Research Article
Machine Learning Approaches to Predict Patient’s Length of Stay in Emergency Department
Table 1
Input data set attributes, types, and definitions.
| Category | Attribute | Definition |
| Check-in data | Date | Day, month, and year of arrival | Day | The name of the day (Sunday, Monday … etc.) | ID | Identity document of the patient in the hospital | Gender | Male\female | Insurance | Insurance info | Mode of arrival | Patient’s arrival mode | Age | Age of the patient |
| Medical procedure | Immediate treatment | Immediate treatment requirements | Triage level | Urgency case level (1–5) | Medication | Medication needed (yes, no) | Consultation | Consultation needed (yes, no) |
| Time | T arrive | The arrival time | T triage assessment | Triage assessment time | T NURS assessment | Nurse assessment time | T doctor assessment | Doctor assessment time | T departure | Patient’s departure time |
| Medical tests | Twenty-three tests, including urine analysis, CBC, cardiac enzymes, stool analysis, X-ray, ultrasound, CT scan, and MRI | Tests |
| Others | Number of nurses | Available number of nurses | Crowding | Number of patients in the ED | Lockdown | Lockdown status | LOS | (T departure-T arrival) |
|
|