hypotension, Glasgow Coma Scale, mechanism and intent of injury, and Injury Severity Score. Children were propensity score matched using condition at admission and other characteristics to estimate multivariable logistic regression models to assess the associations among insurance status, treatment, and outcomes. Among the 12,449 identified patients, 91.0% (n = 11,326) had insurance and 9.0% (n = 1,123) were uninsured. Uninsured patients had worse condition at admission with higher rates of hypotension and higher Injury Severity Score, when compared with publicly and privately insured patients. After propensity score matching, having insurance was associated with a 32% (p = 0.001) and 54% (p < 0.001) increase in the odds of cranial procedures and monitor placement, respectively. Insurance coverage was associated with 25% lower odds of inpatient mortality (p < 0.001). CONCLUSIONS: Compared with insured pediatric patients with a traumatic brain injury, uninsured patients were in worse condition at admission and received fewer interventional procedures with a greater odds of inpatient mortality. Equalizing outcomes for uninsured children following traumatic brain injury requires a greater understanding of the factors that lead to worse condition at admission and policies to address treatment disparities if causality can be identified.

County-level Variation in Low Birthweight and Preterm Birth: An Evaluation of State Medicaid Expansion Under the Affordable Care Act.

BACKGROUND: Rates of low birthweight and prematurity vary 2-fold across states in the United States, with increased rates among states with higher concentrations of racial minorities. Medicaid expansion may serve as a mechanism to reduce geographic variation within states that expanded, by improving health and access to care for vulnerable populations. OBJECTIVE: The objective of this study was to identify the association of Medicaid expansion with changes in county-level geographic variation in rates of low birthweight and preterm births, overall and stratified by race/ethnicity. RESEARCH DESIGN: We compared changes in the coefficient of variation and the ratio of the 80th-to-20th percentiles using bootstrap samples (n=1000) of counties drawn separately for all births and for white, black, and Hispanic births, separately. MEASURES: County-level rates of low birthweight and preterm birth. RESULTS: Before Medicaid expansion, counties in expansion states were concentrated among quintiles with lower rates of adverse birth outcomes and counties in nonexpansion states were concentrated among quintiles with higher rates. In expansion states, county-level variation, measured by the coefficient of variation, declined for both outcomes among all racial/ethnic categories. In nonexpansion states, geographic variation reduced for both outcomes among Hispanic births and for low birthweight among white births, but increased for both outcomes among black births. CONCLUSIONS: The decrease in county-level variation in adverse birth outcomes among expansion states suggests improved equity in these states. Further reduction in geographic variation will depend largely on policies or interventions that reduce racial disparities in states that did and did not expand Medicaid.

Correction to: Do Insurance Mandates Affect Racial Disparities in Outcomes for Children with Autism?

The original version of this article unfortunately contained a mistake in the analysis of the Tables 4 and 5.

Association of State Medicaid Expansion Status With Low Birth Weight and Preterm Birth.

Importance: Low birth weight and preterm birth are associated with adverse consequences including increased risk of infant mortality and chronic health conditions. Black infants are more likely than white infants to be born prematurely, which has been associated with disparities in infant mortality and other chronic conditions. Objective: To evaluate whether Medicaid expansion was associated with changes in rates of low birth weight and preterm birth outcomes, both overall and by race/ethnicity. Design, Setting, and Participants: Using US population-based data from the National Center for Health Statistics Birth Data Files (2011-2016), difference-in-differences (DID) and difference-in-difference-in-differences (DDD) models were estimated using multivariable linear probability regressions to compare birth outcomes among infants in Medicaid expansion states relative to non-Medicaid expansion states and changes in relative disparities among racial/ethnic minorities for singleton live births to women aged 19 years and older. Exposures: State Medicaid expansion status and racial/ethnic category. Main Outcomes and Measures: Preterm birth (<37 weeks' gestation), very preterm birth (<32 weeks' gestation), low birth weight (<2500 g), and very low birth weight (<1500 g). Results: The final sample of 15 631 174 births (white infants: 8 244 924, black infants: 2 201 658, and Hispanic infants: 3 944 665) came from the District of Columbia and 18 states that expanded Medicaid (n = 8 530 751) and 17 states that did not (n = 7 100 423). In the DID analyses, there were no significant changes in preterm birth in expansion relative to nonexpansion states (preexpansion to postexpansion period, 6.80% to 6.67% [difference: -0.12] vs 7.86% to 7.78% [difference: -0.08]; adjusted DID: 0.00 percentage points [95% CI, -0.14 to 0.15], P = .98), very preterm birth (0.87% to 0.83% [difference: -0.04] vs 1.02% to 1.03% [difference: 0.01]; adjusted DID: -0.02 percentage points [95% CI, -0.05 to 0.02], P = .37), low birth weight (5.41% to 5.36% [difference: -0.05] vs 6.06% to 6.18% [difference: 0.11]; adjusted DID: -0.08 percentage points [95% CI, -0.20 to 0.04], P = .20), or very low birth weight (0.76% to 0.72% [difference: -0.03] vs 0.88% to 0.90% [difference: 0.02]; adjusted DID: -0.03 percentage points [95% CI, -0.06 to 0.01], P = .14). Disparities for black infants relative to white infants in Medicaid expansion states compared with nonexpansion states declined for all 4 outcomes, indicated by a negative DDD coefficient for preterm birth (-0.43 percentage points [95% CI, -0.84 to -0.02], P = .05), very preterm birth (-0.14 percentage points [95% CI, -0.26 to -0.02], P = .03), low birth weight (-0.53 percentage points [95% CI, -0.96 to -0.10], P = .02), and very low birth weight (-0.13 percentage points [95% CI, -0.25 to -0.01], P = .04). There were no changes in relative disparities for Hispanic infants. Conclusions and Relevance: Based on data from 2011-2016, state Medicaid expansion was not significantly associated with differences in rates of low birth weight or preterm birth outcomes overall, although there were significant improvements in relative disparities for black infants compared with white infants in states that expanded Medicaid vs those that did not.

Financial Performance of Hospitals in the Mississippi Delta Region Under the Hospital Readmissions Reduction Program and Hospital Value-based Purchasing Program.

BACKGROUND: Previous studies showed that the Hospital Readmissions Reduction Program (HRRP) and the Hospital Value-based Purchasing Program (HVBP) disproportionately penalized hospitals caring for the poor. The Mississippi Delta Region (Delta Region) is among the most socioeconomically disadvantaged areas in the United States. The financial performance of hospitals in the Delta Region under both HRRP and HVBP remains unclear. OBJECTIVE: To compare the differences in financial performance under both HRRP and HVBP between hospitals in the Delta Region (Delta hospitals) and others in the nation (non-Delta hospitals). RESEARCH DESIGN: We used a 7-year panel dataset and applied difference-in-difference models to examine operating and total margin between Delta and non-Delta hospitals in 3 time periods: preperiod (2008-2010); postperiod 1 (2011-2012); and postperiod 2 (2013-2014). RESULTS: The Delta hospitals had a 0.89% and 4.24% reduction in operating margin in postperiods 1 and 2, respectively, whereas the non-Delta hospitals had 1.13% and 1% increases in operating margin in postperiods 1 and 2, respectively. The disparity in total margins also widened as Delta hospitals had a 1.98% increase in postperiod 1, but a 0.30% reduction in postperiod 2, whereas non-Delta hospitals had 1.27% and 2.28% increases in postperiods 1 and 2, respectively. CONCLUSIONS: The gap in financial performance between Delta and non-Delta hospitals widened following the implementation of HRRP and HVBP. Policy makers should modify these 2 programs to ensure that resources are not moved from the communities that need them most.

Do Insurance Mandates Affect Racial Disparities in Outcomes for Children with Autism?

Objective The study investigated whether state mandates for private insurers to provide services for children with autism influence racial disparities in outcomes. Methods The study used 2005/2006 and 2009/2010 waves of the National Survey of Children with Special Health Care Needs. Children with a current diagnosis of autism were included in the sample. Children residing in 14 states and the District of Columbia that were not covered by the mandate in the 2005/2006 survey, but were covered in the 2009/2010 survey, served as the mandate group. Children residing in 32 states that were not covered by a mandate in either wave served as the comparison group. Outcome measures assessed included care quality, family economics, and child health. A difference-in-difference-in-differences (DDD) approach was used to assess the impact of the mandates on racial disparities in outcomes. Results Non-white children had less access to family-centered care compared to white children in both waves of data, but this difference was not apparent across mandate and comparison states as only the comparison states had significant differences. Parents of non-white children reported paying less in annual out-of-pocket expenses compared to parents of white children across waves and groups. DDD estimates did not provide evidence that the mandates had statistically significant effects on improving or worsening racial disparities for any outcome measure. Conclusions This study did not find evidence that state mandates on private insurers affected racial disparities in outcomes for children with autism.

Impact of Economic Constraints on Public Health Delivery Systems Structures.

OBJECTIVES: We estimated the effect of economic constraints on public health delivery systems (PHDS) density and centrality during 3 time periods, 1998, 2006, and 2012. METHODS: We obtained data from the 1998, 2006, and 2012 National Longitudinal Study of Public Health Agencies; the 1993, 1997, 2005, and 2010 National Association for County and City Health Officials Profile Study; and the 1997, 2008, and 2011 Area Resource Files. We used multivariate regression models for panel data to estimate the impact of economic constraints on PHDS density and centrality. RESULTS: Findings indicate that economic constraints did not have a significant impact on PHDS density and centrality over time but population is a significant predictor of PHDS density, and the presence of a board of health (BOH) is a significant predictor of PHDS density and centrality. Specifically, a 1% increase in population results in a significant 1.71% increase in PHDS density. The presence of a BOH is associated with a 10.2% increase in PHDS centrality, after controlling for other factors. CONCLUSIONS: These findings suggest that other noneconomic factors influence PHDS density centrality.

Association of copayments with healthcare utilization and expenditures among Medicaid enrollees with a substance use disorder.

BACKGROUND: The purpose of this study was to examine the association between copayments and healthcare utilization and expenditures among Medicaid enrollees with substance use disorders. METHODS: This study used claims data (2020-2021) from a private insurer participating in Arkansas's Medicaid expansion. We compared service utilization and expenditures for enrollees in different Medicaid program structures with varying copayments. Enrollees with incomes above 100 % FPL (N = 10,240) had copayments for substance use treatment services while enrollees below 100 % FPL (N = 2478) did not. Demographic, diagnostic, utilization, and cost information came from claims and enrollment information. The study identified substance use and clinical comorbidities using claims from July through December 2020 and evaluated utilization and costs in 2021. Generalized linear models (GLM) estimated outcomes using single equation and two-part modeling. A gamma distribution and log link were used to model expenditures, and negative binomial models were used to model utilization. A falsification test comparing behavioral health telemedicine utilization, which had no cost sharing in either group, assessed whether differences in the groups may be responsible for observed findings. RESULTS: Substance use enrollees with copayments were less likely to have a substance use or behavioral health outpatient (-0.04 PP adjusted; p = 0.001) or inpatient visit (-0.04 PP; p = 0.001) relative to their counterparts without copayments, equal to a 17 % reduction in substance use or behavioral health outpatient services and a nearly 50 % reduction in inpatient visits. The reduced utilization among enrollees with a copayment was associated with a significant reduction in total expenses ($954; p = 0.001) and expenses related to substance use or behavioral health services ($532; p = 0.001). For enrollees with at least one behavioral health visit, there were no differences in outpatient or inpatient utilization or expenditures between enrollees with and without copayments. Copayments had no association with non-behavioral health or telemedicine services where neither group had cost sharing. CONCLUSION: Copayments serve as an initial barrier to substance use treatment, but are not associated with the amount of healthcare utilization conditional on using services. Policy makers and insurers should consider the role of copayments for treatment services among enrollees with substance use disorders in Medicaid programs.

Rates Of Preterm Birth And Low Birthweight: An Analysis Of Racial And Ethnic Populations.

Using National Center for Health Statistics data (2016-20), we evaluated variation in low birthweight and prematurity among racial and ethnic subcategories. Disparities as large as 2.3-fold among rates of low birthweight for "multiple race" subcategories underscore the need for granular data stratification and analysis by racial and ethnic subcategories to address the root causes of inequities in infant outcomes.

Economic Report of General Inpatient Hospice in an Academic Medical Center.

This study examined if there was difference in cost of care after implementation of scattered bed inpatient hospice, first implemented in October 2021 in an Academic Medical Center in Arkansas. This retrospective, cross-sectional study compared the cost of care during the pre-implementation phase (n = 121, July 2020-March 2021) to patients admitted to hospice care (n = 84, October 2021-June 2022). Hospice length of stay (LOS) was 4 times longer than the LOS after a Do Not Resuscitate order (DNR) was placed for patients in the pre-implementation period. The end of life costs after the implementation of inpatient hospice was 69% less than the end of life costs in the pre-implementation period.

Asthma Quality Measurement and Adverse Outcomes in Medicaid-Enrolled Children.

OBJECTIVES: To determine the association between the asthma medication ratio (AMR) quality measure and adverse outcomes among Medicaid-enrolled children with asthma in Arkansas, given concerns regarding the utility of the AMR in evaluating pediatric risk of asthma-related adverse events (AAEs). METHODS: We used the Arkansas All-Payer Claims Database to identify Medicaid-enrolled children with asthma using a nonrestrictive case definition and additionally using the standard Healthcare Effectiveness Data and Information Set (HEDIS) persistent asthma definition. We assessed the AMR using the traditional dichotomous HEDIS AMR categorization and across 4 expanded AMR categories. Regression models assessed associations between AMR and AAE including hospitalization and emergency department utilization, with models conducted overall and by race and ethnicity. RESULTS: Of the 22 788 children in the analysis, 9.0% had an AAE (6.7% asthma-related emergency department visits; 3.0% asthma-related hospitalizations). We found poor correlation between AMR and AAE, with higher rates of AAE (10.5%) among children with AMR ≥0.5 compared with AMR <0.5 (8.5%; P < .001), and similar patterns stratified by racial and ethnic subgroups. Expanded AMR categorization revealed notable differences in associations between AMR and AAEs, compared with traditional dichotomous categorization, with worse performance in Black children. CONCLUSIONS: The AMR performed poorly in identifying risk of adverse outcomes among Medicaid-enrolled children with asthma. These findings underscore concerns of the utility of the AMR in population health management and reliance on restrictive HEDIS definitions. New population health frameworks incorporating broader considerations that accurately identify at-risk children are needed to improve equity in asthma management and outcomes.

Variation in Time Between Testing Positive for COVID-19 and Hospital Admission by Race/Ethnicity and Insurance Status.

Understanding the extent to which demographic and socioeconomic factors play a role in the disparities associated with duration between testing positive for COVID-19 and hospital admission will help in achieving equitable health outcomes. This project linked the statewide COVID-19 registry to administrative datasets to examine the variation in times between testing positive for COVID-19 and hospital admission by race/ethnicity and insurance. In 2020, there were 11,314 patients admitted for COVID-19 in Arkansas. Approximately 42.2% tested positive for COVID-19 on the same day as hospital admission. Black patients had 38% higher odds of hospitalization on the day of testing compared with White patients (p<.001). Medicaid and uninsured patients had 51% and 50% higher odds of admission on the day of testing compared with privately insured patients (both p<.001), respectively. This study highlights the implications of reduced access to testing with respect to equitable health outcomes.

Using artificial intelligence to optimize delivery of weight loss treatment: Protocol for an efficacy and cost-effectiveness trial.

Gold standard behavioral weight loss (BWL) is limited by the availability of expert clinicians and high cost of delivery. The artificial intelligence (AI) technique of reinforcement learning (RL) is an optimization solution that tracks outcomes associated with specific actions and, over time, learns which actions yield a desired outcome. RL is increasingly utilized to optimize medical treatments (e.g., chemotherapy dosages), and has very recently started to be utilized by behavioral treatments. For example, we previously demonstrated that RL successfully optimized BWL by dynamically choosing between treatments of varying cost/intensity each week for each participant based on automatic monitoring of digital data (e.g., weight change). In that preliminary work, participants randomized to the AI condition required one-third the amount of coaching contact as those randomized to the gold standard condition but had nearly identical weight losses. The current protocol extends our pilot work and will be the first full-scale randomized controlled trial of a RL system for weight control. The primary aim is to evaluate the hypothesis that a RL-based 12-month BWL program will produce non-inferior weight losses to standard BWL treatment, but at lower costs. Secondary aims include testing mechanistic targets (calorie intake, physical activity) and predictors (depression, binge eating). As such, adults with overweight/obesity (N = 336) will be randomized to either a gold standard condition (12 months of weekly BWL groups) or AI-optimized weekly interventions that represent a combination of expert-led group, expert-led call, paraprofessional-led call, and automated message). Participants will be assessed at 0, 1, 6 and 12 months.