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
Chinese Researchers Unveil Photonic Chip for Ultra-Fast Image Processing
A new photonic chip achieves image processing at 25 million frames per second with high energy efficiency, promising major advances in real-time imaging and AI applications.
•EurekAlert
AI Model Predicts Growth Spurts from Pediatric Neck X-rays for Orthodontics
Korean researchers developed an AI system (ARNet-v2) that predicts children's growth spurts from neck X-rays to enhance orthodontic treatment planning.
•EurekAlert
Dana-Farber Showcases AI and Clinical Trial Advances at ESMO 2025
Dana-Farber researchers present major cancer clinical trial results, including AI-driven data analysis, at ESMO Congress 2025.