An unbiased comparison of 14 epigenetic clocks in relation to 10-year onset of 174 disease outcomes in 18,859 individuals.
Mavrommatis, C.; Belsky, D.; Ying, K.; Moqri, M.; Campbell, A.; Richmond, A.; Gladyshev, V.; Chandra, T.; McCartney, D.; Marioni, R.
Show abstract
Epigenetic Clocks have been trained to predict chronological age, healthspan and lifespan. Such clocks are often analysed in relation to disease outcomes - typically using small datasets and a limited number of clocks. Here, we present the first large-scale (n=18,849), unbiased comparison of 14 widely used clocks as predictors of 174 incident disease outcomes and all-cause mortality. Second-generation clocks significantly outperformed first-generation clocks, which have limited applications in disease settings. Of the 176 Bonferroni significant (P<0.05/174) associations, there were 27 diseases (including primary lung cancer and diabetes) where the hazard ratio for the clock exceeded the clocks association with all-cause mortality. Furthermore, there were 35 instances where adding a clock to a null classification model with traditional risk factors increased the classification accuracy by >1% with an AUCfull > 0.80. Second-generation epigenetic clocks show promise for disease risk prediction, particularly in relation to respiratory and liver-based conditions.
Matching journals
The top 8 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Epigenetic clocks predict prevalence and incidence of leading causes of death and disease burden 97%
- DNAm scores for serum GDF15 and NT-proBNP levels associate with a range of traits affecting the body and brain 95%
- Genetic and Environmental Contributions to Epigenetic Aging Across Adolescence and Young Adulthood 94%
Similar papers in this journal
- Exploring domains, clinical implications and environmental associations of a deep learning marker of biological ageing 95%
- Association between cancer and dementia risk in the UK Biobank: evidence of diagnostic bias 92%
- Circulating insulin-like growth factor-I and risk of 25 common conditions: outcome-wide analyses in the UK Biobank Study 91%
Similar papers in this journal
- COVID-19 inequalities in England: a mathematical modelling study of transmission risk and clinical vulnerability by socioeconomic status 91%
- Unveiling the Epigenetic Impact of Vegan vs. Omnivorous Diets on Aging: Insights from the Twins Nutrition Study (TwiNS) 91%
- Genome-wide analysis of blood lipid metabolites in over 5,000 South Asians reveals biological insights at cardiometabolic disease loci 90%
Similar papers in this journal
- Associations of four biological age markers with child development: A multi-omic analysis in the European HELIX cohort 95%
- An integrative study of five biological clocks in somatic and mental health 95%
- A mathematical model that predicts human biological age from physiological traits identifies environmental and genetic factors that influence aging 93%
Similar papers in this journal
- A unified framework for estimating country-specific cumulative incidence for 18 diseases stratified by polygenic risk 95%
- The Genomic Loci of Specific Human tRNA Genes Exhibit Ageing-Related DNA Hypermethylation 94%
- Using deep learning to predict age from liver and pancreas magnetic resonance images allows the identification of genetic and non-genetic factors associated with abdominal aging 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.