A York University-led study identifies that continual and transfer learning strategies can mitigate harmful data shifts in clinical AI models used in hospitals.
Key Details
- 1Data shifts between training and real-world hospital data can cause patient harm and model unreliability.
- 2Researchers analyzed 143,049 patient encounters from seven hospitals in Toronto using the GEMINI data network.
- 3Significant data shifts were observed between community and academic hospitals, with transfer of models from community to academic settings leading to more harm.
- 4Transfer learning and drift-triggered continual learning approaches improved model robustness and prevented performance drops, especially during the COVID-19 pandemic.
- 5A label-agnostic monitoring pipeline was proposed to detect and address harmful data shifts for safe, equitable AI deployment.
Why It Matters
Data distribution changes are common in real-world clinical environments, often leading to AI model bias or inaccuracy. This research provides practical, evidence-based strategies for continuously monitoring and adapting clinical AI models, helping ensure safer and more robust radiology-AI deployment in hospital settings.
Source
EurekAlert
Related News
•EurekAlert
AI Model Improves Prediction of Knee Osteoarthritis Progression Using MRI and Biomarkers
A new AI-assisted model that combines MRI, biochemical, and clinical data improves predictions of worsening knee osteoarthritis.
•EurekAlert
Photonic Chip Enables Versatile Neural Networks for Imaging and Speech AI
Chinese scientists have developed a reconfigurable integrated photonic chip capable of running diverse neural networks, including those for image and speech processing, with high efficiency.
•EurekAlert
AI Model Predicts Multiple Genetic Markers from Colorectal Pathology Slides
Researchers developed and validated an AI model that simultaneously detects multiple genetic markers in colorectal cancer tissue slides.