PhenoAge is an aging clock derived from patient data on age-related changes in nine clinical chemistry markers that are easily measured via a blood sample. A number of other blood biomarker clocks have been proposed that use more markers. The clock noted here claims a modest improvement over PhenoAge when it comes to predicting mortality risk, but that requires 25 markers. The trade-off is in the cost to the patient to obtain the necessary assays versus the degree of improved performance of the clock. This tends to be true across clocks more generally, regardless of the data used. The more popular clocks based on fewer measures continue to be popular because they do not greatly underperform the more expensive clocks that require many more measures. The work here reproduces that result by showing that combining a subset of markers with the full data set produces much the same result as the full set of markers, which is an interesting approach to controlling patient costs.
Biological age captures physiological deterioration better than chronological age and is amenable to interventions. Blood-based biomarkers have been identified as suitable candidates for biological age estimation. This study aims to improve biological age estimation using machine learning models and a feature-set of 60 circulating biomarkers available from the UK Biobank (n = 306,116). We implement an Elastic-Net derived Cox model with 25 selected biomarkers to predict mortality risk (C-Index = 0.778), which outperforms the well-known blood-biomarker based PhenoAge model (C-Index = 0.750), providing a C-Index lift of 0.028 representing an 11% relative increase in predictive value.
Importantly, we then show that using common clinical assay panels, with few biomarkers, alongside imputation and the model derived on the full set of biomarkers, does not substantially degrade predictive accuracy from the theoretical maximum achievable for the available biomarkers. Biological age is estimated as the equivalent age within the same-sex population which corresponds to an individual's mortality risk. Values ranged between 20-years younger and 20-years older than individuals' chronological age, exposing the magnitude of ageing signals contained in blood markers. Thus, we demonstrate a practical and cost-efficient method of estimating an improved measure of biological age, available to the general population.
Link: https://doi.org/10.1038/s42003-023-05456-z
View the full article at FightAging
