Table 1 Demographics and characteristics of the patients.

From: Development of a machine learning model to identify intraventricular hemorrhage using time-series analysis in preterm infants

Variables

IVH

No IVH

P-value

(n = 79)

(n = 699)

Male, n (%)

46 (58.2)

371 (53.1)

0.452

Gestational age, weeks (IQR)

25.6 (24.6−27.9)

29.7 (27.9−31)

< 0.001†

Birth weight, g (IQR)

807.5 (662.5−1100)

1210 (927.5−1490)

< 0.001†

In-vitro fertilization, n (%)

20 (25.3)

137 (19.6)

0.293

Prenatal steroids, n (%)

56 (70.9)

559 (80.0)

0.083

Resuscitation in delivery room, n (%)

77 (97.5)

569 (81.4)

< 0.001†

Surfactant use, n (%)

72 (91.1)

462 (66.1)

< 0.001†

Apgar score at 5 min < 7, n (%)

43 (54.4)

159 (22.7)

< 0.001†

Body temperature at admission, ℃ (IQR)

36 (36−36)

36 (36−36)

0.784

SpO2 at admission, % (IQR)

95 (91−98)

95 (91−98)

0.620

Duration of NICU stay, days (IQR)

105 (64−133)

58 (42−84)

< 0.001†

  1. Continuous variables are expressed as medians (interquartile range), and categorical variables are expressed as frequencies (proportion). All categorical variables between groups with and without intraventricular hemorrhage (IVH) were compared using the Chi-squared test, and continuous variables were compared using the Mann-Whitney U-test. Statistical significance was set at a P-value of < 0.05, denoted with crosses(†). IVH, intraventricular hemorrhage; SpO2 percutaneous oxygen saturation; FiO2, fraction of inspired oxygen; HCO3, bicarbonate level; NICU, neonatal intensive care unit.
Back to article page