Skip to main content

Table 1 The information gain (IG) of 44 variables

From: Predicting postoperative complications of head and neck squamous cell carcinoma in elderly patients using random forest algorithm model

Variable

IG

Variable

IG

Variable

IG

Variable

IG

Age

4.427

GCS

0.000

Respiratory function

2.971

The chronic diseases

17.430

Cardiac function

2.908

Operation type

1.863

Levels of sodium

1.373

Smoking

1.813

Respiratory function

2.971

Number of procedures

2.009

Potassium

4.144

Alcoholism

1.170

ECG

3.388

Operative blood loss

13.551

Creatinine

0.928

Preoperative radiotherapy

1.053

Systolic BP

3.72

Peritoneal contamination

1.661

Hematocrit

0.980

Preoperative chemotherapy

1.465

Pulse rate

2.981

Malignancy

2.477

Preoperative WBC

4.002

Preoperative surgery

2.099

Hemoglobin levels

4.511

Confidential Enquiry into Perioperative Deaths

0.015

Operation time

17.060

Primary/recurrence

1.745

WBC count

4.002

Rectal temperature

0.010

Diameter of the tumor

10.935

Surgery classification

16.009

Levels of blood urea nitrogen

0.927

Mean arterial pressure:

2.103

Amount of blood loss

13.551

Clinical grading

8.2800

Sodium:

3.291

Blood pH

2.372

Hematocrit of POD1

1.983

Pathological grading:

4.998

Potassium

5.370

Heart rate

2.981

Glucose of POD1

9.560

Preoperative blood urea (g/L)

0.913