Shirley Wang
Research Interests
Make your next move.
Prepare your application
Review drafts before you send them.
Explore related searches
Articles (29)
Year:
2026
Year:
2026
Year:
2026
Year:
2026
Year:
2026
Objectives To develop and validate machine learning (ML) models that predict probable cause of death (CoD) using structured electronic health record (EHR) data, unstructured clinical notes, and publicly available sources. Materials and Methods This multi-institutional retrospective study was conducted across Vanderbilt University Medical Center (VUMC) and Massachusetts General Brigham (MGB), including deceased patients with encounters between October 1, 2015, and January 1, 2021, and confirmed death records. The cohort included 13 708 patients from VUMC and 34 839 from MGB.The primary outcome was underlying CoD categorized into the top 15 National Center for Health Statistics rankable causes, with others grouped as “Other.” Performance was assessed using weighted area under the receiver operating characteristic curve (AUC) and F-measure. Results The XGBoost model using structured EHR data alone achieved weighted AUCs of 0.86 (95% CI, 0.84-0.88) at VUMC and 0.80 (95% CI, 0.79-0.80) at MGB. Adding unstructured notes improved performance, with weighted AUCs of 0.90 (95% CI, 0.88-0.93) at VUMC and 0.92 (95% CI, 0.91-0.92) at MGB. Adding publicly available data did not further improve performance. Cross-institutional validation revealed significant performance degradation. Discussion Models integrating structured and unstructured EHR data show strong within-institution performance but limited generalizability across healthcare systems, highlighting challenges related to institutional data heterogeneity. Conclusions Machine learning models combining structured and unstructured EHR data accurately predict CoD within institutions but perform poorly across sites. Health-care institutions may benefit from adopting robust processes for locally tailored models, and future research should focus on enhancing model generalizability while addressing unique institutional data environments.
Year:
2026
Year:
2026
Objectives Real-world evidence (RWE) increasingly informs clinical decisions, yet manual adjustment for confounding limits scalability. Data-adaptive (DA) algorithms for high-dimensional proxy adjustment show promise but have not been systematically compared to investigator-specified (IS) approaches across diverse treatment scenarios. We evaluated whether DA strategies perform comparably to manually curated IS models using claims-based emulations of 15 randomized trials from the RCT-DUPLICATE initiative. Materials and Methods We identified new-user cohorts for 15 trial emulations in Optum’s de-identified Clinformatics Data Mart Database (2004-2023). Treatment effects were estimated using 3 adjustment strategies: (1) IS models with manually tailored covariates; (2) full-DA strategies using empirical features from semiautomated pipelines; and (3) hybrid-DA models incorporating both empirical and investigator-defined covariates. Agreement with RCT benchmarks was assessed via binary metrics and difference-in-differences. Results Outcome-adaptive LASSO achieved better RWE-RCT agreement than IS adjustment in 73% of full-DA and 87% of hybrid-DA emulations. Other DA methods considering feature associations with both treatment and outcome performed similarly well, while models tuned solely for treatment prediction performed poorly. Performance of IS vs DA strategies differed across emulated trials. Discussion Top DA algorithms matched manual IS models on average, but impact varied by emulation. Case studies illustrate the continued importance of subject-matter knowledge, particularly for complex treatment strategies. Conclusion Data-adaptive algorithms show promise for scalable confounding adjustment in large-scale evidence systems and as augmentation tools for investigator-specified designs. Hybrid strategies combining algorithmic methods with investigator expertise offer the most reliable approach for individual causal questions.
Year:
2026
Cardiovascular outcome trials of the incretin-based medicines tirzepatide and semaglutide have shown benefits in populations with varying levels of cardiovascular risk. However, without direct head-to-head comparisons, treatment decisions rely on indirect evidence from heterogeneous trial populations, leaving optimal treatment choices uncertain. Here we conducted five cohort studies to assess the effectiveness of tirzepatide and semaglutide in patients with elevated cardiovascular risk, including obesity and type 2 diabetes, enrolled in insurance programs in the USA between 2018 and 2025. First, we emulated two cardiovascular outcome trials, SUSTAIN-6 (semaglutide versus sitagliptin as placebo proxy) and SURPASS-CVOT (tirzepatide versus dulaglutide), to benchmark and critically evaluate our design, data and analytic framework. Second, we assessed each drug in expanded populations reflective of patients routinely seen in clinical practice. Third, we directly compared tirzepatide versus semaglutide. Baseline confounders were balanced using propensity score matching. For the primary composite endpoint of myocardial infarction, stroke or all-cause mortality, benchmarking identified high agreement between the reference trials and their emulations for all individual endpoints except for all-cause mortality in SUSTAIN-6, informing subsequent analyses. In expanded populations, comparing semaglutide versus sitagliptin for the composite outcome of myocardial infarction or stroke yielded a hazard ratio of 0.82 (95% confidence interval (CI) 0.74 to 0.91), and comparing tirzepatide versus dulaglutide for the composite outcome including mortality yielded a hazard ratio of 0.87 (95% CI 0.75 to 1.01). In the head-to-head comparison of tirzepatide versus semaglutide, the hazard ratio was 1.06 (95% CI 0.95 to 1.18). These findings support a comparable cardiovascular benefit of tirzepatide and semaglutide in clinical practice and demonstrate how rigorously designed real-world evidence can complement randomized clinical trials. ClinicalTrials.gov registration: NCT06659744 , NCT07088718 , NCT07096063 .
Year:
2026
Claims‐based analyses can suffer from residual and unmeasured confounding due to factors that are poorly captured in claims. Some of these factors may be measured in other data sources, such as in structured fields of electronic health records (EHR), for example, laboratory test results, or in free‐text physician notes. We conducted a proof‐of‐principle study to demonstrate a process for evaluating the potential risk of confounding—factors poorly captured in claims data but measurable in the EHR as part of drug safety surveillance activities. In future practical applications, this approach could be used along with other sensitivity analyses to evaluate potential residual confounding (e.g., E ‐values, negative controls). We used claims‐EHR linked data from the Mass General Brigham site of the US Food and Drug Administration's (FDA) Sentinel Real World Evidence Data Enterprise. We extracted a cohort that was previously used in a prototypical Sentinel claims‐based query that compared initiators of sacubitril‐valsartan vs. angiotensin‐converting enzyme inhibitors or angiotensin receptor blockers on the risk of angioedema. In this cohort, we used EHR data to characterize angioedema risk factors poorly captured in claims and observed that claims‐based proxies balanced most risk factors that were measurable only in EHR data. While quantitative bias analysis methods can be used to adjust for residual confounding using external information on magnitude and direction of bias, this was deemed unnecessary for this example due to the observed balance achieved on risk factors for angioedema measured in the EHR. A robust linked EHR‐claims data infrastructure is crucial for routine application of these methods to evaluate and mitigate residual confounding in drug safety surveillance studies.
Year:
2026
Year:
2025
Year:
2025
Year:
2025
Year:
2025
Year:
2025
Year:
2025
Year:
2025
Year:
2025
Year:
2025
Year:
2024
Year:
2024
Year:
2024
Year:
2024
Year:
2024
Year:
2024
Year:
2024
Year:
2024
Year:
2024
Year:
2024
Collaborators (17)
Massimiliano Russo
Harvard University
Daniel Prieto-Alhambra
Professor (part-time)
Erasmus MC
Jennifer L. Lund
University of North Carolina at Chapel Hill
Kevin Wing
Senior Lecturer in Epidemiology
University of Glasgow
Judith Maro
-
Joshua Smith
Assistant Professor
Vanderbilt University Medical Center
Jie Yang
Harvard University
Melissa McPheeters
Research Professor
Vanderbilt University Medical Center
Katie Harron
Associate Professor
University College London
Kathryn Gray
Associate Professor
Washington University School of Medicine
Mohammed Al-Garadi
Research Assistant Professor
Vanderbilt University Medical Center
Sebastian Schneeweiss
Harvard University
George (Shao Qian) Tan
Monash University Malaysia.
Jenni Ilomaki
Senior Lecturer
-
Kristian Filion
Associate Professor
McGill University
Sonia Hernandez Diaz
Professor
Harvard T.H. Chan School of Public Health
Stuart Nicholls
Assistant Professor
University of Ottawa
Make your next move.
Prepare your application
Review drafts before you send them.