Health Services Research in Anesthesia: A Brief Overview of Common Methodologies

Abstract

The use of large data sources such as registries and claims-based data sets to perform health services research in anesthesia has increased considerably, ultimately informing clinical decisions, supporting evaluation of policy or intervention changes, and guiding further research. These observational data sources come with limitations that must be addressed to effectively examine all aspects of health care services and generate new individual- and population-level knowledge. Several statistical methods are growing in popularity to address these limitations, with the goal of mitigating confounding and other biases. In this article, we provide a brief overview of common statistical methods used in health services research when using observational data sources, guidance on their interpretation, and examples of how they have been applied to anesthesia-related health services research. Methods described involve regression, propensity scoring, instrumental variables, difference-in-differences, interrupted time series, and machine learning.

Health Services Research: A Review for the Interventional Radiologist

“…Methods to examine (and sometimes address) the impact of this fundamental limitation include regression analysis, propensity scoring, instrumental variable analysis, quasi-experimental designs, and machine learning. 25 An example of this common issue is demonstrated in a study evaluating transcatheter and endoscopic treatments for upper gastrointestinal hemorrhage by Hafezi-Nejad et al They initially found that embolization (vs. endoscopy) was associated with higher mortality and greater hospital charges. However, this difference was nullified after controlling for disease severity and other procedures in propensity score–matched groups and by covariate adjustment.…”

Generalization of Odd Ramos-Louzada generated family of distributions: Properties, characterizations, and applications to diabetes and cancer survival datasets

“…Several research studies have used statistical modeling approaches in healthcare management. Notable among these are De Villiers et al [ 3 ], Lama et al [ 4 ], Sandberg et al [ 5 ], Altaf-Ul-Amin et al [ 6 ], Ratnovsky et al [ 7 ], Onchonga et al [ 8 ], and Illescas et al [ 9 ] which provide more details.…”

Closing the Knowledge Translation Gap: Health Services Research and Perioperative Medicine—New Horizons for Anesthesiologists

“…There is a clear need for tools that will enable anesthesiologists to be engaged in HSR and solve the issues outlined above. In their 2 articles, Illescas et al 11 and Zhong et al 12 provide an overview of common statistical methods used in HSR, as well as a description of a wide range of data sources used for anesthesia-related HSR. The article describing HSR statistical methodology is focused on observational data and describes regression, propensity scoring, instrumental variables, machine learning, difference-in-differences, and interrupted time series.…”