A review reveals that only 13% of AI and health equity research articles explicitly define health equity, raising concerns about algorithmic bias.
Key Details
- 1Review included 166 articles on AI and health equity published before October 2026.
- 2Only 13% explicitly defined 'health equity' in the context of AI.
- 32% of articles specifically mentioned radiology as an area affected by AI and equity issues.
- 4Majority of papers (68%) did not focus on any specific health outcome or specialty.
- 570% of author teams were US-based, indicating a need for global perspectives.
- 6Diverse and interdisciplinary teams are recommended to reduce AI bias in healthcare.
Why It Matters
Health equity is a critical issue in applying AI in radiology, as vague definitions and biased algorithms can worsen disparities. Specialty-specific expertise is necessary to ensure that AI applications in imaging do not inadvertently disadvantage vulnerable populations.
Source
EurekAlert
Related News
•EurekAlert
Quantum Machine Learning Shows Promise for Lung Cancer Prediction with Limited Data
FAU researchers demonstrate quantum machine learning can accurately predict lung cancer from sparse clinical data sets.
•EurekAlert
AI-Guided Heart Ultrasound Enables Quality Rural Scans by Non-Experts
AI software enabled non-sonographer health professionals to successfully perform quality echocardiograms in rural U.S. communities, with scans reviewed by off-site experts.
•EurekAlert
UVA's $4M NIH Grant Backs AI to Optimize Cardiac MRI Therapies
UVA secures $4 million NIH funding to develop GenStrain, an AI model using MRI data to personalize cardiac pacing therapies.