"It's my Home away from Home:" A hermeneutic phenomenological study exploring decision-making experiences of choosing a freestanding birth centre for perinatal care.

PROBLEM: The high-value, midwifery-led birth centre (BC) model of care is underutilized in the United States, a country with high rates of obstetric intervention and maternal morbidity and mortality. BACKGROUND: Birth setting decision-making is a complex, preference-sensitive, and resource-dependent process. Understanding how people choose BCs for care may help increase the utilization of BCs and generate positive perinatal outcomes. AIM: This study explores the decision-making experiences of people with Medicaid insurance who chose to give birth in a BC in Massachusetts by gathering interview data to interpret and provide meaning about their selection of birth setting. METHODS: We employed a hermeneutic phenomenology study to interview people about their decision to give birth in a BC. Interview data were coded using a hybrid deductive-inductive approach and analyzed using reflexive thematic analysis to interpret and provide meaning. FINDINGS: Twelve women participated in the study. Five themes emerged that described participants' decision-making processes: 1) Stepping Away from "the System," 2) Decision-Making with External Influences, 3) Accessing BC Care, 4) Finding a Home at the BC, and 5) Decision-Making as a Temporal Process. DISCUSSION: The decision to choose a BC was a dynamic process that occurred over time and was influenced by factors such as the quality of care, accessibility, external influences, and the physical environment. CONCLUSION: Prioritizing an individual's capacity to choose their birth setting and fostering awareness about options in the context of informed decision-making are pivotal steps toward attaining equity in perinatal health. Securing public insurance coverage and equitable reimbursement for BCs represent essential policies aimed at facilitating universal access to the BC model for all people.

What Is "Advanced" Parkinson's Disease? Defining What Determines Medicare Coverage for Deep Brain Stimulation in the USA.

BACKGROUND: The National Coverage Determination (NCD) by the Centers for Medicare and Medicaid Services (CMS) for deep brain stimulation requires that a patient have "advanced idiopathic Parkinson's disease (PD) as determined by Hoehn and Yahr (HY) stage or the Unified Parkinson's Disease Rating Scale part III motor subscale (UPDRS III)." How to apply the HY or UPDRS III scales to define "advanced" PD is unclear. SUMMARY: There is an ongoing recovery audit by the CMS of deep brain stimulation cases that were covered by Medicare but are deemed not to have met the NCD requirements and therefore not to have been medically necessary. Whether a hospital is asked to refund Medicare often hinges upon whether medical documentation supports the diagnosis of advanced PD. However, neither the HY nor the UPDRS III scales use "advanced" to define or describe stages of PD. The NCD has an accompanying National Coverage Analysis that reviews the studies that inform the NCD. These studies use "advanced" as well as the HY and UPDRS III scales. This review identifies how the HY and UPDRS III scales were used to categorize advanced PD in the studies that were cited in the National Coverage Analysis. KEY MESSAGES: In the studies used for the NCD for deep brain stimulation for PD, an HY score ≥3 or a UPDRS III score ≥30 was used to describe patient cohorts considered to have advanced PD.

Detailing Healthcare Claims Data Evidence of Extrapyramidal Symptoms in Medicaid Patients with Schizophrenia after Second-Generation Antipsychotic Medication Initiation.

Researchers have used elements of administrative healthcare claims data (e.g., diagnosis codes and medications) to calculate rates of extrapyramidal symptoms (EPS) in patients with schizophrenia who utilize second-generation antipsychotics (SGAs). However, a detailed description of claims-based EPS evidence has not been previously provided, which is the objective of the current study. This descriptive study, using 2016-2020 de-identified multi-state Medicaid administrative claims data, followed patients diagnosed with schizophrenia for 12 months after initiation of SGA therapy to identify and describe the first evidence of EPS. Time to EPS evidence was calculated and continuously-eligible patients were followed for an additional 12 months to examine EPS medication utilization and costs. Following SGA initiation, 13.6% (n = 2,288) of patients had evidence of EPS during the 12-month follow-up period. Mean time to first evidence of EPS after SGA initiation was 103.7 days (sd = 112.2, median = 58). For a majority of patients (n = 1,636, 71.5%), an EPS medication claim was the initial evidence of EPS, rather than an EPS diagnostic claim. Additionally, a quarter of patients (25.3%) in the EPS evidence cohort had a claim for an EPS medication on the same date as SGA initiation, possibly indicating prophylactic prescribing to prevent EPS development. Nearly 93% of those with EPS medication claims were treated with benztropine, while less than 2% received deutetrabenazine or valbenazine (indicated for tardive dyskinesia (TD)). Annual per patient EPS medication expenditures were $804 (sd = 7,080) overall, but only $40 (sd = 104) when excluding the higher-cost TD medications. Nearly 14% of Medicaid patients with schizophrenia who initiated SGA treatment had evidence of EPS based on claims data. The majority of the time, this evidence was derived from a prescription claim for a medication to treat EPS, rather than an EPS diagnostic claim. Prophylactic prescribing for EPS occurred more often than expected and should be explored more fully. While the cost of traditional EPS medications minimally contributes to the overall cost of care in schizophrenia, use of newer TD drugs can substantially increase spending.

Age and racial and ethnic disparities in filled buprenorphine prescriptions post-emergency department visit in Nevada.

Objectives: We described age, gender, race, and ethnicity associations with filling buprenorphine prescriptions post-emergency department (post-ED) visits. Methods: We analyzed 1.5 years (July 1, 2020-December 31, 2021) of encounter-level Medicaid ED and retail pharmacy claims data obtained from the Nevada Department of Health and Human Services. We studied ED patients with an opioid use disorder (OUD) diagnosis who did not fill a prescription for OUD medications within 6 months before the ED encounter. Using logistic regression, we modeled the associations between the patient's demographic characteristics and the outcome, filling a buprenorphine prescription at a community pharmacy within 14 or 30 days of the ED encounter. Results: Among 2781 ED visits, representing 2094 patients, the median age was 39 years, 54% were male, 18.5% were Black, 11.7% were Hispanic, and 62.3% were White. Only 4% of the ED visits were followed by a filled buprenorphine prescription. Increasing age (14-day window: adjusted odds ratio (aOR) = 0.965, 95% confidence interval [CI]: 0.948-0.983) and being a Black patient (14-day window: aOR: 0.114, 95% CI 0.036-0.361) were both associated with lower odds of filled buprenorphine prescriptions. These results were similar within 30 days of an ED visit. Conclusions: Initiation of buprenorphine following an ED visit remains low among Nevadan Medicaid patients and is less likely with increasing age and among Black patients, despite strong evidence supporting its use. Overburdened EDs, lack of attention from managers, and substance use stigma are among possible explanations. When ED clinicians do write buprenorphine prescriptions, peer recovery support could increase the fill rates.

Medicaid compared to private insurance is associated with lower rates of sterilization in people with unwanted births.

BACKGROUND: Medicaid, unlike any other insurance mechanism, imposes a consent requirement on female patients desiring sterilization that must be completed at least 30 days, but no more than 180 days, before sterilization. Desired sterilization cannot be completed in the Medicaid population without this consent. Large-scale national evidence is lacking on the effect of this requirement. OBJECTIVE: This study aimed to explore the influence of insurance status on the achievement of postpartum sterilization after a self-reported unwanted birth in a nationally representative sample. STUDY DESIGN: This was a retrospective cohort analysis using data from the 2013-2015 National Survey of Family Growth. The National Survey of Family Growth uses a stratified, multistage clustered sample to make nationally representative estimates for men and women aged 15 to 44 years in the household population of the United States. The analysis was limited to a cohort of birthing people who reported their last birth as unwanted and who were insured by either Medicaid or private insurance. The survey was analyzed with the application of inverse probability of treatment weights to balance those with Medicaid and those with private insurance in addition to the survey weight. The association between completion of postpartum sterilization and insurance type was evaluated using weighted logistic regression, adjusting for demographic and clinical characteristics. RESULTS: In an adjusted and inverse probability of treatment weight balanced analysis of a weighted national sample representing 4,164,304 people (416 respondents), Medicaid-insured birthing people with history of unwanted births were found to have 56% lower odds of obtaining postpartum sterilization (odds ratio, 0.44; 95% confidence interval, 0.22-0.87; P=.019) than those with private insurance. CONCLUSION: This study adds to mounting evidence that insurance type plays a significant role in the achievement of desired postpartum sterilization, with individuals with Medicaid less likely to undergo the procedure. The findings call for policy reforms around sterilization policy in the United States, emphasizing the need for uniform consent procedures that do not discriminate based on insurance status.

Child Mental Health, Homelessness, and the Shelter System: Evidence from Medicaid in New York City.

We identified children who resided in the New York City shelter system during 2015-2020 by matching address histories in Medicaid insurance claims to publicly available homeless shelter addresses, permitting examination of health care use before, during, and after shelter stays. We found that 4.5% of NYC children aged 4-17 with consistent Medicaid coverage entered shelter over a three-to-five-year period. After shelter entry, children had increased probabilities of receiving mental health services, including therapy and diagnoses of neurodevelopmental disorders, but little change in physical health service use. Children placed in shelters co-located with mental health services were similar to children entering other shelters prior to entry but had particularly large and sustained increases in use of mental health services afterwards. Children without prior mental health claims placed in shelters co-located with mental health services were 38-48% more likely to receive mental health therapy and 14-16% more likely to receive neurodevelopmental diagnoses than similar children placed elsewhere. These children were also more likely to receive Supplemental Security Income and stayed in shelter longer. This example illustrates the potential of linking administrative data sets in order to study vulnerable populations.

Integrating firearm storage and safety devices into health care.

Millions of US children and adolescents live in homes with loaded firearms, with only half of these homes securing their guns. Firearm-related deaths among youth have doubled over the past decade, making firearms the leading cause of death for children and adolescents in the United States. The recent advisory by the US Surgeon General, identifying firearm violence as a public health crisis, underscores the urgent need for responsible firearm ownership, including safe firearm storage. However, the healthcare community currently lacks durable medical equipment (DME) codes for firearm storage devices, limiting the ability of healthcare providers to support responsible gun ownership. We propose the establishment of DME codes for firearm storage and safety devices, which would facilitate insurance coverage of these vital prevention measures. Durable medical equipment codes would empower physicians and other healthcare providers to integrate anticipatory guidance and lethal means counseling of firearm safety into routine care and support hospital- and community-based efforts to prevent firearm-related injuries and deaths among children and adolescents.

A multi-state analysis on the effect of deprivation and race on PICU admission and mortality in children receiving Medicaid in United States (2007-2014).

INTRODUCTION: In the United States (US), racial and socioeconomic disparities have been implicated in pediatric intensive care unit (PICU) admissions and outcomes, with higher rates of critical illness in more deprived areas. The degree to which this persists despite insurance coverage is unknown. We investigated whether disparities exist in PICU admission and mortality according to socioeconomic position and race in children receiving Medicaid. METHODS: Using Medicaid data from 2007-2014 from 23 US states, we tested the association between area level deprivation and race on PICU admission (among hospitalized children) and mortality (among PICU admissions). Race was categorized as Black, White, other and missing. Patient-level ZIP Code was used to generate a multicomponent variable describing area-level social vulnerability index (SVI). Race and SVI were simultaneously tested for associations with PICU admission and mortality. RESULTS: The cohort contained 8,914,347 children (23·0% Black). There was no clear trend in odds of PICU admission by SVI; however, children residing in the most vulnerable quartile had increased PICU mortality (aOR 1·12 (95%CI 1·04-1·20; p = 0·0021). Black children had higher odds of PICU admission (aOR 1·04; 95% CI 1·03-1·05; p < 0·0001) and higher mortality (aOR 1·09; 95% CI 1·02-1·16; p = 0·0109) relative to White children. Substantial state-level variation was apparent, with the odds of mortality in Black children varying from 0·62 to 1·8. CONCLUSION: In a Medicaid cohort from 2007-2014, children with greater socioeconomic vulnerability had increased odds of PICU mortality. Black children were at increased risk of PICU admission and mortality, with substantial state-level variation. Our work highlights the persistence of sociodemographic disparities in outcomes even among insured children.

A census tract-level assessment of social determinants of health, traffic exposure, and asthma exacerbations in New York State's Medicaid Population (2005-2015).

This study aims to evaluate the association between social determinants, environmental exposure metrics, and the risk of asthma emergency department (ED) visits in the New York State (NYS) Medicaid population using small-area analysis. Traffic densities for each census tract in NYS were calculated using the length of road segments within each tract and total area of the tract to produce a measure of average number of vehicles per square meter per day. Data on social determinants of health including internal and external environments and other demographic factors were obtained from various sources. Poisson regression analyses were conducted to identify significant factors associated with asthma ED visits in Medicaid claim and encounter data for years 2005-2015. High traffic density in NYS excluding New York City (NYC) correlated with increased risk of asthma ED visits (RR 1.69; 95% CI: 1.42, 2.00), mitigated by adjusting for environmental and social determinants (RR 1.00; 95% CI: 0.85, 1.19). Similar trends were observed in NYC only (RR 1.19; 95% CI: 1.00, 1.41), with the adjusted risk remaining elevated (RR 1.14; 95% CI: 0.98, 1.33) albeit not statistically significant. Living in census tracts with high concentrated disadvantage index, high proportions of minorities, and less green space predicted higher asthma ED visits. We mapped predicted rates and model residuals to identify areas of high risk. Our results support previous findings that environmental and social risk factors in poor and urban areas contribute to asthma exacerbations in the NYS Medicaid population, even if they may not necessarily contribute to its development.

Access to Dermatological Appointments Based on Insurance Types in Hawai'i.

Although there is evidence that Medicaid beneficiaries in the continental United States experience barriers to accessing dermatological care, limited data exists on whether these same barriers exist in Hawai'i. Using a secret shopper study design, a total of 46 dermatology offices were contacted, 41 (89%) of which were accepting new patients. Thirty (73%) offices were located on O'ahu, and the remaining 11 (27%) were distributed among the neighboring islands (Hawai'i Island, Kaua'i, Maui). Overall, the acceptance rate for Medicaid (n=14) was 34%, which was significantly lower (P<.0001) than private insurance (n=39 (95%)) and Medicare (n=38 (93%)). The acceptance rate for patients with Medicaid insurance was lower for O'ahu offices (27%) than for neighboring islands' offices (55%), but the difference was not statistically significant (P=.095). Differences in average wait times were not statistically significant among insurance types or between O'ahu and neighboring islands. Overall, these results suggest that Medicaid recipients compared to those with private insurance or Medicare might experience difficulty in accessing dermatological care in Hawai'i.

Program Implementation Strategies Associated With Reduced Acute Care Utilization for Medicaid Beneficiaries in California's Whole Person Care Pilot Program.

Public health care policymakers and payers are increasingly investing in efforts to address patients' health-related social needs (HRSNs) as a strategy for improving health while controlling or reducing costs. However, evidence regarding the implementation and impact of HRSN interventions remains limited. California's Whole Person Care Pilot program (WPC) was a Medicaid Section 1115 waiver demonstration program focused on the provision of care coordination and other services to address eligible beneficiaries' HRSN. In this study, we examine pilot-level variation in impact on acute care utilization and identify factors associated with differential outcomes. The majority of pilots reduced emergency department (ED) visits for enrollees relative to matched controls; however, only four pilots reduced both ED visits and hospitalizations. Coincidence analysis results highlight the importance of cross-sector partnerships, field-based outreach and engagement, and adequate program investment in differentiating pilots that reduced acute care utilization from those that did not.

Trends in Medicaid Take-Up Among Eligible Adults After the Affordable Care Act Medicaid Expansions: 2014-2019.

Little is known about how take-up of Medicaid among eligible adults has changed since 2014. This study used data from the Medical Expenditure Panel Survey to examine changes in Medicaid enrollment among Medicaid-eligible adults between 2014 and 2019. Eligibility for Medicaid was simulated using state- and year-specific eligibility rules. Among all Medicaid-eligible citizen adults aged 19-64 years, the proportion enrolled in Medicaid increased from 55.5% in 2014-2015 to 61.9% in 2016-2017, and then remained approximately at the same level in 2018-2019 (61.5%). Among adults who became eligible because of the Medicaid expansions, the proportion enrolled in Medicaid increased from 44.1% in 2014-2015 to 53.8% in 2016-2017. Among pre-Affordable Care Act (ACA)-eligible adults, there was no statistically significant change in the proportion enrolled in Medicaid between 2014-2015 and 2016-2017 (66.8% and 69.7%, respectively). There were significant differences in changes in take-up rates across population subgroups.

Costly Barriers: A Student's Struggle With Medicaid Access.

A public health student enrolls in Medicaid, only to be unable to access the insurance for months.

Provider's Individual and Network Attributes in the Selection Process of a Predominant Antenatal Care Provider in South Carolina: A Case-Control Study.

INTRODUCTION: This study aims to examine the association between provider attributes, including network (patient panel size, degree-number of peer connections, and community size- number of a closely connected group of peers) and individual attributes (travel distance, specialties, and rural practice), and a predominant (most visited) provider. METHODS: This study utilized South Carolina's Medicaid claims data during 2014 to 2018, focusing on live births in hospitals. Samples were limited to pregnant women continuously enrolled in Medicaid throughout pregnancy. Predominant providers (total = 2153) were identified for 29 569 pregnancies. Network analyses involved 5520 providers, comprising 3667 antenatal care (ANC) providers and 1853 non-ANC providers. A Cartesian product (n = 45 929 845) combined five annual provider lists with all included pregnancies. Logistic regressions with repeated measures were applied to this retrospective case-control study. RESULTS: The results demonstrated that a medium or large degree were associated with being a predominant provider if the community size was medium or large. A predominant provider was more likely to be located near, rather than far from, the served woman, and in rural areas rather than urban ones. They were also more likely to be specialists, midwives, and nurse practitioners than primary care physicians. CONCLUSION: The results suggest that both individual and network attributes were significantly associated with being a predominant provider. Policies aimed at addressing access issues for antenatal care should consider both the individual and network attributes of providers, as providers may not be able to alter their individual attributes but can always optimize their social network.

Development and validation of claims-based algorithms for estimating gestational age of spontaneous abortion and termination.

To study the risk of spontaneous abortion (SAB) or termination using healthcare utilization databases, algorithms to estimate the gestational age (GA) are needed. Using Medicaid data, we developed a hierarchical algorithm to classify pregnancy outcomes. We identified the subset of potential SAB and termination cases, and abstracted the GA from linked electronic medical records (gold standard). We developed three approaches: (1) assign median GA for SAB and termination cases in the US; (2) draw a random GA from the population distributions; (3) estimate GA based on regression models. Algorithm performance was assessed based on the proportion of pregnancies with estimated GA within 1-4 weeks of the gold standard, the mean squared error (MSE) and the R-squared. Approach 1 and Approach 3 had similar performance, though approach 3 using random forest models with variables selected via the Boruta algorithm had better MSE and R-squared. For SAB, 58.0% of pregnancies were correctly classified within 2 weeks of the gold standard (MSE: 8.7, R-squared: 0.09). For termination, the proportions were 66.3% (MSE: 11.7; R-squared: 0.35). SABs and terminations can be studied in healthcare utilization data with careful implementation of validated algorithms though higher level of GA misclassification is expected compared to live births.

Impact of Medicaid expansion on kidney transplantation in the State Oklahoma.

BACKGROUND: There is no data evaluating the impact of Medicaid expansion on kidney transplants (KT) in Oklahoma. AIM: To investigate the impact of Medicaid expansion on KT patients in Oklahoma. METHODS: The UNOS database was utilized to evaluate data pertaining to adult KT recipients in Oklahoma in the pre-and post-Medicaid eras. Bivariate analysis, Kaplan Meier analysis was used to estimate, and cox proportional models were utilized. RESULTS: There were 2758 pre- and 141 recipients in the post-Medicaid expansion era. Post-expansion patients were more often non-United States citizens (2.3% vs 5.7%), American Indian, Alaskan, or Pacific Islander (7.8% vs 9.2%), Hispanic (7.4% vs 12.8%), or Asian (2.5% vs 8.5%) (P < 0.0001). Waitlist time was shorter in the post-expansion era (410 vs 253 d) (P = 0.0011). Living donor rates, pre-emptive transplants, re-do transplants, delayed graft function rates, kidney donor profile index values, panel reactive antibodies levels, and insurance types were similar. Patients with public insurance were more frail. Despite increased early (< 6 months) rejection rates, 1-year patient and graft survival were similar. In Cox proportional hazards model, male sex, American Indian, Alaskan or Pacific Islander race, public insurance, and frailty category were independent risk factors for death at 1 year. Medicaid expansion was not associated with graft failure or patient survival (adjusted hazard ratio: 1.07; 95%CI: 0.26-4.41). CONCLUSION: Medicaid expansion in Oklahoma is associated with increased KT access for non-White/non-Black and non-United States citizen patients with shorter wait times. 1-year graft and patient survival rates were similar before and after expansion. Medicaid expansion itself was not independently associated with graft or patient survival outcomes. Ongoing research is necessary to determine the long-term effects of Medicaid expansion.

A Few Doctors Will See Some of You: The Critical Role of Underrepresented in Medicine (URiM) Family Physicians in the Care of Medicaid Beneficiaries.

PURPOSE: Despite being key to better health outcomes for patients from racial and ethnic minority groups, the proportion of underrepresented in medicine (URiM) physicians remains low in the US health care system. This study linked a nationally representative sample of family physicians (FPs) with Medicaid claims data to explore the relative contributions to care of Medicaid populations by FP race and ethnicity. METHODS: This descriptive cross-sectional study used 2016 Medicaid claims data from the Transformed Medicaid Statistical Information System and from 2016-2017 American Board of Family Medicine certification questionnaire responses to examine the diversity and Medicaid participation of FPs. We explored the diversity of FP Medicaid patient panels and whether they saw ≥150 beneficiaries in 2016. Using logistic regression models, we controlled for FP demographics, practice characteristics, and characteristics of the communities in which they practiced. RESULTS: Of 13,096 FPs, Latine, Hispanic, or of Spanish Origin (LHS) FPs and non-LHS Black FPs saw more Medicaid beneficiaries compared with non-LHS White and non-LHS Asian FPs. The patient panels of URiM FPs had a much greater proportion of Medicaid beneficiaries from racial and ethnic minority groups. Overall, non-LHS Black and LHS FPs had greater odds of seeing ≥150 Medicaid beneficiaries in 2016. CONCLUSIONS: These findings clearly show the critical role URiM FPs play in caring for Medicaid beneficiaries, suggesting physician race and ethnicity are correlated with Medicaid participation. Diversity in the health care workforce is essential for addressing racial health inequities. Policies need to address problems in pathways to medical education, including failures to recruit, nurture, and retain URiM students.

Perceptions of Government-Assisted Payors: A Survey and Analysis of American Shoulder and Elbow Surgeons Current Medicare, Medicare Advantage and Medicaid Practice Allocation.

INTRODUCTION: Significant discrepancy and variance exist in the United States health care system with regards to patient access to medical care based on a patient's insurance type, whether that be government-assisted or a private insurer. There are currently three major government-assisted insurance programs: Medicare, Medicare Advantage, and Medicaid, each of which have their own patient mix and regulatory processes that govern care delivery. The purpose of this study was to evaluate the current perceptions of shoulder and elbow surgeons surrounding practice patterns and barriers to access for patients whose primary insurance is a government-assisted payor. METHODS: This was a national, observational study that surveyed the American Shoulder and Elbow Surgeons (ASES) society membership. This 15-question survey assessed surgeon demographics, practice types, reimbursement models, as well as rates and trends of their access to patients with government-assisted insurance. Subgroup analysis between practice type and barriers to access for patients with one of these three government-assisted insurance were also analyzed and compared. Pearson's Chi-squared test or Fisher's exact test was used to test association between categorical responses and categorical/binary respondent characteristics. A P value < .05 was deemed statistically significant. RESULTS: A total of 257 ASES members completed the survey. Mean years in practice for respondents was 14. For Medicare patients, the most common perceived barriers were reimbursement (49%) followed by administrative burden (33%) and then implant reimbursement at the surgeon's primary surgical facility (32%). For Medicare Advantage patients the most common barrier to access was administrative burden (52%), reimbursement (50%), and the patient's ability to access peri-operative services such as physical therapy, home health etc. (40%). The most common barriers for Medicaid patients were relatively evenly distributed between reimbursement (62%), low patient engagement in their care (61%), and patient's ability to access peri-operative services (60%). CONCLUSION: Amongst members of the ASES, barriers to patient access varied by government-assisted payor. For Medicare advantage, administrative burden was largest barrier to access. Whereas for Medicare and Medicaid, reimbursement was the most significant barrier. Further investigation and understanding of these barriers to patient access are necessary to improve availability of shoulder and elbow subspecialized care to a broader population of patients insured by government-assisted payors.

Development and Validation of an Algorithm to Predict Stillbirth Gestational Age in Medicaid Billing Records.

INTRODUCTION: With Medicaid covering half of US pregnancies, Medicaid Analytic eXtract (MAX) provides a valuable data source to enrich understanding about stillbirth etiologies. OBJECTIVE: We developed and validated a claims-based algorithm to predict GA at stillbirth. METHOD: We linked the stillbirths identified in MAX 1999-2013 to Florida Fetal Death Records (FDRs) to obtain clinical estimates of GA (N=825). We tested several algorithms including using a fixed median GA, median GA at the time of specific prenatal screening tests, and expanded versions considering additional predictors of stillbirth within including linear regression and random forest models. We estimated the proportion of pregnancies with differences of ± 1, 2, 3 and 4 weeks between the predicted and FDR GA and the model mean square error (MSE). We validated the selected algorithms in two external samples. RESULTS: The best performing algorithm was a random forest model (MSE of 12.67 weeks2) with 84% of GAs within ± 4 weeks. Assigning a fixed GA of 28 weeks resulted in an MSE of 60.21 weeks2 and proportions of GA within ± 4 weeks of 32%. We observed consistent results in the external samples. DISCUSSION: Our prediction algorithm for stillbirths can facilitate pregnancy research in the Medicaid population.