Imaging-based biological age gap and risk of mortality and incident diseases: a systematic review and meta-analysis
Abstract Artificial intelligence-derived imaging ageing clocks enable estimation of biological ageing from medical images. Yet meta-analytic quantification of the associations between imaging age gaps and both mortality and incident age-related diseases across multiple organs remains lacking. This study synthesised 40 eligible reports, of which 21 contributed to the meta-analysis. Meta-analyses showed that each 5-year increase in imaging age gap was associated with a higher hazard of all-cause mortality (HR 1.31, 95% CI 1.19–1.44), although heterogeneity was substantial ( I ² = 96.3%), with organ type and sample size contributing to heterogeneity. For cancer-specific mortality, the pooled HR was 1.06 (95% CI 0.96–1.18). Higher imaging age gaps were associated with incident dementia, stroke, heart failure, diabetes and hypertension, but not Parkinson’s disease. Imaging age gaps may support non-invasive risk stratification and long-term health management, but clinical translation requires standardisation, diverse external validation, interpretability, and evidence of clinical utility and equity.
Authors
- Shuangyu Li (ORCID: https://orcid.org/0000-0002-8651-1148)
- Juan Su (ORCID: https://orcid.org/0000-0002-1887-3622)
- 沙宪政
- Huan Wang (ORCID: https://orcid.org/0000-0002-1845-0179)
- Boyi Wang
- Xiran Jiang
- Lijun Jin
- Enuo CUI
- Danyang Zhang
- Yan Zhang
- Wei Li
Publication Details
- Journal
- npj Digital Medicine
- Published
- 2026-11-19
- DOI
- https://doi.org/10.1038/s41746-026-03472-x
- Primary Topic
- Frailty in Older Adults
- Type
- article
- Field-Weighted Citation Impact
- 0.00