Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

Automated Tailoring of Clinical Performance Feedback in Low-Resource Settings

Landis Lewis, Zachary (2014) Automated Tailoring of Clinical Performance Feedback in Low-Resource Settings. Doctoral Dissertation, University of Pittsburgh. (Unpublished)

[img]
Preview
PDF
Primary Text

Download (4MB) | Preview

Abstract

A patient-centered, continuously learning healthcare system is a compelling vision for the future of healthcare, introduced by the Institute of Medicine. A key part of this vision is the creation of feedback loops to support continuous clinical learning and behavior change. Opportunities to generate clinical performance feedback are increasing, due to globally unprecedented growth in the adoption of eHealth. These opportunities are especially promising in low-income countries where a critical problem is poor performance of healthcare providers that lowers the quality of care.

Clinical audit and feedback, defined as the provision of performance summaries to healthcare providers, teams, and organizations, is widely used for quality improvement and the implementation of evidence-based practice. Evidence shows that clinical audit and feedback can significantly improve compliance with desired practice, but it is unclear when and how it is most effective. Psychological theories offer rigorously evaluated theoretical causal mechanisms that may explain when feedback is likely to be effective for clinical learning and behavior change, but these have rarely been used to inform the design of feedback interventions. In addition to uncertainty regarding the effect of feedback on clinical performance, a critical challenge for using eHealth data to automate the delivery of feedback is understanding data quality for the purpose of performance measurement. To overcome the dual challenges of variable data quality and performance feedback effectiveness, I propose a novel, theory-informed approach for generating clinical performance feedback: automated feedback message tailoring.

This research explores evidence, theories, methods, and clinical settings that establish a foundation of knowledge for the automated tailoring of feedback messages. I developed and applied this knowledge within antiretroviral therapy clinics in Malawi, Africa, where an electronic medical record system is routinely used, to understand the potential impact of feedback message tailoring in low-resource settings. This work introduces a novel information tool that may enable clinical supervisors to use existing eHealth data to provide more effective performance feedback, and which may support the testing of hypotheses about the effect of tailored feedback messages on clinical performance.


Share

Citation/Export:
Social Networking:
Share |

Details

Item Type: University of Pittsburgh ETD
Status: Unpublished
Creators/Authors:
CreatorsEmailPitt UsernameORCID
Landis Lewis, Zacharyzjl1@pitt.eduZJL1
ETD Committee:
TitleMemberEmail AddressPitt UsernameORCID
Committee ChairJacobson, Rebecca Scrowleyrs@upmc.eduREBECCAJ
Committee MemberDouglas, Gerald Pgdouglas@pitt.eduGDOUGLAS
Committee MemberHochheiser, Harryharryh@pitt.eduHARRYH
Committee MemberKam, Matthewkam.matt@gmail.com
Date: 24 October 2014
Date Type: Publication
Defense Date: 28 August 2014
Approval Date: 24 October 2014
Submission Date: 23 October 2014
Access Restriction: 1 year -- Restrict access to University of Pittsburgh for a period of 1 year.
Number of Pages: 221
Institution: University of Pittsburgh
Schools and Programs: School of Medicine > Biomedical Informatics
Degree: PhD - Doctor of Philosophy
Thesis Type: Doctoral Dissertation
Refereed: Yes
Uncontrolled Keywords: Audit and feedback, eHealth, low-income countries, electronic medical records, HIV/AIDS, performance measurement, clinical practice guidelines, implementation science, learning healthcare systems, psychological theory, behavior change
Date Deposited: 24 Oct 2014 18:51
Last Modified: 19 Dec 2016 14:42
URI: http://d-scholarship.pitt.edu/id/eprint/23402

Metrics

Monthly Views for the past 3 years

Plum Analytics


Actions (login required)

View Item View Item