latent-profile-analysis-sleep-patterns-their-association-with

Latent Profile Analysis of Sleep Patterns and their Association with Physical Activity Levels Among Chinese College Students

This cross-sectional study aimed to identify latent profiles of sleep patterns among college students and examine their associations with physical ...

Central South University

Alzheimer's disease (AD) etiology is complex, influenced by demographic risk factors such as age, sex, and educational level, alongside multi-omics factors derived from genomics, transcriptomics, and epigenomics. Advancements in multi-omics technology present both challenges and opportunities for AD diagnosis, enabling a more comprehensive understanding of the complex interactions among contributing factors, with the goal of improving diagnostic accuracy. To address this challenge, we propose a novel feature fusion approach in this study, AD-GCN, which integrates multi-omics data and their interaction networks to achieve more precise diagnosis and analysis of AD. In this study, we applied polygenic risk score and random forest algorithms for feature selection on genetic variation and methylation data. We then developed an AD-GCN for both multi-omics and single-omics classification tasks and compared its performance with that of machine learning ensemble methods. The experimental results demonstrated that multi-omics classification significantly outperformed single-omics classification, with AD-GCN surpassing the machine-learning ensembles. These findings highlight AD-GCN's strong potential to enhance AD diagnosis and improve accuracy in differentiating disease stages by integrating interactions across omics data, laying a solid foundation for the development of more precise and personalized AD diagnostic models.

AD-GCN: A novel graph convolutional network integrating multi-omics data for enhanced Alzheimer's disease diagnosis.

To investigate ethnic differences inprogression from prediabetes to diabetes in a multi-ethnic community, and develop prediction models for diabetes risk and glycemic progression. This 4.7-year retrospective cohort included 4,726 non-diabetic Han, Yi, and Dai individuals. Cox regression was used to analyze the cumulative incidence of diabetes. Two prediction models were developed and validated: a diabetes risk model and GlycoStep, a model for glycemic progression. Prediabetes was significantly associated with diabetes development (HR = 2.25). Over 4.7 years, the cumulative diabetes incidence was 12.7% in the prediabetes group versus 5.5% in normoglycemic individuals. The Yi had the highest incidence, followed by Han and Dai. The diabetes risk model achieved a C-index of 0.76 and AUCs of 0.65-0.80 over 2-4 years, demonstrating effective predictive performance. Similarly, the GlycoStep model exhibited strong predictive ability (C-index: 0.66; AUC range: 0.68-0.77), with ethnic-specific variations. These findings highlight ethnic disparities in diabetes progression and support individualized prevention strategies in multi-ethnic communities.

Article	Year
AD-GCN: A novel graph convolutional network integrating multi-omics data for enhanced Alzheimer's disease diagnosis. PloS one\| PubMed ID: 40455746	2025
A retrospective cohort study identifies differential diabetes progression among Han, Dai, and Yi groups in Yunnan. iScience\| PubMed ID: 41852728	2026

Wei Luo

Biography

JoVE Journal Publications

Other Publications