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 Repurposes Routine CT Scans for Osteoporosis Detection
AI algorithms can extract bone density data from routine CT scans to identify osteoporosis, enabling opportunistic screening.
•EurekAlert
AI Method Automates X-ray Absorption Spectroscopy for Material Analysis
Researchers have developed an AI-based approach to automate and enhance the analysis of X-ray absorption spectroscopy (XAS) data for materials science.
•EurekAlert
Zero-Cost EHR-Based AI Tool Scales Dementia Detection in Primary Care
A zero-cost, EHR-integrated AI tool significantly boosts dementia detection in primary care clinics without adding clinician workload.