config.json

{
 "approved_by_author": "\u231b",
 "citation": "Fong, Sheng, et al. \"LinAge2: providing actionable insights and benchmarking with epigenetic clocks.\" npj Aging 11.1 (2025): 29.",
 "citations": 6,
 "citations_date": "2026-08-20",
 "clock_name": "linage2",
 "data_type": "clinical biomarkers",
 "doi": "https://doi.org/10.1038/s41514-025-00221-4",
 "journal": "npj Aging",
 "last_author": "Jan Gruber",
 "model_type": "PCA + Cox regression",
 "n_features": 85,
 "notes": "Principal-component clinical clock trained on 20-year mortality in the NHANES IV 1999-2000 wave and tested in the 2001-2002 wave. The 59 model features are log transformed where the reference specifies, robustly z-scored by sex against a healthy 40-50 year old NHANES reference, and folded at 6 MAD-scaled units; the folded vector is projected onto sex-specific singular vectors and scored by a sex-specific Cox model, so male and female samples run through entirely separate parameter sets. Chronological age is supplied in years and enters the Cox terms in months, where it is a genuine covariate rather than a cancelling offset. Sex is coded female = 1 and male = 0; a dataset with no female column scores every sample with the male parameters. C-reactive protein is supplied raw in mg/dL and takes a plain natural log with no floor, so a reading below detection coded as 0 folds to the -6 cap instead of being clamped the way the BioAge clocks clamp it. The input contract is wider than the 59 model features: total cholesterol, HDL cholesterol and triglycerides are consumed only by the Friedewald LDL and are not features themselves, and 26 questionnaire codes feed the comorbidity, self-reported-health and healthcare-use indices. An absent questionnaire block is the main hazard and it biases the estimate downward. The substituted values are the reference cohort's median profile everywhere except the comorbidity index: answering no to all 22 conditions gives 0 where the cohort's median is 1/22, so that one feature is substituted marginally healthier than the median. It costs almost nothing, because the index's entire 0 to 1 range moves the estimate by only 0.06 years. The self-reported-health index is what does the damage: its substitute of good, unchanged health is exactly the cohort median, and a subject who would have reported poor and worsening health reads about 5.3 years younger than they should. The healthcare-use index is the raw NHANES 1999-2000 HUQ050 code (0 = none, 1 = 1, 2 = 2 to 3, 3 = 4 to 9, 4 = 10 to 12, 5 = 13 or more visits), so its valid range is 0 to 5 and the fold at 6 never fires on it; the 0 to 8 HUQ051 scale of later NHANES cycles must be collapsed onto it first (3 to 5 -> 3, 6 -> 4, 7 and 8 -> 5) or healthcare use is overstated. Substituting its median code of 2 for a subject who made 13 or more visits moves the male estimate up by about 0.35 years and the female estimate down by about 1.9 years. An absent lipid panel substitutes a total cholesterol chosen so that the derived LDL lands on the reference median, avoiding the reference implementation's hard 0 mmol/L substitution; a NaN inside a lipid column that is present still takes that hard 0 path and lowers the estimate by roughly 0.35 years. The range check cannot see this at all: it resolves ranges over the clock's declared input features, and the comorbidity, self-reported-health and healthcare-use indices are derived inside the model rather than supplied, so no range check ever applies to them. Heed the missing-feature warning the prediction pipeline emits; for this clock it is the only signal that the questionnaire block was absent.",
 "platform": [
  "clinical laboratory assays"
 ],
 "population": "adults",
 "postprocess": "linage2",
 "predicts": [
  "biological age"
 ],
 "reference_values": true,
 "research_only": null,
 "species": "Homo sapiens",
 "tissue": [
  "blood",
  "urine"
 ],
 "training_target": [
  "mortality"
 ],
 "unit": [
  "years"
 ],
 "version": "0.5.0",
 "year": 2025
}