Advancing polytrauma care: developing and validating machine learning models for early mortality prediction

Table 2 Baseline characteristics of patients from the Dryad database who died or survived within 72 h

	Alive (N = 2388)	Dead (N = 687)	P Value^c
Demographic characteristics
Age^a, years	42 (27, 58)	51 (32, 73)	< 0.001
Sex^b			0.084
Female	613 (25.7)	199 (29.0)
Male	1775 (74.3)	488 (71.0)
BMI^a, kg/m^2	24.5 (23.1, 26.0)	24.9 (23.9, 26.1)	< 0.001
Scoring system
ISS^a	26 (20, 34)	34 (25, 50)	< 0.001
GCS^a	12 (3, 15)	3 (3, 3)	< 0.001
Laboratory test
pH^a	7.35 (7.30, 7.38)	7.28 (7.20, 7.35)	< 0.001
BE^a, mmol/L	− 2.50 (− 4.40, − 0.90)	− 5.30 (− 9.07, − 2.40)	< 0.001
Lactate^a, mmol/L	2.10 (1.40, 3.02)	3.30 (2.20, 5.61)	< 0.001

Bold values indicate a p-value of less than 0.05
BMI body mass index, ISS injury severity score, GCS glasgow coma scale, BE base excess
^aValues are presented as the median (inter-quartile range)
^bValues are presented as number (percentage)
^cP values between groups were assessed by the Chi-square and Mann–Whitney U tests

ISSN: 1479-5876