Bibliographic record
Abstract
This editorial refers to the article ‘A streamlined CMR-derived machine-learning model for estimating cardiovascular biological age: development and validation in the UK-biobank and multi-ethnic study of atherosclerosis’, by P.-G. Masci et al., https://doi.org/10.1093/ehjci/jeaf337. Aging is a major risk factor for cardiovascular disease and represents an escalating public health challenge, especially as life expectancy continues to rise. People age at different rates due to the interplay between genetic risks, early life factors and later life exposures with growing interest in measuring biological aging and its modifiers. Different strategies are used to define aging and are referred to as generations of ‘aging clocks’. First-generation clocks train models to predict chronological age in normative groups, second-generation clocks predict onset of age-related outcomes, and third-generation clocks assess intra-individual rates of aging over time. Imaging provides organ specificity for assessing differential aging, and the calculation of a ‘predicted age-gap’ in neuroimaging pioneered analytic techniques for assessing progressive functional and anatomical changes in the brain.1 A similar concept has recently been applied to cardiovascular magnetic resonance (CMR) imaging in large populations such as the UK Biobank, training first-generation clocks to predict chronological age from various image-derived phenotypes. Radiomic features encoding geometric and textural information have been used to capture a cardiovascular age-gap, or ‘age-delta,’ and to examine this against modifiable exposures.2,3 A subsequent approach by Shah et al.4 used a range of volumetric, functional, and tissue-based traits derived from automated CMR analysis to identify genetic associations with cardiovascular age-delta, implicating regulation of sarcomere homeostasis, myocardial immunomodulation, and tissue responses to biophysical stress.4 Recently, combining whole-body imaging with cardiovascular age assessment has highlighted the pro-inflammatory role played by visceral fat in promoting aging.5
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.013 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.003 | 0.002 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.029 | 0.029 |
| Insufficient payload (model declined to judge) | 0.010 | 0.007 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".