Deep learning predicts mortality from skin biopsy images

Researchers have developed a contrastive deep learning model capable of determining an individual's age solely from histopathological skin biopsy images. This model can also construct a novel biomarker of aging using visual features from these biopsies. When correlated with health registers, this biomarker has been shown to predict mortality and the prevalence of chronic age-related diseases, highlighting the potential of combining deep learning with routinely collected health data for improved health insights. AI

IMPACT This research demonstrates a novel application of deep learning for health insights, potentially leading to new diagnostic tools for aging and disease prediction.

RANK_REASON The cluster contains an academic paper detailing a new research methodology and findings. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• Contrastive Deep Learning
• Kaustubh Chakradeo

• paper
• model release
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →