Health Services and Outcomes Research Methodology最新文献

{"title":"Gaming the System: Evaluating Spillover in a Video Game Intervention for Advance Care Planning using Physician Social Networks.","authors":"Carly A Bobak, Deepika Mohan, Megan A Murphy, Amber E Barnato, A James O'Malley","doi":"10.1007/s10742-025-00370-9","DOIUrl":"10.1007/s10742-025-00370-9","url":null,"abstract":"<p><p>Stepped-wedge cluster-randomized trials (SW-CRTs) are increasingly used to evaluate healthcare interventions, yet contamination arising from professional collaboration remains an underappreciated threat to valid inference. We examined spillover effects in a SW-CRT assessing a video-game intervention to increase Advance Care Planning (ACP) billing among hospitalists, which previously showed no direct intervention effect (OR = 0.96, 95% CI: 0.88-1.06, <i>p</i> = 0.42). Leveraging physician social networks constructed from shared-patient encounters, we quantified diffusion of intervention exposure through professional ties. In a network-adjusted intent-to-treat model excluding within-hospital connections, the intervention effect became positive though not statistically significant (OR = 1.08, 95% CI: 0.94-1.24, <i>p</i> = 0.26), while spillover from intervened peers showed a strong association with ACP billing (OR = 1.20, 95% CI: 1.13-1.27, <i>p</i> < 0.001). In an alternative as-treated formulation that included within-hospital ties and modeled exposure as the number of intervened physicians per patient, the intervention effect strengthened and achieved significance (OR = 1.11, 95% CI: 1.03-1.20, <i>p</i> = 0.006). A persistent positive interaction between intervention and spillover (OR = 1.01, 95% CI: 1.00-1.02, <i>p</i> = 0.03) indicated that the direct effect was amplified in more highly connected networks. Simulation results supported these findings, demonstrating that omitting spillover biases estimates toward the null, while network-adjusted models recover both direct and indirect effects with unbiased point estimators and coverage probabilities of interval estimators close to the nominal level. Together, these findings underscore the importance of incorporating social network structure into SW-CRT analyses to more accurately capture both the direct and diffusive pathways through which interventions influence behavior.</p>","PeriodicalId":45600,"journal":{"name":"Health Services and Outcomes Research Methodology","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2026-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13134650/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147821941","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A causal framework for evaluating drivers of policy effect heterogeneity using difference-in-differences.","authors":"Gary Hettinger, Youjin Lee, Nandita Mitra","doi":"10.1007/s10742-025-00358-5","DOIUrl":"10.1007/s10742-025-00358-5","url":null,"abstract":"<p><p>Policymakers and researchers often seek to understand how a policy differentially affects a population and the pathways driving this heterogeneity. For example, when studying an excise tax on sweetened beverages, researchers might assess the roles of cross-border shopping, economic competition, and store-level price changes on beverage sales trends. However, traditional policy evaluation tools, like the difference-in-differences (DiD) approach, primarily target average effects of the observed intervention rather than the underlying drivers of effect heterogeneity. Common approaches to evaluate sources of heterogeneity often lack a causal framework, making it difficult to determine whether observed outcome differences are truly driven by the proposed source of heterogeneity or by other confounding factors. In this paper, we present a framework for evaluating such policy drivers by representing questions of effect heterogeneity under hypothetical interventions and use it to evaluate drivers of the Philadelphia sweetened beverage tax policy effects. Building on recent advancements in estimating causal effect curves under DiD designs, we provide tools to assess policy effect heterogeneity while addressing practical challenges including confounding and neighborhood dynamics.</p><p><strong>Supplementary information: </strong>The online version contains supplementary material available at 10.1007/s10742-025-00358-5.</p>","PeriodicalId":45600,"journal":{"name":"Health Services and Outcomes Research Methodology","volume":"26 1","pages":"26-47"},"PeriodicalIF":2.2,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12967569/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147390161","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Estimating an intervention's effects on health care disparities within and between physician organizations: decomposing the effects of health system affiliation.","authors":"Maria DeYoreo, Denis Agniel, Shiyuan Zhang, José J Escarce, Justin W Timbie","doi":"10.1007/s10742-025-00350-z","DOIUrl":"10.1007/s10742-025-00350-z","url":null,"abstract":"<p><p>Vertically integrated health systems are expanding across the U.S., but there is no evidence that system-affiliated providers are better able to reduce socioeconomic disparities than unaffiliated providers. This paper develops and interprets statistical models for estimating the longitudinal effects of an exposure, health system affiliation, on within- and between-group disparities. Mixed effect difference-in-differences regression models were used to estimate the effect of physician organization (PO) health system affiliation on socioeconomic disparities in diabetes medication adherence for fee-for-service Medicare beneficiaries from 2013 to 2019, decomposing the effect of affiliation on disparities into within- and between-PO socioeconomic disparities. We find that after becoming affiliated, adherence for dually-eligible beneficiaries worsened relative to non dually-eligible beneficiaries within POs, but between-PO disparities were reduced. Simulation studies were used to evaluate the methods, and showed the importance of centering dual-eligibility status and its interaction with affiliation status at the PO-year level and including the PO-year level means as predictors to decompose effects of affiliation into within and between-PO effects.</p>","PeriodicalId":45600,"journal":{"name":"Health Services and Outcomes Research Methodology","volume":"26 2","pages":"240-255"},"PeriodicalIF":2.2,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13144186/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147844082","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Choosing an analytic approach: key study design considerations in state policy evaluation.","authors":"Elizabeth M Stone, Megan S Schuler, Elizabeth A Stuart, Max Rubinstein, Max Griswold, Bradley D Stein, Beth Ann Griffin","doi":"10.1007/s10742-025-00369-2","DOIUrl":"10.1007/s10742-025-00369-2","url":null,"abstract":"<p><p>This paper reviews and details methods for state policy evaluation to guide selection of a research approach, based on an evaluation's setting and available data. We highlight key design considerations for an analysis, including treatment and control group selection, timing of policy adoption, expected effect heterogeneity, and data considerations. We then provide an overview of analytic approaches and differentiate between methods based on an evaluation's context, such as settings with no control units, a single treated unit, multiple treated units, or with multiple treatment cohorts. Methods discussed include: interrupted time series models, difference-in-differences estimators, autoregressive models, and synthetic control methods, along with method extensions which address issues like staggered policy adoption and heterogenous treatment effects. We end with an illustrative example, applying the developed framework to evaluate the impacts of state-level naloxone standing order policies on overdose rates. Overall, we provide researchers with an approach for deciding on methods for state policy evaluations, which can be used to select study designs and inform methodological choices.</p><p><strong>Supplementary information: </strong>The online version contains supplementary material available at 10.1007/s10742-025-00369-2.</p>","PeriodicalId":45600,"journal":{"name":"Health Services and Outcomes Research Methodology","volume":"26 1","pages":"3-25"},"PeriodicalIF":2.2,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12967469/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147390531","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Propensity score weighting analysis with complex survey data for estimating population-level treatment effects on survival: a simulation study.","authors":"Lihua Li, Chen Yang, Wei Zhang, Yulei He, John R Pleis, Lauren M Rossen, Bian Liu, Morgan Earp, Madhu Mazumdar","doi":"10.1007/s10742-025-00344-x","DOIUrl":"10.1007/s10742-025-00344-x","url":null,"abstract":"<p><p>Propensity score weighting (PSW) is a valuable tool for estimating treatment effects on survival outcomes in observational studies. However, there is no clear best practice for applying PSW to complex survey data with survival outcomes. This paper addresses this gap by exploring how to integrate PSW into complex survey with design features (strata, clusters, sampling weights) for unbiased population-level estimates. We evaluate three PSW methods where: Method I: neither the propensity score (PS) model nor the outcome model accounts for the survey design; Method II: the PS model does not account for the survey design, but the outcome model does; Method III: both the PS model and outcome model account for the survey design. Through extensive simulations, we compare performance in estimating absolute treatment effects measured by population survival quantile effects and relative treatment effects measured by population marginal hazard ratios. Mean relative bias, mean absolute bias and coverage probability are estimated for model evaluations under various scenarios, including varying treatment effect magnitude, censoring type and rate, level of PS overlap, presence of outliers and nonresponse. Findings reveal that both survey-weighted Methods II and III outperform the unweighted Method I under most scenarios for both measures of treatment effects, especially when there is a true treatment effect. Both weighted methods II and III are found to perform closely, including when there exists informative censoring, influential outliers, or non-response. We recommend that when considering PSW with complex survey data for estimating population-level treatment effects on survival outcomes, both modelling stages should incorporate survey designs, but it is most critical for the outcome modelling. For illustration, all methods are applied to the public-use 2000-2018 National Health Interview Survey (NHIS) Linked to Mortality Files with mortality information through 2019 to estimate the effect of smoking cessation after a cancer diagnosis on subsequent overall survival.</p>","PeriodicalId":45600,"journal":{"name":"Health Services and Outcomes Research Methodology","volume":"25 4","pages":"382-409"},"PeriodicalIF":2.2,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12700616/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145757776","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Difference-in-differences analysis with repeated cross-sectional survey data.","authors":"Kerry Ye, Alyssa Bilinski, Youjin Lee","doi":"10.1007/s10742-025-00364-7","DOIUrl":"10.1007/s10742-025-00364-7","url":null,"abstract":"<p><p>Difference-in-differences (DiD) approach is one of the most widely used approaches for evaluating policy effects. However, traditional DiD methods may not recover the population-level average treatment effect on the treated (ATT) in the absence of population-level panel data, particularly when the composition of units in the treatment group changes over time. In this work, we address the following two challenges when applying DiD methods with repeated cross-sectional (RCS) survey data: (1) heterogeneous compositions of study samples across different time points, and (2) availability of data for only a sample of the population. We introduce a policy-relevant target estimand and establish its identification conditions. We then propose a new weighting approach that incorporates both estimated propensity scores and given survey weights. We establish the theoretical properties of the proposed method and examine its finite-sample performance through simulations. Finally, we apply our proposed method to a real-world data application, estimating the effect of a beverage tax on adolescent soda consumption in Philadelphia.</p>","PeriodicalId":45600,"journal":{"name":"Health Services and Outcomes Research Methodology","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2025-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12674181/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145679055","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Physician explanation of Z-coded homelessness in medicaid claims.","authors":"Michael Enich, Emmy Tiderington, Joel C Cantor","doi":"10.1007/s10742-025-00360-x","DOIUrl":"10.1007/s10742-025-00360-x","url":null,"abstract":"<p><p>The International Classification of Diseases, 10th Revision (ICD-10) introduced a set of social determinants of health (SDOH) codes including Z59.0, indicating homelessness. Z codes are not widely used, and it is not clear how Z59.0 is used to document homelessness. The goal of this study was to examine patterns of Z59.0 within a linked administrative data set and explore physician explanations for coding prevalence. This study used sequential explanatory mixed methods, first examining claims data from New Jersey Medicaid linked to Homeless Management Information System (HMIS) data for adults aged 18 and older in 19 in 21 counties from 2014 to 2016 (<i>n</i> = 724,463). The rate and patterns of Z59.0 coding was compared to HMIS-recorded homeless service use. Then we conducted semi-structured interviews with 18 physicians at high-coding hospitals analyzed via thematic analysis. Only 1.1% of inpatient and ED claims were Z-coded. Claims for male individuals who were age 43-59, Non-Hispanic/White, enrolled via Medicaid expansion, of higher health burden, in the inpatient setting, or chronically homeless were more frequently Z-coded; this was consistent with physician expectations. Physicians were surprised by the frequency Z-coding of claims for individuals who were Non-Hispanic/White and could not give clear explanations as to why some hospitals had higher Z code prevalence. They suggested that individuals who had a Z code without known homeless service use <i>were</i> experiencing homelessness. This study suggests Z-coding for homelessness identifies individuals not using formal homeless services and may be useful to support provider efforts to address housing as a health-related social need.</p>","PeriodicalId":45600,"journal":{"name":"Health Services and Outcomes Research Methodology","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13334411/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148438037","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The role of spatially varying loadings in dynamic spatial factor models for modeling the opioid syndemic.","authors":"Eva Murphy, David Kline, Staci A Hepler","doi":"10.1007/s10742-025-00356-7","DOIUrl":"10.1007/s10742-025-00356-7","url":null,"abstract":"<p><p>Understanding the interactions and spatio-temporal variations of public health outcomes is crucial for gaining insight into interrelated epidemics across different locations and time periods. Dynamic spatial factor models provide a flexible framework for capturing shared variability among multiple outcomes through a latent factor and its corresponding loadings. A common assumption in these models is that factor loadings are spatially constant, implying uniform relationships between outcomes across the study region. However, this assumption may overlook important regional differences in how outcomes relate to the underlying latent factor. In this study, we derive the covariance structure of the outcome vector to highlight how spatially varying versus constant loadings influence the overall correlation structure. We find that when loadings vary across space, the spatial covariance of the outcomes is shaped by both the spatial covariance of the loadings and the latent factors. In contrast, when loadings are spatially constant, the spatial covariance of the outcomes is determined primarily by the latent factors, leading to uniform variation across the spatial domain. To assess these differences in practice, we apply a Bayesian hierarchical spatial dynamic factor model to analyze the opioid syndemic in North Carolina. Our results suggest that incorporating spatially varying loadings provides a more detailed, county-specific understanding of the epidemic. This added flexibility enables a localized interpretation of opioid-related interactions and offers insights that could inform targeted public health interventions.</p>","PeriodicalId":45600,"journal":{"name":"Health Services and Outcomes Research Methodology","volume":"25 3","pages":""},"PeriodicalIF":2.2,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12490277/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145233814","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The impact of knowledge of hospitalization on mortality predictions.","authors":"Chuanling Qin, Curtis Peterson, William B Weeks, A James O'Malley","doi":"10.1007/s10742-025-00348-7","DOIUrl":"10.1007/s10742-025-00348-7","url":null,"abstract":"<p><p>Despite the rapid advancement of machine learning algorithms, the important problem of distinguishing patients based on the likelihood of their mortality remains a challenge. In this paper, we investigated the degree to which the incorporation of the time-varying factor, length of hospitalization could contribute to modeling mortality. A two-part modeling approach was proposed to capture the potential heterogeneity over follow-up time and to evaluate the extent to which allowing a predictor based on a fixed-time event like hospitalization (as a time-varying coefficient) enhanced mortality prediction. A test was then conducted to assess whether the association between hospitalization and mortality diminished with continued survival of a patient. Leveraging logistic regression models and the XGBoost procedure, the findings supported the claim that the baseline hospitalization is a risk factor whose importance diminishes the longer the patient survives. While simulation studies and theoretical considerations indicate that the two-part model provides deeper insight into the evolving dynamics of regression coefficients and enhances the prediction accuracy of the marginal probability of mortality, its application to the empirical data that motivated this research yielded less compelling results, a finding that aligns with previous findings. Factors such as class imbalance and the magnitude of heterogeneous effects can significantly impact the performance of the two-part model in empirical datasets.</p>","PeriodicalId":45600,"journal":{"name":"Health Services and Outcomes Research Methodology","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12788376/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145953283","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Combining multiple sources of relationships in a network to advance understanding of physicians' beliefs regarding peer-effects.","authors":"Yifan Zhao, Carly A Bobak, Megan A Murphy, Olivia Sacks, Lili Liu, Natasha Ray, Amber E Barnato, A James O'Malley","doi":"10.1007/s10742-025-00343-y","DOIUrl":"https://doi.org/10.1007/s10742-025-00343-y","url":null,"abstract":"<p><p>Patient-sharing physician networks are increasingly recognized as valuable tools for examining physician relationships in healthcare research. However, very few studies have examined the reliability of such networks and summary measures derived from them in relation to directly measured physician relationships. In this paper, we evaluate the level of congruence between a survey-based network derived from survey responses to specific name-generator questions and a patient-sharing network derived from claims data. We also examine the association of summary measures derived from either network with physicians' beliefs about peer influence in medical practice. Statistical models with hierarchical and multiple-membership structures were used to estimate the strength of the associations. We found that a survey measure indicating whether a physician was nominated by others was statistically significantly associated with their survey reported beliefs about peer influence. We also observed notable associations between the physicians' structural importance in the network reflected in their eigenvector and betweenness centrality in the patient-sharing network and their beliefs about peer influence. This study of multi-source network relational information advances our understanding of physician survey responses and yields more precise predictions of physician beliefs toward peer-influence than either data source alone. Overall, we found that patient-sharing networks are an important alternative to directly measured survey-based name-generator questions in health services research and other applications. While patient-sharing networks recover some of the information in directly measured peer physician nominations, they also contain distinct information that is helpful for interpreting healthcare insights.</p>","PeriodicalId":45600,"journal":{"name":"Health Services and Outcomes Research Methodology","volume":" ","pages":""},"PeriodicalIF":1.6,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12385539/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144973490","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}