Prediction of cardiac arrest in critically ill patients presenting to the emergency department using a machine learning score incorporating heart rate variability compared with the modified early warning score

Table 2 Baseline characteristics of study patients

Characteristic	No cardiac arrest within 72 hours (n= 882)	Cardiac arrest within 72 hours (n= 43)	P value^a
Age (years)
Median (IQR)	62 (50 to 74)	70 (59 to 78)	0.018
Male gender	542 (61.5)	31 (72.1)	0.198
Race
Chinese	586 (66.4)	35 (81.4)
Malay	130 (14.7)	5 (11.6)	0.134
Indian	118 (13.4)	1 (2.3)
Others	48 (5.4)	2 (4.7)
Diagnosis grouping^b
Cardiovascular	359 (40.7)	9 (20.9)
Respiratory	137 (15.5)	10 (23.3)
Neurological	87 (9.9)	4 (9.3)
Gastrointestinal	46 (5.2)	0 (0)
Renal	25 (2.8)	0 (0)
Endocrine	58 (6.6)	4 (9.3)	0.275
Infectious diseases	59 (6.7)	1 (2.3)
Vascular	22 (2.5)	3 (7.0)
Trauma	31 (3.5)	2 (4.7)
Cancer	28 (3.2)	9 (20.9)
Others	30 (3.4)	1 (2.3)
Medical history^c
Diabetes	295 (33.4)	5 (11.6)	0.405
Hypertension	472 (53.5)	18 (41.9)	0.876
Heart disease	292 (33.1)	12 (27.9)	0.868
Renal disease	115 (13.0)	6 (14.0)	0.251
Respiratory disease	103 (11.7)	7 (16.3)	0.222
Stroke	63 (7.1)	0 (0)	1.000
Cancer	69 (7.8)	2 (4.7)	1.000
Others	523 (59.3)	32 (74.4)	0.204
Prior medical therapy^d
Beta-blockers	227 (25.7)	14 (32.6)	0.726
Calcium-channel blockers	165 (18.7)	11 (25.6)	0.432
Digoxin	36 (4.1)	2 (4.7)	0.415
Amiodarone	12 (1.4)	0 (0)	1.000
Other anti-arrythmics	5 (1.4)	0 (0)	1.000

Data shown are numbers (%) unless otherwise stated. IQR, interquartile range (25th to 75th percentiles). ^aP value from either the chi-square test or the Mann-Whitney test as appropriate. ^bBased on admitting emergency physician clinical diagnosis. ^cMedical history at presentation to the emergency department. ^dPrior outpatient medical therapy at presentation to the emergency department.

ISSN: 1364-8535