Estimating Causal Effects in Observational Studies Using Electronic Health Data:
            Challenges and (some) Solutions

Stuart, Elizabeth A.; DuGoff, Eva H.; Abrams, Michael T.; Salkever, David S.; Steinwachs, Donald

doi:10.13063/2327-9214.1038

Cited by 38 publications

(23 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In terms of methods designed for large‐scale EHR‐based studies, Schuemie et al and Schuemie et al propose a P ‐value calibration method that may be able to account for both random and systematic (eg, confounding, sampling biases) sources of error using distributions of effect estimates believed to be null effects. Modern causal inference methods using the potential outcome/counterfactual framework are also being integrated in biobank analysis …”

Section: Statistical Issues Related To Biobank Researchmentioning

confidence: 99%

See 1 more Smart Citation

The emerging landscape of health research based on biobanks linked to electronic health records: Existing resources, statistical challenges, and potential opportunities

Beesley

Salvatore

Fritsche

et al. 2019

Statistics in Medicine

View full text Add to dashboard Cite

Biobanks linked to electronic health records provide rich resources for health‐related research. With improvements in administrative and informatics infrastructure, the availability and utility of data from biobanks have dramatically increased. In this paper, we first aim to characterize the current landscape of available biobanks and to describe specific biobanks, including their place of origin, size, and data types. The development and accessibility of large‐scale biorepositories provide the opportunity to accelerate agnostic searches, expedite discoveries, and conduct hypothesis‐generating studies of disease‐treatment, disease‐exposure, and disease‐gene associations. Rather than designing and implementing a single study focused on a few targeted hypotheses, researchers can potentially use biobanks' existing resources to answer an expanded selection of exploratory questions as quickly as they can analyze them. However, there are many obvious and subtle challenges with the design and analysis of biobank‐based studies. Our second aim is to discuss statistical issues related to biobank research such as study design, sampling strategy, phenotype identification, and missing data. We focus our discussion on biobanks that are linked to electronic health records. Some of the analytic issues are illustrated using data from the Michigan Genomics Initiative and UK Biobank, two biobanks with two different recruitment mechanisms. We summarize the current body of literature for addressing these challenges and discuss some standing open problems. This work complements and extends recent reviews about biobank‐based research and serves as a resource catalog with analytical and practical guidance for statisticians, epidemiologists, and other medical researchers pursuing research using biobanks.

show abstract

Section: Statistical Issues Related To Biobank Researchmentioning

confidence: 99%

“…Modern causal inference methods using the potential outcome/counterfactual framework are also being integrated in biobank analysis. [118][119][120]…”

Section: Considerations Related To Study Designmentioning

confidence: 99%

The emerging landscape of health research based on biobanks linked to electronic health records: Existing resources, statistical challenges, and potential opportunities

Beesley

Salvatore

Fritsche

et al. 2019

Statistics in Medicine

View full text Add to dashboard Cite

show abstract

“…Most researchers include all variables that could potentially correlate with the selection influences impacting treatment and outcome (Coffman, 2012;Cuong, 2013;Lanza, Coffman, & Xu, 2013;Stuart et al, 2013), regardless of the magnitude of correlation (Rubin, 1997).…”

Section: Propensity Score Matchingmentioning

confidence: 99%

Alternatives to Randomized Control Trials: A Review of Three Quasi-experimental Designs for Causal Inference

Panko

Curtis

Gorrall

et al. 2015

View full text Add to dashboard Cite

Abstract. The Randomized Control Trial (RCT) design is typically seen as the gold standard in psychological research. As it is not always possible to conform to RCT specifications, many studies are conducted in the quasi-experimental framework. Although quasi-experimental designs are considered less preferable to RCTs, with guidance they can produce inferences which are just as valid. In this paper, the authors present 3 quasi-experimental designs which are viable alternatives to RCT designs. These designs are Regression Point Displacement (RPD), Regression Discontinuity (RD), and Propensity Score Matching (PSM). Additionally, the authors outline several notable methodological improvements to use with these designs.Keywords. Psychometrics, Quasi-Experimental Design, Regression Point Displacement, Regression Discontinuity, Propensity Score Matching.Resumen. Los diseños de Pruebas Controladas Aleatorizadas (PCA) son típicamente vistas como el mejor diseño en la investigación en psicología. Como tal, no es siempre posible cumplir con las especificaciones de las PCA y por ello muchos estudios son realizados en un marco cuasi experimental. Aunque los diseños cuasi experimentales son considerados menos convenientes que los diseños PCA, con directrices estos pueden producir inferencias igualmente válidas. En este artículo presentamos tres diseños cuasi experimentales que son formas alternativas a los diseños PCA. Estos diseños son Regresión de Punto de Desplazamiento (RPD), Regresión Discontinua (RD), Pareamiento por Puntaje de Propensión (PPP). Adicionalmente, describimos varias mejorías metodológicas para usar con este tipo de diseños.

show abstract

“…Meta-analyses of clinical trials may have higher power and be more generalizable, but are vulnerable to publication bias, small-study effects and limited degree of heterogeneity (12). Electronic health records (EHRs) hold promise as an alternative way to conduct causal inference experiments, that can address some of these meta-analyses limitations (13,14).…”

Section: Introductionmentioning

confidence: 99%

Estimating Effects Of Second Line Therapy For Type 2 Diabetes Mellitus: Retrospective Cohort Study

Gottlieb

Yanover

Cahan

et al. 2017

Preprint

View full text Add to dashboard Cite

Objective: Metformin is the recommended initial drug treatment in type 2 Diabetes Mellitus, but there is no clearly preferred choice for an additional drug when indicated. We use electronic health records to infer the counterfactual drug effectiveness in reducing HbA1c levels and effect on body-mass index (BMI) of four second line diabetes drug classes. Study design and setting:Retrospective analysis of the electronic health records of US-based patients in the Explorys database using causal inference methodology to adjust for censored patients and confounders. Participants and Exposures:Our cohort consisted of roughly 25,000 patients with type 2 diabetes, prescribed metformin along with a drug out of four second line drug classes -sulfonylureas, thiazolidinediones, DPP-4 inhibitors and GLP-1 agonists, during the years 2000-2013.Main outcome measures: Glycated hemoglobin (HbA1c) and BMI of these patients after six and twelve months of treatment. Results:We show that all four drug classes reduce glycated hemoglobin levels, but the effect of sulfonylureas after 12 months of treatment is less pronounced compared to other classes. We also predict that thiazolidinediones increase body weight while DPP-4 inhibitors decrease it. Conclusion:Our results are in line with current knowledge on second line drug effectiveness and effect on BMI. They demonstrate that causal inference from Electronic health records is an effective way for conducting multi-treatment causal inference studies. WHAT IS ALREADY KNOWN ON THIS TOPICThe effect of type 2 diabetes second-line drugs on glycosylated hemoglobin levels and on Body-Mass Index have been evaluated in clinical studies. However, the clinical implication of these studies is limited by small number of participating individuals and the homogeneity of the study populations. Meta-analysis studies have increased sample size but potentially suffer from the similar homogeneity biases. WHAT THIS STUDY ADDSThis study performs, for the first time, a large-scale analysis of the therapeutic and adverse effects of type 2 diabetes second-line drugs in real-world population using electronic health records. We confirm current knowledge for glycosylated hemoglobin levels, while showing similar effects on BMI for inhibitors of Dipeptidyl peptidase 4 (DPP-4), Glucagon-like peptide-1 receptor agonists (GLP-1).peer-reviewed)

show abstract

Estimating Causal Effects in Observational Studies Using Electronic Health Data: Challenges and (some) Solutions

Cited by 38 publications

References 46 publications

The emerging landscape of health research based on biobanks linked to electronic health records: Existing resources, statistical challenges, and potential opportunities

The emerging landscape of health research based on biobanks linked to electronic health records: Existing resources, statistical challenges, and potential opportunities

Alternatives to Randomized Control Trials: A Review of Three Quasi-experimental Designs for Causal Inference

Estimating Effects Of Second Line Therapy For Type 2 Diabetes Mellitus: Retrospective Cohort Study

Contact Info

Product

Resources

About