Biologically inspired features, with manifold learning, were used to represent faces for ethnicity estimation demonstrating their robustness and high ethnicity classification accuracies within same-gender and same-age groups.
This high ethnicity-related variability can greatly complicate the interpretation of disease-associated studies, especially those conducted in multi-ethnic societies.
Of the ADA high-risk factors, only high-risk ethnicity was not associated with higher frequency of diabetes screening after adjustment for patient and visit characteristics (OR 0.90 [95% CI 0.76 1.08]) (Table 2).
Most significantly, this analysis demonstrated that high-risk ethnicity patients, despite higher frequency of clinic visits, are not more likely to be screened compared with nonminority patients with similar risk factors, which is inconsistent with current diabetes screening guidelines.
Overall uptake of screening before 26 weeks' gestation was similar in northern Europeans and in women of "higher risk" ethnicity.
In adjusted analyses, however, women of higher risk ethnicity had a shorter delay from the visits for pregnancy confirmation to testing: the mean difference from northern Europeans was about 7.4 days (95% confidence interval 2.5 to 12.3).
· High-risk ethnicity (African American, Hispanic or Latino).
Of the 15,557 eligible patients, 607 (4%) were of high-risk ethnicity, 61% were female, and 86% were ≥45 years of age.
In overweight patients <45 years, where screening eligibility is based on having an additional risk factor, high-risk ethnicity (OR 1.01 [0.70–1.44]) was not associated with increased screening frequency.
A total of 10,586 (68%) of all eligible patients and 361 (59%) of eligible high-risk ethnicity patients were screened using FPG, GTT, or HbA1c.
