Table 2.
Average identification and verification results for the GLOBAL cohort
| GLOBAL Cohort | EER | σ | AUC | σ | R1 | σ | R10 | σ | R20 | σ |
|---|---|---|---|---|---|---|---|---|---|---|
| SEX | 35.7 | 0.7 | 72.3 | 0.9 | 1.46 | 0.00 | 19.66 | 0.04 | 39.81 | 0.34 |
| GB | 31.1 | 0.9 | 77.3 | 0.4 | 4.61 | 2.63 | 36.41 | 1.96 | 56.55 | 1.61 |
| BMI | 37.1 | 0.8 | 67.6 | 0.9 | 1.34 | 0.21 | 18.08 | 0.52 | 35.80 | 0.86 |
| AGE | 39.4 | 0.7 | 66.8 | 2.1 | 1.46 | 0.00 | 19.66 | 0.04 | 38.23 | 1.02 |
| SEX + GB | 22 | 0.7 | 86.2 | 0.2 | 7.53 | 1.18 | 52.67 | 3.93 | 76.58 | 0.45 |
| SEX + GB + BMI | 20.8 | 0.8 | 87.5 | 0.4 | 8.86 | 2.01 | 58.62 | 1.20 | 79.98 | 0.98 |
| SEX + GB + BMI + AGE | 17.5 | 0.9 | 90.2 | 0.8 | 12.01 | 1.25 | 67.84 | 1.48 | 87.38 | 2.20 |
| X = [SEX, AGE, BMI, GB] | 19.8 | 1.5 | 88.2 | 0.9 | 11.65 | 1.80 | 65.66 | 2.09 | 84.10 | 1.11 |
The results for a DNA-to-Face prediction strategy from a set of predictors X are given in the last row. All values are given in percentage. Random performance is given as EER = 0.5, AUC = 0.5, R1 = 1%, R10 = 10%, R20 = 20%. % refers to the percentage of individuals in the gallery (n = 275, test dataset)
EER verification equal error rate, AUC verification area under the curve, R1 rank 1% identification rate, R10 rank 10% identification rate, R20 rank 20% identification rate, σ standard deviation, GB genomic background, BMI body mass index