Research Article
An Artificial Neural Networks Model for Early Predicting In-Hospital Mortality in Acute Pancreatitis in MIMIC-III
Table 1
General characteristics of AP patients in MIMIC-III.
| Characteristics | |
| Number of patients | 337 | Age (IQR, year) | 65 (47.2-74) | Sex | | Male (, %) | 189 (56.08%) | Female | 148 (43.92%) | Marital status (, %) | | Divorced | 24 (7.12%) | Married | 160 (47.48%) | Single | 96 (28.49%) | Others | 57 (16.91%) | Ethnicity (, %) | | Asian | 5 (1.48%) | Black/African American | 32 (9.50%) | Hispanic or Latino | 9 (2.67%) | White | 222 (65.88%) | Others | 69 (20.47%) | In-hospital mortality (, %) | 38 (11.2%) | Length of stay in ICU (IQR, day) | 8.6 (2-10) | Scoring system (IQR) | | SOFA | 1 (0-3) | Ranson | 3 (2-4) |
|
|
Abbreviations: AP: acute pancreatitis; SOFA: sequential organ failure assessment.
|