Research Article
A Fact-Finding Procedure Integrating Machine Learning and AHP Technique to Predict Delayed Diagnosis of Bladder Patients with Hematuria
Table 3
Characteristics of bladder cancer patients with delay diagnosed and control subjects.
| | Variables | Value | Delay diagnosed group (n = 210) | Nondelayed diagnosed group (n = 325) |
| | Age | Patient | 67.3 (31–93) | 67.4 (16–98) | | | Physician | 54.7 (47–63) | 56 (43–63) |
| | Seniority (physician) | | 11.7 (4–20) | 13 (5–20 | | Gender (patient) | Male | 142 (67.6) | 227 (68.8) | | | Female | 68 (32.4) | 98 (30.2) |
| | Gender (physician) | Male | 201 (95.7) | 313 (96.3) | | | Female | 9(4) | 12 (3.7) |
| | Hospital level | Medical center | 60 (28.6) | 113 (34.8) | | | Regional hospital | 81 (38.6) | 135 (41.5) | | | District hospital | 36 (17.1) | 43 (13.2) | | | Clinic | 33 (15.7) | 32 (10.5) |
| | Visit behavior | Surgery | 52 (24.7) | 19 (5.8) | | | Gynecology | 38 (18.1) | 13 (4) | | | Chinese medicine | 48 (22.3) | 3 (0.9) | | | Gastroenterology | 61 (29.0) | 6 (1.8) | | | Nephrology | 53 (25.2) | 30 (9.2) |
| | Cystoscopy after hematuria record for half year | 205 (97.6) | 120 (36.9) | | Visit times | Surgery | 1.69 | 0.03 | | | Gynecology | 1.69 | 0.05 | | | Chinese medicine | 1.73 | 0.01 | | | Gastroenterology | 0 | 0.02 | | | Nephrology | 0 | 0.18 |
| | Location (level of urbanization) | | | | | City | 82 (39.0) | 114 (44.3) | | | Commuting zone | 54 (25.7) | 80 (24.6) | | | Towns and semidense areas | 10 (4.8) | 12 (3.7) | | | Rural areas | 64 (30.5) | 89 (27.4) |
|
|
n (%), the others are μ( σ). |
