Automated Tailoring of Clinical Performance Feedback in Low-Resource Settings

摘要: A patient-centered, continuously learning healthcare system is a compelling vision for the future of healthcare, introduced by Institute Medicine. key part this creation feedback loops to support continuous clinical and behavior change. Opportunities generate performance are increasing, due globally unprecedented growth in adoption eHealth. These opportunities especially promising low-income countries where critical problem poor providers that lowers quality care. Clinical audit feedback, defined as provision summaries providers, teams, organizations, widely used improvement implementation evidence-based practice. Evidence shows can significantly improve compliance with desired practice, but it unclear when how most effective. Psychological theories offer rigorously evaluated theoretical causal mechanisms may explain likely be effective change, these have rarely been inform design interventions. In addition uncertainty regarding effect on performance, challenge using eHealth data automate delivery understanding purpose measurement. To overcome dual challenges variable effectiveness, I propose novel, theory-informed approach generating feedback: automated message tailoring. This research explores evidence, theories, methods, settings establish foundation knowledge tailoring messages. developed applied within antiretroviral therapy clinics Malawi, Africa, an electronic medical record routinely used, understand potential impact low-resource settings. This work introduces novel information tool enable supervisors use existing provide more which testing hypotheses about tailored messages performance.