Table 2 Performance of the algorithm stratified per age category on person level.
From: Age and sex affect deep learning prediction of cardiometabolic risk factors from retinal images
<=30 years | >30 and <=39 years | >39 and <=50 years | >50 years | Total | |
|---|---|---|---|---|---|
Sex (% male) | 0.99 | 0.96 | 0.98 | 0.97 | 0.97 |
Systolic blood pressure (mmHg) | 0.24 | 0.23 | 0.30 | 0.04 | 0.40 |
Diastolic blood pressure (mmHg) | 0.16 | 0.16 | 0.21 | 0.21 | 0.24 |
Haemoglobin A1c (%) | −0.14 | 0.28 | 0.24 | 0.06 | 0.34 |
Relative fat mass value | 0.29 | 0.33 | 0.33 | 0.47 | 0.43 |
Testosterone (nmol/L) | 0.61 | 0.57 | 0.45 | 0.50 | 0.54 |
