Proposed method predicts vascular biological age using relative individual risk difference
The abstract proposes a method for predicting vascular biological age from arteriosclerosis detection data, adding a new index called relative individual risk difference (RIRD) to capture individual differences in aging. In the reported comparison, corrected vascular biological age performed comparably to the Klemera-Doubal method in detecting non-healthy individuals and better than uncorrected vascular biological age. [1]
Automatic summary · not editorially reviewed
The key findings
The abstract states there is no gold standard for biological age, so existing studies usually use chronological age as the training label for supervised artificial intelligence models. [1]
The proposed relative individual risk difference is defined as the difference between an individual's vascular biological age and the mean vascular biological age of the health group. [1]
The corrected vascular biological age showed comparable ability to the Klemera-Doubal method in detecting non-healthy individuals and outperformed the uncorrected vascular biological age. [1]
The source at a glance
- Study type / format
- Methodological modeling study (abstract)
- Population / context
- Healthy population and non-healthy individuals in a vascular biological age modeling study, as described in the abstract.
- Summary based on
- Study abstract
- Original publication
- June 25, 2026
Why chronological age labels fall short
The abstract states that there is no gold standard for biological age (BA). Existing studies therefore usually use chronological age (CA) as the training label when building BA prediction models with supervised artificial intelligence algorithms. However, CA cannot reflect individual differences in aging, which the authors link to the frequently observed age delta correlation (ADC) phenomenon.
Supporting source [1]
Proposed RIRD index and corrected vascular age
The work proposes a new method for predicting vascular biological age using arteriosclerosis detection data. It introduces the relative individual risk difference (RIRD) to quantify individual differences in aging. RIRD is defined as the difference between an individual's vascular biological age and the mean vascular biological age of the health group. Based on RIRD, an approximate absolute health group is selected from the healthy population; this group is used to build a supervised regression model for vascular biological age prediction and to obtain a corrected vascular biological age.
Supporting source [1]
Comparison with Klemera-Doubal and ADC bias
Compared with the widely used Klemera-Doubal method (KDM), the corrected vascular biological age showed comparable ability to detect non-healthy individuals and outperformed the uncorrected vascular biological age. Vascular biological age without considering RIRD showed a significant ADC phenomenon, whereas both the corrected vascular biological age and KDM effectively eliminated this bias. The authors conclude that CA and individual differences in aging are two indispensable components of BA and that individual aging heterogeneity should be incorporated when building BA prediction models with supervised artificial intelligence algorithms.
Supporting source [1]
How to interpret this
This is an abstract; the full text was not reviewed. The abstract reports no sample size, follow-up, study design details or numerical performance values, and the method is proposed rather than validated. The comparison concerns detection of non-healthy individuals, not prediction of disease or lifespan.
Based on the study abstract; the full paper, tables and supplementary data were not reviewed.
Source & supporting passages
Tang Q, Ding P, Dai G, Liu S, Zhang L, Hu X, Cui J, Su B, Xu J, An H, Peng Y. · europepmc.org · June 25, 2026