Study raises concerns about AI health-prediction models trained on unreliable datasets

🌐 Medical Xpress (IM) —
Study raises concerns about AI health-prediction models trained on unreliable datasets

AI Summary

Research raises concerns that some AI-based health prediction models for stroke and diabetes risk use datasets with unverifiable origins. The study led by QUT and AusHSI highlights reliability issues in datasets hosted on Kaggle, a popular AI resource platform.

Some AI models designed to predict stroke and diabetes risk may be based on datasets whose origins cannot be verified, according to new research. The study, published in BMC Medicine and led by researchers at QUT and the Australian Center for Health Services Innovation (AusHSI), examined two widely downloaded health datasets hosted on Kaggle, an online platform for sharing datasets and machine-learning resources, marketed as "the world's AI proving ground."

Health AI & Tech AI models health prediction stroke risk diabetes risk QUT AusHSI Kaggle dataset reliability

Read original source →