A framework for applied AI in Healthcare
This project examines barriers to implementing AI decision-aids in clinical care and proposes a framework and interface design to support adoption in healthcare settings.
Background
As technology advances and the use of artificial intelligence (AI) technology is adopted in various fields, there are increasing efforts to develop AI technology for healthcare applications to improve care delivery and patient outcomes. However, there are few examples of AI technology currently being used in clinical settings. Thus in the formation of this project, the team wanted to understand why this disparity exists. The objective of this project is to explore the challenges and considerations for implementing AI predictive technologies in clinical settings. To explore this problem space, the team surveyed the academic and grey literature, and consulted with subject-matter experts. With this broadened understanding, the current and desired states of the problem space were established and existing gaps defined. To further explore these gaps, a qualitative research study with primary stakeholders and user-centered design tools were used to frame the elements at play in the specific context of an AI risk prediction tool for use as a clinician decision-aid. Learnings from stakeholder perspectives were synthesized as the project entered its ideation phase, where a preliminary framework for implementing AI decision-aids into clinical setting was developed and a user interface for an example of an AI decision-aid was designed.
Project team
- Paige Gilbank
- Kaleigh Johnson-Cover
- Tran Truong
TRP supervisors
Project advisory committee
- Jennifer Bell
- Jennifer Jones
- Mike Carter
- Greg Jamieson
See our community directory for more on committee members.