Table 4.
Geriatric hospital – fairness ratios (false negative rate and false discovery rate) relative to the reference groups, female for sex and 80-90 years for age, are assessed using the 80% rule, where values within (0.8-1.25) are fair. Median false negative rate and false discovery rate ratio scores and 90% CI (5th and 95th percentiles): Sex – the artificial intelligence model is fair – achieves both equal opportunity (false negative rate ratio) and predictive parity (false discovery rate ratio). Age range – in comparison to the reference group (80-90 y), the artificial intelligence model is fair for all patients aged 60-70 y, 70-80 y, and 90-100 y, but not fair for patients aged 100-110 y.
| Feature and group | FNRa ratio (90% CI) | FDRb ratio (90% CI) | |
| Sex |
|
|
|
|
|
Male | 0.870 (0.687-0.980) | 0.912 (0.858-0.981) |
|
|
Femalec | 1.000 (1.000-1.000) | 1.000 (1.000-1.000) |
| Age range (y) |
|
|
|
|
|
60-70 | 1.103 (1.058-1.368) | 0.915 (0.688-1.177) |
|
|
70-80 | 1.140 (1.045-1.206) | 1.035 (0.979-1.132) |
|
|
80-90c | 1.000 (1.000-1.000) | 1.000 (1.000-1.000) |
|
|
90-100 | 1.048 (1.014-1.116) | 1.129 (0.966-1.185) |
|
|
100-110 | 1.593 (1.482-1.699) | 1.619 (1.547-1.784) |
aFNR: false negative rate.
bFDR: false discovery rate.
cReference group.