Related Experiment Video
Updated: Jun 15, 2025
03:14
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
525
Community-engaged artificial intelligence research: A scoping review
Tyler J Loftus1,2, Jeremy A Balch1,2, Kenneth L Abbott2
1University of Florida Intelligent Clinical Care Center, Gainesville, Florida, United States of America.
PLOS Digital Health
|August 23, 2024
Summary
Community engagement in artificial intelligence healthcare research is rare, with only 0.2% of studies involving community stakeholders. Engaging communities can improve AI model generalizability and clinical application quality.
Area of Science:
- Artificial Intelligence in Healthcare
- Community-Engaged Research
- Health Informatics
Background:
- Community settings are central to healthcare delivery, yet their involvement in artificial intelligence (AI) research is poorly understood.
- Engaging communities offers a significant opportunity to enhance the scientific quality and relevance of AI healthcare applications.
- A systematic scoping review is needed to map current knowledge and identify gaps in community-engaged AI research.
Purpose of the Study:
- To systematically map the landscape of community-engaged artificial intelligence (AI) healthcare research.
- To identify opportunities for optimizing the generalizability of AI applications through community involvement.
- To understand the role of community stakeholders and data throughout AI model development, validation, and implementation.
Main Methods:
- A systematic scoping review of Embase, PubMed, and MEDLINE databases.
- Searched for articles on AI/machine learning healthcare applications involving community engagement in model development, validation, or implementation.
- Data extracted on model performance, community engagement nature, and barriers/facilitators, adhering to PRISMA extension for Scoping Reviews guidelines.
Main Results:
- Only 21 out of ~10,880 AI healthcare articles (0.2%) described community involvement.
- All studies utilized community-derived data, often from existing datasets or internet-based acquisition.
- Community stakeholder involvement in design was minimal (one study); small sample sizes were a primary barrier (53% of studies), risking overfitting and threatening generalizability.
Conclusions:
- Community engagement in AI healthcare application development, validation, and implementation is notably infrequent.
- To enhance generalizability, researchers should involve community stakeholders in user-centered design, usability, and clinical implementation.
- Leveraging community data and stakeholder input is crucial for developing AI tools that are effective and relevant in real-world healthcare settings.
Related Concept Videos
01:56Ethics in Research
22.9K
Today, scientists agree that good research is ethical in nature and is guided by a basic respect for human dignity and safety. However, this has not always been the case. Modern researchers must demonstrate that the research they perform is ethically sound.
22.9K
02:16Stereotype Content Model
14.0K
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...
14.0K
01:27Intelligence
7.3K
The term "intelligence" is complex because it refers to both behavior and individuals, and its interpretation varies across cultures. European Americans tend to link intelligence with reasoning and cognitive skills, while in Kenya, it is tied to responsible participation in family and social life. In Uganda, intelligence is seen as the ability to know the right actions and carry them out effectively, while the Iatmul people of Papua New Guinea associate it with the capacity to remember...
7.3K