2021
DOI: 10.2196/16651
|View full text |Cite
|
Sign up to set email alerts
|

Applying A/B Testing to Clinical Decision Support: Rapid Randomized Controlled Trials

Abstract: Background Clinical decision support (CDS) is a valuable feature of electronic health records (EHRs) designed to improve quality and safety. However, due to the complexities of system design and inconsistent results, CDS tools may inadvertently increase alert fatigue and contribute to physician burnout. A/B testing, or rapid-cycle randomized tests, is a useful method that can be applied to the EHR in order to rapidly understand and iteratively improve design choices embedded within CDS tools. … Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
22
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
6
1
1

Relationship

0
8

Authors

Journals

citations
Cited by 35 publications
(26 citation statements)
references
References 31 publications
0
22
0
Order By: Relevance
“…In Phase 3, we piloted the winning idea in a PIC practice with one physician over 5 five-hour shifts. When piloting, we used a mixed methods rapid implementation approach called rapid prototyping, which systematically tested and refined the strategy to ensure the implementation method was acceptable and feasible [ 38 , 39 , 48 , 49 ]. All study procedures were approved by the University of Pennsylvania’s Institutional Review Board.…”
Section: General Methodsmentioning
confidence: 99%
See 1 more Smart Citation
“…In Phase 3, we piloted the winning idea in a PIC practice with one physician over 5 five-hour shifts. When piloting, we used a mixed methods rapid implementation approach called rapid prototyping, which systematically tested and refined the strategy to ensure the implementation method was acceptable and feasible [ 38 , 39 , 48 , 49 ]. All study procedures were approved by the University of Pennsylvania’s Institutional Review Board.…”
Section: General Methodsmentioning
confidence: 99%
“…Rapid prototyping is the systematic testing of ideas in order to create and refine strategies quickly [ 55 ]. First employed in industrial design, this method has been extended to healthcare contexts where effective implementation strategies don’t yet exist and immediate feedback is necessary to optimize healthcare quality and safety [ 38 , 39 , 48 , 49 , 56 , 57 ]. Rapid prototyping facilitates learning as quickly as possible whether a strategy works and allows researchers to make adjustments as needed.…”
Section: General Methodsmentioning
confidence: 99%
“…If the optimization criteria are met, then this can often justify movement to Phase III. Plausible optimization trials for this phase could include but are not limited to: A/B testing (as used in the technology industry for improving usability) [67][68][69] , factorial trials as used in MOST 53,54,56,57 , sequential multiple assigned randomized trials [62][63][64][65] , micro-randomized trials [58][59][60][61]70 , and control optimization trials 71,72 . Nahum-Shani, I. et al 39 provide guidance on when to use which optimization design.…”
Section: Question 2c: Have the Optimization Criteria Relevant To The ...mentioning
confidence: 99%
“…In addition to online environments, A/B testing could also be used to improve communication tools in the clinical setting. For example, a research team at NYU Langone Health used A/B testing as a strategy to improve clinical decision support features in their medical center’s electronic health record system [ 45 ]. The team tested three different versions of a tobacco cessation alert that varied in the framing of the message: financial (emphasizing the additional revenue that a physician could generate by performing tobacco cessation counseling) vs. evidence-based (highlighting that tobacco cessation was part of providing high-quality care) vs. regulatory (stressing that tobacco cessation counseling was integral to the institution’s expectations and policies), and in an additional round of testing, assessed the impact of adding images to reinforce the message framing [ 45 ].…”
Section: Approaches To Make Health Communication Research More Timely...mentioning
confidence: 99%
“…For example, a research team at NYU Langone Health used A/B testing as a strategy to improve clinical decision support features in their medical center’s electronic health record system [ 45 ]. The team tested three different versions of a tobacco cessation alert that varied in the framing of the message: financial (emphasizing the additional revenue that a physician could generate by performing tobacco cessation counseling) vs. evidence-based (highlighting that tobacco cessation was part of providing high-quality care) vs. regulatory (stressing that tobacco cessation counseling was integral to the institution’s expectations and policies), and in an additional round of testing, assessed the impact of adding images to reinforce the message framing [ 45 ]. The experiments indicated that neither the framing nor the addition of images resulted in significant differences in acceptance rates for the tobacco alert, possibly because changes to alert presentation might not be sufficient to modify clinical practice behaviors in a significant way [ 45 ].…”
Section: Approaches To Make Health Communication Research More Timely...mentioning
confidence: 99%