Research: Specific Aims and GPT - yina/2025-catalyzing-health-promptathon GitHub Wiki
Tasks
Task | Goal | Prompt |
---|---|---|
Summarize | Summarize key points of the aims | This is a specific aims page from an NIH grant. What are it's key objectives? What is the significance of these objective? |
Classify | What type of study design is proposed? | What is the research study design proposed? |
Transform | Transform the aims page into a table with it's key components. | Convert this aims page into a table with the following sections – significance, design, methods, measures, analysis. |
Identify alternatives | Generate alternative designs | What would be alternative study designs to the one proposed? |
Classify | Classify what NIH study section this proposal should be sent to | Based on the specific aims, what NIH study section should this proposal be sent to? |
Transform | Transform the aims page into a general audience summary | Write a lay audience summary of this NIH specific aims page The language should be accessible to non-experts. Here is the specific aims page: “””xxx””” |
Specific Aims
Thank you for Dr. Mann from the https://med.nyu.edu/research/healthcare-innovation-bridging-research-informatics-design-lab/our-research.
1. Specific Aims
Healthcare information technology provides some of our most potent yet underutilized tools for containing
healthcare costs and improving quality. Clinical prediction rules are frontline decision aids that combine state-
of-the-art evidence with real-time patient history, physical examination, and laboratory data. While often well-
validated, this form of clinical decision support has been underutilized because of poor design and flawed
implementation that failed to take into account real-world practice and workflow. Integrating clinical prediction
rules into electronic health records (EHRs) holds great promise for realizing their potential, and our ongoing
AHRQ-funded project has demonstrated clear reductions in resource utilization in a single site.1 However, the
real challenge lies in disseminating our innovation – similar single-site demonstrations have rarely been
replicated in new settings with different workflows, in large part because of the diversity of EHR systems
among institutions but also because of inadequate attention to strategies for diffusing the innovation. Donald
Berwick summarized this challenge succinctly and accurately: “In health care, invention is hard, but
dissemination is even harder”.2
The proposed project seeks to generalize across diverse ambulatory settings the innovative platform we have
developed for using clinical prediction rules to integrate evidence directly into practice. We will determine if
and how primary care practitioners will use a well-designed, customized integrated clinical prediction rule
(iCPR) embedded within EHRs for two exemplar conditions, strep throat and pneumonia, and we will identify
the variations in uptake across several different primary care settings. The proposed study builds on the
success of our ongoing project demonstrating the feasibility, usability and efficacy of a novel iCPR tool; an
active clinical decision support that can launch from several locations in the typical provider workflow. We
observed that integrating our well-validated, highly usable clinical prediction rules into the EHR at the point of
care, in real time, greatly enhanced clinician use of iCPR and reduced antibiotic prescription and diagnostic
test ordering. The proposed project will draw on well-established implementation frameworks in order to
identify the factors influencing implementation and develop optimal strategies for diffusing iCPR across care
providers and care settings via the most widely used commercial EHR, with an emphasis on usability.
To achieve this goal, we have assembled a multi-disciplinary team of researchers, informaticians, clinicians
and programmers across three diverse clinical settings (academic, safety-net, community) to pursue the
following specific aims:
Specific Aim 1: Integrate our previously tested and refined iCPR tool for strep throat and pneumonia into the
same commercial EHR in three different clinical settings, adapting the innovation to provider preference,
culture, and workflow rather than imposing a rigidly standardized tool.
Hypothesis 1: iCPR can be successfully integrated into the same commercial EHR in diverse settings using
implementation tailoring techniques including rapid-cycle, low-cost usability and iterative refinement.
Specific Aim 2: Determine the rate and variability in iCPR utilization across different settings.
Hypothesis 2: iCPR will be adopted by providers differently depending on the site’s clinical setting, clinician
preferences, organizational culture, and other contextual factors, and the differences in uptake can be
identified and measured.
Specific Aim 3: Determine the impact of iCPR on antibiotic prescribing and diagnostic test-ordering patterns
across diverse clinical settings with a randomized controlled trial.
Hypothesis 3: Use of iCPRs will lead to an appropriate decrease in antibiotic use and diagnostic testing.
Specific Aim 4: Use a well-established theory-driven implementation framework to identify facilitators and
barriers to integration in each setting, and develop a toolkit for adapting and implementing the tool in diverse
settings.
Hypothesis 4: Facilitators and barriers to implementation can be systematically identified and synthesized
into a dissemination toolkit.
This proposal seeks to: 1) use innovative strategies to integrate the novel iCPR tool into the workflow of
diverse primary care settings; 2) induce substantial provider utilization of the tool and reductions in antibiotic
and diagnostic-test ordering similar to the single-site development trial; and 3) create a toolkit that includes the
iCPR programming and report generation code for customizing the implementation and dissemination process
at any site using this EHR platform in the nation. Achieving these objectives will create a scalable platform for
disseminating iCPR and other evidence-based tools via users of this highly penetrant commercial EHR and
encourage judicious use of critical healthcare resources across the U.S.