Model performance
1 paper1 finding
Upstream
1Diverse populations
downin humans1
1 study
Diverse populations
downin humans1
Diverse populations decrease model performance in humans.
“current models underperform in diverse populations”
Review
Toward equitable biomarkers of aging: rethinking methylation clocks
Trends in genetics : TIG18 Jun 2025
Latest
320 in 12 monthsFrontiers in Medicine
Multistage CBAM-enhanced deep learning for three-class classification of radiographically derived bone mass status labels on knee radiographs
Computational studyBiomarkers
BJOG
Prediction of 10-Year Incident Hypertension After Pregnancy: A Population-Based Cohort Study
Cohort study of 28,234 peopleHypertension
arXiv
Task-Centric Multimodal Learning for Cognitive Impairment Detection
Preprint: cross-sectional study in peopleMild cognitive impairment
PLOS Digital Health
Demographic subgroup-aware analysis of blood pressure predictive models
Study in peopleDiastolic blood pressure
Cancer Epidemiology, Biomarkers & Prevention
Machine Learning Identifies Community-Level Factors Associated with Lung Cancer Incidence
Cross-sectional study of 542 peopleLung cancer
BMC Geriatrics
Development and validation of a machine learning model for screening individuals at high risk of self-reported osteoporosis among community-dwelling older adults: a cross-sectional study
Cross-sectional study of 1,896 peopleOsteoporosis
Journal of the American Heart Association
Lipoprotein(a) and Coronary Artery Disease Polygenic Risk Scores Do Not Improve Secondary Manifestations of Arterial Disease Score Prediction of Coronary Events After Ischemic Stroke
Cohort study of 1,202 peopleLipoprotein
Frontiers in Medicine
Explainable deep learning reveals a stagewise temporal deterioration from skin tone to contour to texture in Chinese women's skin aging
Cross-sectional study of 300 peopleBiomarkers
Frontiers in Endocrinology
Development of a predictive model for pancreatic cancer integrating serum metabolomics and polygenic risk score
Cohort study of 157,235 peoplePolygenic risk score