Truace
Subscribe

A machine learning-derived aging index for risk stratification and mortality prediction in cardiovascular-kidney-metabolic syndrome: A retrospective cohort study

Background The cardiovascular‑kidney‑metabolic (CKM) syndrome shows substantial heterogeneity in progression, yet existing biological age indices are not tailored to CKM pathways. We developed an aging index (CKMAI) using machine learning and evaluated its predictive performance for mortality and high‑risk CKM status. Methods and findings We conducted a retrospective cohort study of 6,896 adults from the National Health and Nutrition Examination Survey (NHANES) 2005-2018, weighted for the US adult population. A…

By the Truvace desk2 min read1 sourcePeer-reviewedTRV-2026-1817· cite & verify
A machine learning-derived aging index for risk stratification and mortality prediction in cardiovascular-kidney-metabolic syndrome: A retrospective cohort study
"Plugged into dialysis" by newslighter is licensed under CC BY 2.0. To view a copy of this license, visit https://creativecommons.org/licenses/by/2.0/.

In brief

Researchers used machine learning to build an aging index tailored to cardiovascular-kidney-metabolic syndrome, called CKMAI. They screened more than 100 candidate survival models in 6,896 adults from NHANES 2005-2018 and picked a simple Cox model through Pareto front optimization.

The index may help clinicians stratify risk and target prevention in a condition whose progression varies widely between patients. The evidence is retrospective and comes mainly from one US survey, so its performance in independent populations and in routine care remains to be established.

Main points

  1. Time-dependent AUCs for all-cause mortality were 0.893 at 3 years, 0.907 at 5 years and 0.890 at 10 years.
  2. For cardiovascular mortality, AUCs reached 0.937 at both 5 and 10 years; the AUC for high-risk CKM status was 0.790.
  3. Clustering found six aging-metabolic phenotypes; the frail elderly cluster had a hazard ratio of 11.74 for mortality.
  4. Depression partially mediated the index-outcome links, from 5.6% for all-cause mortality to 11.1% for high-risk CKM status.

The gain

A machine-learning-derived CKM-specific aging index predicted all-cause and cardiovascular mortality and high-risk CKM status better than PhenoAge, KDM and the cardiometabolic index in a weighted US adult cohort.

The rundown

The study was a retrospective cohort analysis weighted to represent the US adult population. Performance was assessed with time-dependent AUC, net reclassification improvement, integrated discrimination improvement, calibration and decision curve analysis, and the authors report significant improvement at all time points and superior net benefit.

Nonlinear threshold analysis found inflection points at CKMAI values of 61.587 for all-cause mortality, 60.732 for cardiovascular mortality and 34.092 for high-risk CKM status, with steeper risk increases below each threshold. CKMAI also showed a super-additive interaction with PhenoAge (RERI 15.06).

The index draws on clinical laboratory measures, nutritional assessments, lifestyle factors and social determinants of health. The authors present it as a practical tool for risk stratification and targeted prevention in CKM syndrome.

Sources

  1. Peer-reviewedPLOS Medicine2026-10-06

The debate