University of North Carolina at Chapel Hill

4 related articles

Lifetime Data Analysis Oct 15, 2026
Sampled on outcome, still predictable: a weighted gradient boosting machine matches Cox on uranium miner cancer data
In outcome-dependent sampling, covariates are collected for only part of the cohort, so standard survival models trained on the sampled data target a distribution that differs from the cohort. A gradient boosting machine carries the sampling weights into training and tuning, selecting iterations by a weighted integrated Brier score, and the weighted empirical risk is shown to converge to the corresponding integrated Brier risk. In simulations it outperformed the Cox model in high-dimensional and nonlinear settings, and on uranium miner cancer data the test C-index was 0.803 versus 0.801 for Cox.
In outcome-dependent sampling, covariates are collected for only part of the cohort, so standard survival models trained on the sampled data target a distribution that differs from the cohort. A gradient boosting machine carries the sampling weights into training and tuning, selecting iterations by a weighted integrated Brier score, and the weighted empirical risk is shown to converge to the corresponding integrated Brier risk. In simulations it outperformed the Cox model in high-dimensional and nonlinear settings, and on uranium miner cancer data the test C-index was 0.803 versus 0.801 for Cox.
University of North Carolina at Chapel Hill Boston University Haibo Zhou Jianwen Cai Haolin Li
发表出处待核验 Oct 1, 2026
A 45-member modified Delphi consensus: screen for eating disorders before GLP-1 receptor agonist prescribing, and generally avoid these agents in active anorexia and bulimia nervosa
Using a three-round modified Delphi method, a 45-member panel of clinicians and researchers in diabetes, obesity and/or eating disorders plus people with lived experience reached an average 91.7% consensus on recommendations for GLP-1 receptor agonist use in eating disorder contexts, covering pre-treatment screening, risk-stratified monitoring, standardized educational materials and concurrent evidence-based psychotherapy, stating that these agents should generally be avoided in active eating disorders, particularly anorexia nervosa, atypical anorexia nervosa and bulimia nervosa with marked dietary restraint and/or significant weight suppression, and setting out research priorities in epidemiology, regulation and binge eating disorder trials.
Using a three-round modified Delphi method, a 45-member panel of clinicians and researchers in diabetes, obesity and/or eating disorders plus people with lived experience reached an average 91.7% consensus on recommendations for GLP-1 receptor agonist use in eating disorder contexts, covering pre-treatment screening, risk-stratified monitoring, standardized educational materials and concurrent evidence-based psychotherapy, stating that these agents should generally be avoided in active eating disorders, particularly anorexia nervosa, atypical anorexia nervosa and bulimia nervosa with marked dietary restraint and/or significant weight suppression, and setting out research priorities in epidemiology, regulation and binge eating disorder trials.
NYU Langone Health University of Pennsylvania Sanford Research Johns Hopkins University University of North Carolina at Chapel Hill University of Virginia New York University University of Louisville Ashley White Monique Jericho Nami Trappenberg Kimberly D. Dennis Diane Alix Klein Anastasia Harris Susan L McElroy Brooke Langman
Modified Delphi Consensus GLP-1 Receptor Agonists in Eating Disorders
bioRxiv Sep 26, 2026
HANAMI predicts drug-gene-disease motifs with heterogeneous graph contrastive learning, improving up to about 6% over state-of-the-art baselines and holding an ~18% edge in zero-shot settings
The authors present HANAMI (Heterogeneous grAph coNtrastive leArning for drug-gene-disease Motif predIction), a multi-view deep graph learning framework that integrates heterogeneous biomedical knowledge such as chemical structures, genomic sequences, and clinical phenotypes and uses relation-aware topology encoding, structure-aware aggregation, and contrastive learning to predict drug-gene-disease motifs; systematic evaluation on benchmark datasets shows up to about 6% improvement over existing state-of-the-art methods in motif prediction, an approximately 18% performance advantage maintained in zero-shot settings involving previously unseen entities, and the ability to prioritize drug-disease relationships investigated in Phase II or III trials while identifying candidate genes suggestin
The authors present HANAMI (Heterogeneous grAph coNtrastive leArning for drug-gene-disease Motif predIction), a multi-view deep graph learning framework that integrates heterogeneous biomedical knowledge such as chemical structures, genomic sequences, and clinical phenotypes and uses relation-aware topology encoding, structure-aware aggregation, and contrastive learning to predict drug-gene-disease motifs; systematic evaluation on benchmark datasets shows up to about 6% improvement over existing state-of-the-art methods in motif prediction, an approximately 18% performance advantage maintained in zero-shot settings involving previously unseen entities, and the ability to prioritize drug-disease relationships investigated in Phase II or III trials while identifying candidate genes suggestin
The Ohio State University Wexner Medical Center The Ohio State University University of North Carolina at Chapel Hill Stony Brook University Hongsheng Xie Yuan Gao Can Chen Shanlin Ke
medRxiv Sep 14, 2026
CARDIAC-FM: A Generalizable Multimodal Foundation Model Integrating ECG and Cardiac MRI
This study developed CARDIAC-FM, a multimodal foundation model that integrates 12-lead ECG and cardiac MRI through self-supervised representation learning and cross-modal contrastive alignment, pretrained on 57,609 paired samples from UK Biobank, improving prediction of incident atrial fibrillation and heart failure, generalizing zero-shot to the Cardiovascular Health Study and the Multi-Ethnic Study of Atherosclerosis, and transferring to cardiac MRI phenotype prediction, time-to-event modelling, and additional outcomes including myocardial infarction, ischaemic stroke, cardiovascular death, and all-cause mortality.
This study developed CARDIAC-FM, a multimodal foundation model that integrates 12-lead ECG and cardiac MRI through self-supervised representation learning and cross-modal contrastive alignment, pretrained on 57,609 paired samples from UK Biobank, improving prediction of incident atrial fibrillation and heart failure, generalizing zero-shot to the Cardiovascular Health Study and the Multi-Ethnic Study of Atherosclerosis, and transferring to cardiac MRI phenotype prediction, time-to-event modelling, and additional outcomes including myocardial infarction, ischaemic stroke, cardiovascular death, and all-cause mortality.
University of Washington University of North Carolina at Chapel Hill University of California, San Francisco Bruce M Psaty Joshua C Bis W. T. Longstreth Bojun Chen James S Floyd Siting Li Yi Qian Ting Ye
Self-Supervised Learning Masked Autoencoder Pre-training Transformer Encoder Contrastive Learning Multimodal AI Framework Foundation Models External Validation

You’re all caught up

Sampled on outcome, still predictable: a weighted gradient boosting machine matches Cox on uranium miner cancer data

A 45-member modified Delphi consensus: screen for eating disorders before GLP-1 receptor agonist prescribing, and generally avoid these agents in active anorexia and bulimia nervosa

HANAMI predicts drug-gene-disease motifs with heterogeneous graph contrastive learning, improving up to about 6% over state-of-the-art baselines and holding an ~18% edge in zero-shot settings

CARDIAC-FM: A Generalizable Multimodal Foundation Model Integrating ECG and Cardiac MRI