Table 4 Hazard Ratios for normal ECGs.

From: Deep neural network-estimated electrocardiographic age as a mortality predictor

 

CODE-15% (n = 80,679)

ELSA-Brasil (n = 7,691)

 

HR (CI 95%)

p value

HR (CI 95%)

p value

Adjusted by age and sex

 ECG-age < age−8 years

0.66 (0.57–0.76)

<0.001

0.91 (0.68–1.21)

0.502

 ECG-age > age+8 years

1.53 (1.30–1.80)

<0.001

1.63 (1.00–2.66)

0.050

Adjusted by age, sex, hypertension, diabetes mellitus, and smoking

 ECG-age < age−8 years

0.66 (0.57–0.76)

<0.001

1.00 (0.75–1.33)

0.990

 ECG-age > age+8 years

1.52 (1.29–1.79)

<0.001

1.49 (0.91–2.43)

0.114

Adjusted by age, sex, hypertension, diabetes mellitus, smoking, and dyslipidemia

 ECG-age < age−8 years

0.66 (0.57–0.76)

<0.001

1.00 (0.75–1.33)

0.990

 ECG-age > age+8 years

1.52 (1.29–1.79)

<0.001

1.49 (0.91–2.43)

0.114

Adjusted by age, sex, hypertension, diabetes mellitus, smoking, dyslipidemia, and obesity

 ECG-age < age−8 years

Not available

1.00 (0.75–1.33)

0.992

 ECG-age > age+8 years

1.42 (0.86–2.35)

0.171

  1. The table displays, for patients with a normal ECG, the hazard ratios (HR) according to the differences between ECG-age and chronological age. The HR summarizes the Cox regression models obtained for overall mortality. The models were adjusted by different selection of variables (including age, sex, and cardiovascular risk factors).
  2. The number of events was n = 1074 for CODE-15% and n = 228 for ELSA-Brasil. The number of events when ECG-age is more than 8 years smaller than the chronological age there were, n = 249 and n = 105 for CODE-15% and ELSA-Brasil, respectively. Considering ECG-age is more than 8 years greater than the chronological age there were n = 203 and n = 19 events for CODE-15% and ELSA-Brasil, respectively.
Back to article page