Related Experiment Video
Updated: Apr 13, 2026
05:21
Computerized Adaptive Testing System of Functional Assessment of Stroke
Published on: January 7, 2019
5.9K
A Better Way: Initial Acceptability Testing of Using Artificial Intelligence Tools to Accelerate Development of
Medrxiv : the Preprint Server for Health Sciences
|September 2, 2025
Summary
This study introduces a new 12-step approach using artificial intelligence (AI) to develop clinical guidance in 24 weeks, significantly reducing the typical 24-month timeline. Trauma community feedback highlighted the need for multidisciplinary input and user-friendly features for this accelerated process.
Area of Science:
- Medical Informatics
- Clinical Practice Guidelines
- Artificial Intelligence in Healthcare
Background:
- Current clinical guidance development is lengthy, often taking 1-2 years, leading to outdated recommendations and delayed evidence-informed practice.
- Existing clinical guidance development processes face challenges in efficiency and timeliness, necessitating innovative approaches.
Purpose of the Study:
- To test the initial acceptability of a novel 12-step approach designed to accelerate clinical guidance development from over 24 months to 24 weeks.
- To explore the potential of artificial intelligence (AI) tools in conjunction with subject matter experts (SMEs) to streamline guidance creation.
Main Methods:
- A 12-step approach was drafted using agile methodology and the PRISM framework, integrating AI for initial output and SME review.
- The approach was presented to trauma community stakeholders at the 2025 Design for Implementation conference for feedback.
- A post-conference survey assessed participant confidence in AI's role in accelerating guidance development.
Main Results:
- Participants provided recommendations for multidisciplinary involvement, resource-stratified recommendations, and user-friendly features (offline/multilingual access).
- 64% of surveyed participants (n=56) expressed confidence in AI's ability to accelerate the clinical guidance development process.
- The proposed 12-step approach aims to create bedside-ready clinical decision trees within a 24-week timeframe.
Conclusions:
- Significant opportunities exist to improve clinical guidance by enhancing collaboration, incorporating resource variability, and leveraging AI for expedited development.
- Further research is essential to validate the responsible integration of AI in clinical guidance to bridge the gap between evidence and practice.
- The initial acceptability of the 24-week, AI-assisted approach suggests a promising direction for more timely and effective clinical decision support.
