Table 1.
Personal health parameters from the NHIS and PLCO datasets used in the ANN.
| NHIS | PLCO | |||||||
|---|---|---|---|---|---|---|---|---|
| Cancer | No cancer | Cancer | No cancer | |||||
| Mean (SD) | % Missing | Mean (SD) | % Missing | Mean (SD) | % Missing | Mean (SD) | % Missing | |
| CONTINUOUS VARIABLES | ||||||||
| Age | 42.3 (17.4) | 0.0 | 48.5 (18.5) | 0.0 | 69.5 (6.5) | 0.0 | 73.6 (5.9) | 0.0 |
| Diabetes age | 44.1 (17.4) | 7.1 | 48.1 (17.4) | 2.5 | N/A | 100.0 | N/A | 100 |
| Smoking age | 18.4 (6.3) | 0.7 | 19.2 (7.8) | 1.5 | 20.3 (6.4) | 1.5 | 19.6 (5.6) | 0.4 |
| Years quit | 8.6 (12.2) | 0.3 | 16.5 (13.9) | 1.0 | 25.8 (13.1) | 0.6 | 30.5 (12.5) | 2.0 |
| Pack-years | 20.8 (22.1) | 52.0 | 17.3 (17.9) | 52.5 | 27.7 (22.2) | 2.0 | 30.3 (25.3) | 2.1 |
| Vigorous exercise | 56.9 (221.6) | 3.0 | 66.0 (190.1) | 4.3 | N/A | 100.0 | N/A | 100 |
| Moderate exercise | 108.0 (285.1) | 4.1 | 106.9 (264.1) | 5.3 | N/A | 100.0 | N/A | 100 |
| Drinking frequency | 60.4 (102.1) | 0.6 | 63.2 (92.0) | 1.2 | N/A | 100.0 | N/A | 100 |
| Drinking amount | 2.1 (1.7) | 21.3 | 2.1 (2.0) | 11.5 | N/A | 100.0 | N/A | 100 |
| Binging frequency | 6.7 (26.3) | 21.8 | 6.4 (28.9) | 12.1 | N/A | 100.0 | N/A | 100 |
| Family members with breast cancer | 0.29 (0.84) | 86.5 | 0.23 (0.76) | 85.4 | 1.86 (4.51) | 3.9 | 1.72 (4.46) | 3.3 |
| Family members <50 with breast cancer | 0.14 (0.61) | 86.5 | 0.12 (0.60) | 85.4 | 0.41 (2.08) | 0.0 | 0.42 (2.11) | 0.0 |
| Family members with ovarian cancer | 0.34 (1.13) | 86.3 | 0.08 (0.57) | 85.3 | 0.67 (2.74) | 3.9 | 0.44 (2.24) | 3.3 |
| Family members <50 with ovarian cancer | 0.23 (0.89) | 86.3 | 0.05 (0.42) | 85.3 | 0.21 (1.52) | 0.0 | 0.13 (1.19) | 0.0 |
| BMI | 28.4 (7.6) | 3.7 | 27.1 (6.6) | 5.3 | 27.0 (5.7) | 3.5 | 27.1 (5.6) | 4.1 |
| DISCRETE VARIABLES | ||||||||
| Emphysema | 4.7% | 0.1 | 1.6% | 0.1 | 0.9% | 3.7 | 2.1% | 3.3 |
| Asthma | 20.2% | 0.1 | 12.8% | 0.1 | N/A | 100.0 | N/A | 100.0 |
| Stroke | 7.7% | 0.3 | 3.0% | 0.1 | 2.0% | 3.5 | 2.1% | 3.3 |
| Coronary heart disease | 8.9% | 0.4 | 3.6% | 0.2 | 3.8% | 3.9 | 4.9% | 3.4 |
| Angina pectoris | 5.9% | 0.4 | 2.3% | 0.2 | N/A | 100.0 | N/A | 100.0 |
| Heart attack | 8.4% | 0.4 | 2.6% | 0.1 | 3.8% | 3.9 | 4.9% | 3.4% |
| Other heart disease | 17.3% | 0.2 | 8.2% | 0.1 | N/A | 100.0 | N/A | 100.0 |
| Ulcer | 20.4% | 0.1 | 8.0% | 0.2 | N/A | 100.0 | N/A | 100.0 |
| Drink | 75.0% | 0.7 | 71.2% | 1.2 | N/A | 100.0 | N/A | 100.0 |
| Other cancer | 7.8% | 0.0 | 0.0% | 0.0 | 2.4% | 0.0 | 0.1% | 0.0 |
| Hypertension | 45.8% | 0.0 | 30.1% | 0.0 | 34.7% | 3.3 | 36.2% | 3.3 |
| Hispanic | 11.3% | 0.0 | 16.2% | 0.0 | 1.6% | 4.3 | 1.8% | 5.0 |
| Diabetes: | 0.1 | 0.1 | 3.5 | 3.3 | ||||
| Diabetic | 6.0% | 8.4% | 4.7% | 6.4% | ||||
| Prediabetic | 0.0% | 1.4% | N/A | N/A | ||||
| Not Diabetic | 94.0% | 90.2% | 95.3% | 93.6% | ||||
| Smoking: | 0.5 | 0.7 | 0.0 | 0.0 | ||||
| Current | 21.7% | 18.0% | 8.9% | 9.5% | ||||
| Former | 27.9% | 18.8% | 34.7% | 33.7% | ||||
| Never | 50.4% | 63.2% | 56.4% | 56.8% | ||||
| Smoking frequency: | 1.0 | 2.0 | 0.0 | 0.0 | ||||
| Every day | 36.3% | 38.9% | 20.4% | 21.9% | ||||
| Some day | 7.4% | 10.0% | N/A | N/A | ||||
| Quit | 56.3% | 51.1% | 79.6% | 78.1% | ||||
| Race: | 0.0 | 0.0 | 0.0 | 0.0 | ||||
| White | 82.4% | 73.4% | 89.4% | 86.2% | ||||
| Black | 10.3% | 15.8% | 3.5% | 5.6% | ||||
| AINA | 1.2% | 0.9% | 0.2% | 0.3% | ||||
| Asian Indian | 0.0% | 0.7% | 2.4% | 3.3% | ||||
| Chinese | 0.3% | 0.9% | 2.4% | 3.3% | ||||
| Filipino | 0.6% | 1.0% | 2.4% | 3.3% | ||||
| Other | 4.9% | 6.8% | 0.2% | 0.5% | ||||
| Multiracial | 0.2% | 0.3% | N/A | N/A | ||||