Search

Sherri Rose, Ph.D. is an associate professor at Stanford University in the Center for Health Policy and Center for Primary Care and Outcomes Research as well as Co-Director of the joint Harvard–Stanford Health Policy Data Science Lab. A renowned expert in machine learning methodology for causal inference and prediction, her applied work has focused on risk adjustment, algorithmic fairness, health program evaluation, and comparative effectiveness research. Dr. Rose's leadership positions include current roles as Co-Editor of Biostatistics and Chair of the American Statistical Association's Biometrics Section. She is also a Fellow of the American Statistical Association. Dr. Rose earned a BS in Statistics from The George Washington University and a PhD in Biostatistics from the University of California, Berkeley before completing an NSF Mathematical Sciences Postdoctoral Research Fellowship at Johns Hopkins University. Prior to joining the faculty at Stanford University, she was on the faculty at Harvard Medical School in the Department of Health Care Policy. Below, an interview of Dr. Rose, conducted by her colleague, Dr. Laura Hatfield, on the occasion of her 2020 Mid-Career Award from the Health Policy Statistics Section (HPSS) of the American Statistical Association. This award recognizes leaders in health care policy and health services research who have made outstanding contributions through methodological or applied work and who show a promise of continued excellence at the frontier of statistical practice that advances the aims of HPSS. [ABSTRACT FROM AUTHOR]

Patient-centered care involves patients in decision-making about their medical care. Effective shared decision-making requires relevant evidence on the expected health outcomes of treatment, assessment of patient preferences for possible health outcomes, and a method to synthesize this information. Few tools exist to help clinicians and patients synthesize clinical evidence and personal preferences. We develop a statistical framework that combines multiple data sources on expected treatment outcomes with individual preferences to produce a personalized preference-weighted outcome score (PWOS). The PWOS can be calculated for multiple treatments and compared to determine which will provide the best balance of risks and benefits given a patient's preferences. We demonstrate our method by evaluating adjuvant chemotherapy regimens for colorectal cancer. We begin by identifying heterogeneity in patient preferences for health outcomes associated with colorectal cancer disease and treatment, finding classes of patients who value efficacy and side effects differently. Then we fit a hierarchical Bayesian model to randomized clinical trials and produce posterior distributions of expected outcomes under three chemotherapy regimens. We use the PWOS to combine distinct sets of patient preferences with these expected outcomes. Our method preserves estimation uncertainty and accounts for correlation among outcomes. In a simulation study of applying PWOS to make decisions at the population level, we find that our methods are most useful when there are large differences in individual preferences and small distinctions in treatment efficacy (i.e., preference-sensitive settings). [ABSTRACT FROM AUTHOR]

Recent interest in understanding the effect of interventions on patient-reported outcomes as well as traditional clinical endpoints has led to an expansion of methods for simultaneous modeling of longitudinal and survival data in clinical trials. Such joint models link the multiple outcome measures using an underlying latent structure, typically a collection of individual-level random effects. They can estimate treatment effects separately on different aspects of a disease process, as well as illuminate associations among outcomes and individual variability. In communicating model output to clinicians and patients, it is challenging to convey a meaningful interpretation of multiple treatment effects, complex outcome associations, and important underlying assumptions. This paper presents graphical displays designed to make the output of Bayesian joint models accessible to non-technical audiences, while preserving important methodological features. We emphasize individual-level posterior predictions of longitudinal and survival outcomes, illustrating our methods using patient-reported symptom severity and survival in a clinical trial example. [ABSTRACT FROM AUTHOR]