Table 1 Comparing the AUROCs between an existing mortality score or a biological age as reported in the original paper and the IMPACT-20 model tested for the corresponding follow-up time and age ranges in the NHANES dataset.

From: Interpretable machine learning prediction of all-cause mortality

 

Task

Age

AUROC

AUROC of IMPACT-20

AUROC of IMPACT-20 (temporal validation)

Mortality risk scores

Intermountain6

1-year mortality

18 +

0.84

0.92

0.88

Gagne Index7

1-year mortality

65 +

0.79

0.85

0.85

Intermountain6

5-year mortality

18 +

0.87

0.89

0.88

Prognostic score5

5-year mortality

40–70

Male: 0.80

Male: 0.85

Male: 0.80

Female: 0.79

Female: 0.83

Female: 0.80

Schonberg Index8

5-year mortality

65 +

0.75

0.80

0.83

Biological ages

Horvath DNAm Age17,19

10-year mortality

21–84

0.56

0.90

0.89

Hannum DNAm Age18,19

10-year mortality

21–84

0.57

0.90

0.89

DNAm PhenoAge19

10-year mortality

21–84

0.62

0.90

0.89

Phenotypic Age19,67

10-year mortality

20–85

0.88

0.90

0.89

  1. The “AUROC” column shows the AUROCs reported in the original paper. The “AUROC of IMPACT-20” column shows the performance of IMPACT models trained with the selected top 20 features (Supplementary Tables 2 and 3). The “AUROC of IMPACT-20 (temporal validation)” column shows the performance of the IMPACT-20 models evaluated on the temporal validation set (Supplementary Methods).