Skip to main content

Table 2 Demographics and admission information of two cohorts

From: An effective multi-step feature selection framework for clinical outcome prediction using electronic medical records

Characteristics

Negative

Positive

P values

In Cohort 1, n (%)

39,897 (81.79)

8,883 (18.21)

 

Age, year, median [Q1, Q3]

65 [52, 78]

69 [58, 79]

<0.001

Gender, male, n (%)

22,090(55.37)

5314(59.82)

< 0.001

Race, n (%)

< 0.001

 Unknown

4126(10.34)

1147(12.91)

 

 White

29,161(73.09)

6357(71.56)

 

 Black

3232(8.1)

707(7.96)

 

 Hispanic

1365(3.42)

235(2.65)

 

 Asian

916(2.3)

207(2.33)

 

 Other

1097(2.75)

230(2.59)

 

Type of hospital admission, n (%)

< 0.001

 Elective

5473(13.72)

1726(19.43)

 

 Urgent

976(2.45)

269(3.03)

 

 Emergency

33,448(83.84)

6888(77.54)

 

Type of ICU when first admitted, n (%)

< 0.001

 Coronary Care Unit

5659(14.18)

1394(15.69)

 

 Cardiac Surgery Recovery Unit

6032(15.12)

2889(32.52)

 

 Medical Intensive Care Unit

15,855(39.74)

2693(30.32)

 

 Surgical Intensive Care Unit

6970(17.47)

1171(13.18)

 

 Trauma/Surgical Intensive Care Unit

5381(13.49)

736(8.29)

 

In Cohort 2, n (%)

25,978 (88.97)

3,219 (11.03)

 

Age, year, median [Q1, Q3]

67 [54, 79]

74 [62, 84]

< 0.001

Gender, male, n (%)

13,950 (53.7)

1715 (53.3)

0.664

Race, n (%)

  

< 0.001

 Unknown

1671 (6.4)

378 (11.7)

 

 White

17,247 (66.4)

2100 (65.2)

 

 Black

3835 (14.8)

378 (11.7)

 

 Hispanic

1122 (4.3)

99 (3.1)

 

 Asian

916 (3.5)

137 (4.3)

 

 Other

1187 (4.6)

127 (3.9)

 

Type of arrival transport, n (%)

  

< 0.001

 Unknown

3106 (11.96)

550 (17.09)

 

 Ambulance

16,100 (61.98)

2057 (63.90)

 

 Walk-in

6397 (24.62)

550 (17.09)

 

 Helicopter

319 (1.23)

54 (1.68)

 

 Other

56 (0.22)

8 (0.25)

 

Insurance, Medicare or Medicaid, n (%)

13,792 (53.09)

1940 (60.27)

< 0.001

  1. Abbreviations: Q1, first quartile (25th percentile); Q3, third quartile (75th percentile); Patient characteristics were compared between the positive and negative cases in both the AKI and IHM cohorts using the t-test for normally distributed continuous variables, the Wilcoxon rank-sum test for non-parametric continuous variables, and the Chi-square test for categorical variables.