About

Roee Gutman is a Professor (Tenured) in the Department of Biostatistics at Brown University. His areas of interest and research include Bayesian data analysis, missing data, file linking, causal inference and bioinformatics, as well as applications of these methods to health policy research and practice and epidemiology. Some examples of recent projects include linking Meals on Wheels of America (MOWA) client data to Medicare claims without unique identifiers, equating health assessments across post-acute settings, and examining the effects of bed-hold policies on re-hospitalization and mortality in nursing homes.

Research topics

• Nursing
• Medicine
• Medical emergency
• Family medicine
• Emergency medicine
• Immunology
• Pediatrics
• Internal medicine

Selected publications

• Analysis of Linked Files: A Missing Data Perspective

  Statistical Science · 2026-01-14

  preprintOpen accessSenior author

  In many applications, researchers seek to identify overlapping entities across multiple data files. Record linkage algorithms facilitate this task, in the absence of unique identifiers. As these algorithms rely on semi-identifying information, they may miss records that represent the same entity, or incorrectly link records that do not represent the same entity. Analysis of linked files commonly ignores such linkage errors, resulting in biased, or overly precise estimates of the associations of interest. We view record linkage as a missing data problem, and delineate the linkage mechanisms that underpin analysis methods with linked files. Following the missing data literature, we group these methods under three broad categories: likelihood and Bayesian methods, imputation methods, and weighting methods. We summarize the assumptions and limitations of the methods, and evaluate their performance in a wide range of simulation scenarios.

  PublisherOA PDFDOI

• Protocol for a type 1 hybrid effectiveness implementation trial to evaluate whether a technology-based collaborative care model is non-inferior to remote blood pressure monitoring on persistent hypertension and preventive care attendance among postpartum people with hypertension

  Contemporary Clinical Trials · 2025-10-24 · 3 citations

  articleOpen access

  BACKGROUND: Because persistent hypertensive disorders of pregnancy (HDP) are major sources of short- and long-term maternal morbidity, national guidelines recommend blood pressure (BP) measurement 3-10 days after childbirth and preventive care visits within one year of delivery. Programs in which patients self-measure BP (SMBP) at home improve BP ascertainment but have unclear effects on preventive care receipt or maternal morbidity. We aim to examine a novel SMBP program's effect on HDP-related morbidity and to develop a toolkit to support wide dissemination of our program. METHODS: In this type 1 hybrid effectiveness implementation trial, 1536 postpartum patients with HDP will be randomized 1:1 to a routine SMBP program or a novel SMBP program, RI-SPHERES. In routine care, participants enter SMBP into the electronic medical record for provider response. In RI-SPHERES, a 4G Long Term Evolution (LTE)-enabled BP cuff automatically sends all SMBP to an artificial-intelligence-based platform, which provides participants with text-message feedback and notifies providers of abnormal SMBP. A multidisciplinary collaborative care group meets weekly to review RI-SPHERES's participant registry. The primary outcome of this non-inferiority trial is stage II hypertension (≥140/90 mmHg) at six weeks postpartum, with a non-inferiority margin of 6 %. The main secondary outcome is preventive care receipt (non-urgent well visit appointment from six weeks to one year postpartum). Mixed methods research will identify facilitators and barriers to RI-SPHERES that will promote its widespread implementation. ETHICS AND DISSEMINATION: Women & Infants Hospital of Rhode Island's IRB approved this study. CLINICAL TRIALS REGISTRATION: NCT06842875.

  PublisherDOI

• Positive Screens Are More Likely in a National Lung Cancer Screening Registry Than the National Lung Screening Trial

  Journal of the American College of Radiology · 2025-02-27 · 3 citations

  article
  PublisherDOI

• A Bayesian Framework for Latent Compliance Modeling in Cluster Randomized Trials with One-Sided Noncompliance

  ArXiv.org · 2025-09-18

  preprintOpen accessSenior author

  In pragmatic cluster randomized controlled trials (PCRCTs), healthcare providers are randomized while both providers and patients may deviate from the assigned intervention. In many PCRCTs, cluster-level implementation is measured using multiple continuous metrics, while individual compliance is recorded as a binary indicator. Standard complier average causal effect (CACE) estimands focus on individual-level compliance and do not account for heterogeneity in implementation across clusters. When intervention uptake is shaped by both provider- and patient-level processes, it is of scientific interest to characterize how effects vary across these sources of compliance. We propose a Bayesian framework for PCRCTs with one-sided binary noncompliance at the individual level and one-sided partial compliance at the cluster level. The method uses a latent mixture model to summarize heterogeneity in cluster-level implementation based on baseline characteristics and observed implementation measures, and links these latent implementation types to individual compliance and outcomes through a joint model. Because compliance is only observed in treated clusters, the model imputes unobserved compliance behavior for clusters and individuals assigned to control. The framework enables estimation of finite- and super-population intent-to-treat (ITT) and CACE estimands, both marginally and within latent implementation types. We apply the method to the METRIcAL trial, a pragmatic cluster randomized study evaluating a personalized music intervention for nursing home residents with dementia. The analysis illustrates how accounting for implementation heterogeneity and individual compliance can provide insights beyond standard ITT analyses.}{Causal inference; Principal stratification; Complier average causal effect; Cluster randomized trials; Noncompliance; Bayesian methods; Latent variable models; Interference.

  PublisherOA PDFDOI

• A study protocol for a randomized controlled trial evaluating the impact of adding community health worker coaching calls and healthy grocery bag deliveries to a Meals on Wheels home-delivered meal program for homebound older adults in Rhode Island

  BMC Public Health · 2025-10-01

  articleOpen access

  BACKGROUND: Home-delivered meal programs (HDMP), such as Meals on Wheels, offer nutritious meals for homebound older adults experiencing nutritional risk. Despite receiving meals, participants may still have difficulty achieving nutritional goals, overcoming social isolation, and addressing other health issues. We aim to evaluate the impact of adding enhancements to traditional HDMP on improving diet quality, food and nutrition security, loneliness, and health-related quality of life among older adults in a randomized controlled trial. METHODS: Homebound older adults at nutritional risk and participating in the Meals on Wheels of Rhode Island, Inc. (MOWRI) HDMP are randomized to receive either a usual care control group of the traditional HDMP (5 meals delivered per week) or the enhanced program (Meals+), which includes four Community Health Worker (CHW) coaching calls using motivational interviewing, and delivery of three healthful grocery bags during 12 weeks, in addition to the traditional HDMP. The primary outcome is diet quality measured by the validated Dietary Screening Tool (DST). Food and nutrition security, loneliness, and health-related quality of life are secondary outcomes assessed by validated measures. In the 12-week follow-up call, CHWs also ask participants about utilization and satisfaction with the intervention. The usual care group receives coaching from CHWs to connect them to community resources in this follow-up call. Study procedures were tested in a pilot randomized controlled trial (n = 12), resulting in modifications to the study protocol. DISCUSSION: Enhancements such as CHW calls and grocery bags can help HDMP target food access, social and health interventions for older adults. These enhanced HDMP have the potential to be sustained and replicated nationwide. TRIAL REGISTRATION: Number NCT06401694; Start date: 2024-06-20.

  PublisherOA PDFDOI

• Methods to adjust for stratification variables in stratified cluster randomized trials

  Health Services and Outcomes Research Methodology · 2025-06-08

  articleSenior author
  PublisherDOI

• Amyloid PET and clinical management in a diverse, cognitively impaired population: The New IDEAS Study

  Alzheimer s & Dementia · 2025-07-01 · 5 citations

  articleOpen access

  INTRODUCTION: The New Imaging Dementia-Evidence for Amyloid Scanning (IDEAS) study (NCT04426539) evaluated the association between amyloid positron emission tomography (PET) and changes in clinical management among ethnoracially diverse, clinically heterogeneous patients. METHODS: We assessed diagnosis and management plan before and 90 ± 30 days after amyloid PET among Medicare beneficiaries who met 2018 National Institute on Aging-Alzheimer's Association criteria for mild cognitive impairment (MCI) or dementia. We aimed to identify ≥ 30% change in a composite patient management endpoint (CPME; i.e., changes in Alzheimer's disease [AD]/non-AD medications, changes in counseling). RESULTS: Among 5757 participants (median age 75 years; 21.7% Black, 20.3% Latinx, 58.1% all other races/ethnicities [AORE]), a change in CPME occurred in 59.0% (95% confidence interval 57.6%-60.5%) of individuals post PET. Change varied by ethnoracial identity and type of clinical presentation: Black (MCI: 55.3%, dementia: 55.8%), Latinx (MCI: 53.7%, dementia: 61.9%), AORE (MCI: 62.0%, dementia: 58.3%), typical (MCI: 64.8%, dementia: 60.9%), atypical (MCI 45.5%, dementia: 53.6%). DISCUSSION: Amyloid PET is associated with clinical management among diverse, clinically heterogeneous populations. HIGHLIGHTS: Changes in management plan occurred in 59% of patients 90 days after amyloid positron emission tomography. Rates of change in management exceeded the pre-specified goal of > 30% across ethnoracial groups. Rates of change in management also exceeded > 30% among amnestic and non-amnestic Alzheimer's disease presentations.

  PublisherOA PDFDOI

• Impact of a Pharmacy Copayment Increase on Medication Use in the Military Health System

  Medical Care · 2025-07-01

  article

  BACKGROUND: We analyzed the impact of a copayment increase instituted February 1, 2018 for persons covered by the retail or mail order Military Health System (MHS) pharmacy benefit. METHODS: We compared medication use in 2 cohorts in the 12 months before and after the copayment increase: MHS beneficiaries between 18 and 64 years old (MHS cohort), and MHS beneficiaries older than or equal to 65 years old with Medicare (Medicare cohort). Subjects with diabetes, hypertension and hypercholesterolemia were eligible. Using propensity score matching, we compared the control group of those who obtained medications at military pharmacies ($0 copay) to those who experienced a copay increase. The outcome variable was any use of condition-specific medication. RESULTS: In the MHS cohort there were 30,753, 46,965, and 59,783 non-unique persons with diabetes, hyperlipidemia, and hypertension, respectively, in the intervention and control groups. In the Medicare cohort there were 45,977, 205,363, and 365,628 non-unique persons, respectively. The post-period mPDC differences for the MHS cohort were 0.02 (95% CI: 0.01, 0.03), 0.03 (95% CI: 0.02, 0.03), and 0.03 (95% CI: 0.01, 0.03) for the diabetes, hyperlipidemia, and hypertension cohorts, respectively. The post-period mPDC differences for the Medicare cohort were 0.01 (95% CI: 0.01, 0.02), 0.03 (95% CI: 0.03, 0.04), and 0.01 (95% CI: 0.01, 0.02), respectively. CONCLUSIONS: The small (1-3 percentage point) copayment increases are unlikely to have had adverse clinical effects. Insurers and policy-makers should understand that even small copayment increases can impact the use of clinically important medications and should carefully consider the tradeoffs.

  PublisherDOI

• Causal inference with cross-temporal design

  Biometrics · 2025-01-07 · 2 citations

  articleOpen accessSenior author

  When many participants in a randomized trial do not comply with their assigned intervention, the randomized encouragement design is a possible solution. In this design, the causal effects of the intervention can be estimated among participants who would have experienced the intervention if encouraged. For many policy interventions, encouragements cannot be randomized and investigators need to rely on observational data. To address this, we propose a cross-temporal design, which uses time to mimic a randomized encouragement experiment. However, time may be confounded with temporal trends that influence the outcomes. To disentangle these trends from the intervention effects, we replace the commonly used exclusion restrictions with temporal assumptions. We develop Bayesian procedures to estimate the causal effects and compare it to instrumental variables and matching approaches in simulations. The Bayesian approach outperforms the other 2 approaches in terms of estimation accuracy, and it is relatively robust to various violations of the common trends assumption. Taking advantage of the expansion of the Medicare Advantage (MA) program between 2011 and 2017, we implement the proposed method to estimate the effects of MA enrollment on the risk of skilled nursing facility residents being re-hospitalized within 30 days after discharge from the hospital.

  PublisherOA PDFDOI

• A Bayesian Record Linkage Approach that Adjusts for Variables in One File 

  International Journal for Population Data Science · 2024-09-10

  articleOpen accessSenior author

  In many healthcare and social science applications, information about units is dispersed across multiple data files. Linking records across files is necessary to estimate associations between variables exclusive to each of the files. Common record linkage algorithms only rely on similarities between linking variables common to all the files. Moreover, analysis of linked files often ignores errors that may arise from incorrect or missed links. Bayesian record linking methods allow for natural propagation of linkage errors, by jointly sampling the linkage structure and the model parameters. We extend an existing Bayesian record linkage approach to integrate associations between variables exclusive to each file being linked. We show analytically, and using simulations, that the proposed method improves the linkage process, and results in accurate statistical inferences. We apply the proposed method to link Meals on Wheels (MOW) recipients to Medicare Enrollment records, and examine the relationship between activities of daily living and healthcare utilization among MOW recipients.

  PublisherOA PDFDOI

Recent grants

• QuBBD: Estimating drug-drug and drug-disease interactions for nursing homes residents

  NSF · $100k · 2015–2017

Frequent coauthors

• Vincent Mor

  Providence College

  128 shared

• Kali S. Thomas

  Johns Hopkins University

  55 shared

• Jessica Roydhouse

  University of Tasmania

  54 shared

• Amal N. Trivedi

  Providence VA Medical Center

  52 shared

• Andrew R. Zullo

  Brown University

  45 shared

• Ellen McCreedy

  Issues Research

  44 shared

• Pedro Gozalo

  Providence College

  34 shared

• Ira B. Wilson

  Brown University

  29 shared

Labs

• Roee Gutman LabPI

Education

• Ph.D., Statistics

  Harvard University

• M.S., Applied Statistics

  Tel Aviv University

  2004

• B.S., Statistics, Operations Research and Computer Science

  Tel Aviv University

  1999

Awards & honors

• Funding from the Patient-Centered Outcomes Research Institut…
• Funding from the National Science Foundation (NSF)
• Funding from the National Institute on Ageing (NIA)