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 Uses Routine Mammograms to Predict Women's Heart Disease Risk
AI can use mammograms to predict the risk of serious cardiovascular disease in women by quantifying breast arterial calcification.
•EurekAlert
Deep Learning Enables Virtual Multiplexed Immunostaining in Pathology
Researchers developed a deep learning framework for generating virtual immunostaining on label-free tissue to assess vascular invasion in thyroid cancer.
•EurekAlert
WPI Team Achieves 93% Accuracy in MRI-AI Alzheimer's Prediction
Worcester Polytechnic Institute developed a machine learning tool using MRI scans to predict Alzheimer’s disease with nearly 93% accuracy, uncovering significant age and sex differences in brain atrophy patterns.