From: Use of machine learning techniques to identify HIV predictors for screening in sub-Saharan Africa
Characteristics | Levels | Overall | HIV Positive | HIV Negative |
---|---|---|---|---|
n (Total number of individuals,%) | 87,044 | 9,533 (11.0) | 77,511 (89.0) | |
Gender, n (%) | Males | 41,939 | 3,552 (8.5) | 38,387 (91.5) |
 | Females | 45,105 | 5,981 (13.3) | 39,124 (86.7) |
Country, n (%) | Malawi | 19,829 | 2,100 (10.6) | 17,729 (89.4) |
 | Eswatini | 11,875 | 3,230 (27.2) | 8,645 (72.8) |
 | Zambia | 21,280 | 2,569 (12.1) | 18,711 (87.9) |
 | Tanzania | 34,060 | 1,634 (4.8) | 32,426 (95.2) |