Researchers have developed a method to map demographic information from routine clinical histopathology images. By analyzing 1.3 million whole-slide images from over 250,000 patients across 25 organs, they utilized pathology foundation models and multiple-instance learning to identify signals associated with sex, age group, and self-reported race. The study found that demographic attributes were broadly recoverable across organs, with AUROCs for sex, age group, and race averaging 0.828, 0.733, and 0.662, respectively. These findings offer a comprehensive map of demographic information within histopathology, aiding in the understanding of its origins and the development of more interpretable computational pathology models. AI
IMPACT This research could lead to more interpretable AI models in healthcare and highlight potential biases in medical data.
RANK_REASON Academic paper detailing a new computational method and its application. [lever_c_demoted from research: ic=1 ai=1.0]
- alphaXiv
- arXivLabs
- AUROCs
- CatalyzeX Code Finder for Papers
- Computational Pathology
- Computer vision and pattern recognition
- DagsHub
- Gotit.pub
- H&E stain
- Histomorphological basis of articular cartilage destruction in rheumatoid arthritis
- Hugging Face
- Multiple instance learning
- ScienceCast
- Whole slide images for primary diagnostics in dermatopathology: a feasibility study.
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
