Skip to main content

Table 3 The heterogeneous features for test data (710 cases) according to blood tests

From: Clinical applications of machine learning in the survival prediction and classification of sepsis: coagulation and heparin usage matter

Features

Cluster one

Cluster two

Cluster three

Cluster four

P value

Number of clusters

90

520

19

81

 

survival (%)

68 (75.56%)

416 (80%)

13 (68.42%)

57 (70.37%)

0.152

Age, median (IQR), y

64 (51.5–77.5)

66 (54–77)

60 (51.3–69.3)

65 (54–74)

0.364

Male, no. (%)

55 (61.11%)

296 (56.92%)

12 (63.16%)

49 (60.49%)

0.797

Top ten blood test varies, median (IQR), unit

 PTT, sec

31.7 (27.7–36.5)

30.1 (26.6–34.2)

150 (119.0–150)

50.5(43.6–57.7)

0.000

 Neutrophils, %

52 (36.3–61.7)

83 (77–88.7)

81 (70.2–87.5)

81 (76.9–88.6)

0.000

 PT, sec

14.4 (13.3–17.1)

14.3 (13.1–16.3)

19.5 (15.4–23.1)

28 (19.6–39)

0.000

 INR(PT), NULL %

1.3 (1.2–1.7)

1.3 (1.1–1.6)

1.9 (1.6–2.7)

3 (2–4.3)

0.000

 Lymphocytes, %

27.1 (18.5–35.3)

7.1 (4–11.9)

9.7 (3.7–11)

7.2 (3–12)

0.000

 White blood cells, K/μL

4.7 (2.8–10.3)

13.0 (8.4–18.4)

9.6 (7.4–18.2)

12.4 (8.2–19.2)

0.000

 Platelet count, K/μL

2.2 (1.9–2.5)

2.4 (2.2–2.5)

2.4 (2.1–2.6)

2.3 (2.2–2.5)

0.000

 MCHC, %

33.4 (32.3–34.6)

33 (32–34)

32.7 (30.5–33.6)

32.5 (31.2–33.6)

0.000

 Albumin, %

2.9 (2.6–3.4)

2.9 (2.6–3.4)

2.9 (2.8–2.9)

2.6 (2.3–3)

0.000

 Red blood cells, K/μL

3.4 (3.0–4.0)

3.7 (3.3–4.3)

3.8 (3.4–4.0)

3.5 (2.9–3.9)

0.000