Table 2.
Univariate difference between training sample and validation sample
| Variables | Cohort | |
|---|---|---|
| Training | Validation | |
| N = 2796411 | N = 1198461 | |
| Mothers’ Age (%) | ||
| ≤ 24 Years | 794486 (28.41) | 341018 (28.45) |
| 25-29 Years | 803113 (28.72) | 344361 (28.73) |
| 30-34 Years | 758087 (27.11) | 325266 (27.14) |
| ≥ 35 Years | 440725 (15.76) | 187816 (15.67) |
| Mothers’ Nativity (%) | ||
| Born in U.S. | 2172903 (77.70) | 931206 (77.70) |
| Born Outside U.S. /Unknown/Not Stated | 623508 (22.30) | 267255 (22.30) |
| Mothers’ Race (%) | ||
| White | 2119115 (75.78) | 907536 (75.73) |
| Black | 447972 (16.02) | 192503 (16.06) |
| American Indian/Alaskan Native/Asian or Pacific Islander | 229324 (8.20) | 98422 (8.21) |
| Mothers’ Hispanic Origin (%) | ||
| Non-Hispanic/Hispanic Origin Not Stated | 2151766 (76.95) | 921667 (76.90) |
| Hispanic | 644645 (23.05) | 276794 (23.10) |
| Marital Status (%) | ||
| Married | 1672583 (59.81) | 716631 (59.80) |
| Unmarried | 1123828 (40.19) | 481830 (40.20) |
| Mothers’ Education (%) | ||
| ≤ High School or GED/Unknown | 1102757 (39.43) | 472551 (39.43) |
| Associate/Some College Credit | 786618 (28.13) | 336873 (28.11) |
| ≥ Bachelor's | 806822 (28.85) | 346400 (28.90) |
| Missing | 100214 (3.58) | 42637 (3.56) |
| Pre-pregnancy Smoking Status (%) | ||
| Nonsmoker | 2357285 (84.30) | 1009935 (84.27) |
| Smoker/Unknown/Not Stated | 338912 (12.12) | 145889 (12.17) |
| Missing | 100214 (3.58) | 42637 (3.56) |
| Pre-pregnancy BMI (%) | ||
| Under Weight-Normal ≤ 24.9 | 1288811 (46.09) | 552926 (46.14) |
| Overweight 25.0-29.9 | 664673 (23.77) | 283995 (23.70) |
| Obesity ≥ 30.0/Unknown/Not Stated | 742713 (26.56) | 318903 (26.61) |
| Missing | 100214 (3.58) | 42637 (3.56) |
| Pre-pregnancy Diabetes Status (%) | ||
| No/Unknown/Not Stated | 2675048 (95.66) | 1146820 (95.69) |
| Yes | 21149 (0.76) | 9004 (0.75) |
| Missing | 100214 (3.58) | 42637 (3.56) |
| Pre-pregnancy Hypertension Status (%) | ||
| No/Unknown/Not Stated | 2653410 (94.89) | 1137811 (94.94) |
| Yes | 42787 (1.53) | 18013 (1.50) |
| Missing | 100214 (3.58) | 42637 (3.56) |
| Previous Preterm Birth Status (%) | ||
| No/Unknown/Not Stated | 2621496 (93.75) | 1123851 (93.77) |
| Yes | 74701 (2.67) | 31973 (2.67) |
| Missing | 100214 (3.58) | 42637 (3.56) |
| Infertility Treatment Usage Status (%) | ||
| No/Unknown/Not Stated | 2654757 (94.93) | 1137952 (94.95) |
| Yes | 41440 (1.48) | 17872 (1.49) |
| Missing | 100214 (3.58) | 42637 (3.56) |
| Fertility Enhancing Drug Usage Status (%) | ||
| No/Not Applicable/Unknown/Not Stated | 2676910 (95.73) | 1147528 (95.75) |
| Yes | 19287 (0.69) | 8296 (0.69) |
| Missing | 100214 (3.58) | 42637 (3.56) |
| Delivery Payment Source (%) | ||
| Medicaid | 1164617 (41.65) | 499282 (41.66) |
| Private Insurance | 1276362 (45.64) | 547205 (45.66) |
| Self-pay/Other/Unknown | 255218 (9.13) | 109337 (9.12) |
| Missing | 100214 (3.58) | 42637 (3.56) |
| Newborn Gestational Age (%) | ||
| < 34 weeks: ePTB | 93751 (3.35) | 40258 (3.36) |
| ≥ 34 weeks | 2702660 (96.65) | 1158203 (96.64) |