Biological age estimation from DNA methylation and determination of relevant biomarkers is an active research problem which has predominantly been tackled with black-box penalized regression. Machine learning is used to select a small subset of features from hundreds of thousands of CpG probes and to increase generalizability typically lacking with ordinary least-squares regression. Here, we show that such feature selection lacks biological interpretability and relevance in the clocks of the first and next generations and clarify the logic by which these clocks systematically exclude biomarkers of aging and age-related disease.
View Article and Find Full Text PDFObjective: The purpose of this study was to determine whether gray matter volume and diffusion-based metrics in associated white matter changed in breachers who had neuroimaging performed at two timepoints. A secondary purpose was to compare these changes in a group who had a one-year interval between their imaging timepoints to a group that had a two-year interval between imaging.
Methods: Between timepoints, clusters with significantly different gray matter volume were used as seeds for reconstruction of associated structural networks using diffusion metrics.
Cancer Epidemiol Biomarkers Prev
November 2024
Background: Screening colonoscopy harms data are limited for adults ages 76-85 years.
Methods: We conducted a retrospective cohort study of screening colonoscopies vs. fecal immunochemical tests (FIT) and general population matched comparators aged 76-85 within 3 integrated healthcare systems (2010-2019).