Table 1.
Description of the personal health features from NHIS and PLCO datasets used in the ANN.
| Variable | NHIS | PLCO | ||||||
|---|---|---|---|---|---|---|---|---|
| Cancer | No cancer | Cancer | No cancer | |||||
| Mean (±SD) | % Missing | Mean (±SD) | % Missing | Mean (±SD) | % Missing | Mean (±SD) | % Missing | |
| CONTINUOUS VARIABLES | ||||||||
| Age | 59.8 (17.1) | 0.0 | 47.8 (18.1) | 0.0 | 71.1 (6.3) | 0.0 | 73.6 (5.9) | 0.0 |
| Diabetes age | 55.2 (15.2) | 1.8 | 48.4 (16.9) | 2.3 | N/A | 100 | N/A | 100 |
| Smoking age | 19.3 (9.8) | 0.9 | 18.6 (7.3) | 1.6 | 18.8 (5.3) | 0.7 | 18.6 (5.1) | 0.6 |
| Years quit | 19.2 (16.6) | 1.4 | 17.3 (14.2) | 1.1 | 25.6 (13.6) | 2.5 | 31.2 (12.5) | 1.9 |
| Pack-years | 27.3 (22.9) | 71.0 | 19.1 (20.5) | 53.7 | 44.3 (33.6) | 2.5 | 35.9 (29.3) | 2.3 |
| Vigorous exercise | 44.1 (191.9) | 0.0 | 89.2 (250.0) | 4.4 | N/A | 100 | N/A | 100 |
| Moderate exercise | 85.2 (192.2) | 1.0 | 118.6 (297.7) | 5.5 | N/A | 100 | N/A | 100 |
| Drinking frequency | 78.5 (118.7) | 0.0 | 77.1 (102.7) | 1.3 | N/A | 100 | N/A | 100 |
| Drinking amount | 2.2 (3.9) | 29.8 | 2.6 (2.8) | 12.4 | N/A | 100 | N/A | 100 |
| Binging frequency | 10.7 (49.5) | 30.6 | 13.7 (46.0) | 13.3 | N/A | 100 | N/A | 100 |
| Family members with PC | 0.4 (1.4) | 85.8 | 0.1 (0.6) | 86.6 | 0.5 (2.3) | 5.9 | 0.3 (1.8) | 3.9 |
| Family members >50 with PC | 0.0 (0.0) | 58.8 | 0.0 (0.3) | 86.6 | 1.0 (0.0) | 0.0 | 1.0 (0.0) | 0.0 |
| BMI | 25.3 (5.3) | 1.9 | 27.3 (6.0) | 3.9 | 27.1 (4.5) | 6.0 | 27.3 (4.9) | 4.7 |
| DISCRETE VARIABLES | ||||||||
| Male | 48.8% | 0.0 | 55.9% | 0.0 | 42.6% | 0.0 | 50.5% | 0.0 |
| Emphysema | 7.6% | 0.0 | 1.8% | 0.1 | 3.2% | 5.4 | 2.5% | 3.8 |
| Asthma | 15.2% | 0.0 | 11.4% | 0.1 | N/A | 100 | N/A | 100 |
| Stroke | 6.6% | 0.0 | 3.0% | 0.1 | 2.6% | 5.7 | 2.4% | 3.8 |
| Coronary heart disease | 11.4% | 0.5 | 4.6% | 0.2 | 12.2 | 5.6 | 9.1 | 3.8 |
| Angina pectoris | 7.6% | 0.0 | 2.5% | 0.2 | N/A | 100 | N/A | 100 |
| Heart attack | 8.5% | 0.0 | 3.6% | 0.1 | 12.2% | 5.6 | 9.1% | 3.8 |
| Other heart disease | 16.6% | 0.0 | 7.9% | 0.2 | N/A | 100 | N/A | 100 |
| Ulcer | 20.9% | 0.0 | 7.7% | 0.2 | N/A | 100 | N/A | 100 |
| Drink | 75.8% | 0.0 | 77.4% | 1.2 | N/A | 100 | N/A | 100 |
| Other cancer | 9.0% | 0.0 | 0.0% | 0.0 | 2.2% | 0.0 | 0.1% | 0.0 |
| Hypertension | 52.6% | 0.0 | 29.6% | 0.0 | 41.9% | 5.3 | 36.7% | 3.8 |
| Hispanic | 7.6% | 0.0 | 16.3% | 0.0 | 2.2% | 9.0 | 2.1% | 5.7 |
| Diabetes | 0.0 | 0.1 | 5.5 | 3.9 | ||||
| Diabetic | 26.1% | 8.6% | 12.7% | 7.7% | ||||
| Prediabetic | 0.0% | 1.4% | N/A | N/A | ||||
| Not diabetic | 73.9% | 90.0% | 87.3% | 92.3% | ||||
| Smoking | 0.0 | 0.8 | 0.0 | 0.0 | ||||
| Current | 14.7% | 20.3% | 16.4% | 10.3% | ||||
| Former | 36.0% | 22.2% | 41.2% | 41.7% | ||||
| Never | 49.3% | 57.5 | 42.4% | 48.0% | ||||
| Smoking frequency | 0 | 1.9 | 0.0 | 0.0 | ||||
| Every day | 24.3% | 37.5% | 28.5% | 19.9% | ||||
| Some day | 4.7% | 10.1% | N/A | N/A | ||||
| Quit | 71.0 | 52.3% | 71.5% | 80.0% | ||||
| Race | 0.0 | 0.0 | 0.0 | 0.0 | ||||
| White | 78.2% | 74.6% | 82.8% | 85.6% | ||||
| Black | 14.2% | 14.4% | 4.7% | 5.0% | ||||
| AINA | 0.5% | 0.9% | 0.1% | 0.3% | ||||
| Asian Indian | 1.0% | 0.9% | 5.1% | 3.6% | ||||
| Chinese | 1.0% | 1.0% | 5.1% | 3.6% | ||||
| Filipino | 1.0% | 1.0% | 5.1% | 3.6% | ||||
| Other | 3.8% | 6.9% | 0.4% | 0.5% | ||||
| Multiracial | 0.5% | 0.3% | N/A | N/A | ||||