AI models for cancer pathology often rely on shortcut correlations rather than detecting true biological signals, compromising reliability.
Key Details
- 1University of Warwick research analyzed 8,000+ patient samples across four cancer types using deep learning pathology models.
- 2Findings show many models predict biomarkers based on confounded visual cues, not causal biological features.
- 3AI models' headline accuracy can drop markedly when evaluated in stratified subgroups controlling for confounding factors.
- 4Reported accuracy for AI (just over 80%) was only modestly better than using tumour grade alone (~75%), already assessed by pathologists.
- 5Authors stress need for bias-aware evaluation and subgroup testing to prevent premature and unsafe clinical deployment.
Why It Matters
This research underscores significant risks of overrelying on AI diagnostic tools that may not generalize well in real-world settings. Robustness, causal modeling, and rigorous validation standards are essential before AI can safely supplement or replace human expertise in pathology and radiology.
Source
EurekAlert
Related News
•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.
•EurekAlert
Machine Learning Models Predict Cancer Risk with Routine Health Data
Researchers developed machine learning models using routinely collected health data to predict individual risk for 20 common cancers, outperforming traditional methods for several cancer types.
•EurekAlert
Duke Receives $25M to Lead National Trustworthy AI Hub for Dementia and Aging
Duke University has launched a $25 million national center to make AI for aging and dementia clinically robust and trustworthy.