Predicting the severity of dengue fever in children on admission based on clinical features and laboratory indicators: application of classification tree analysis

Table 3 Output from logistic regression using the decision tree algorithm to predict severe dengue infection

Variable	OR	95% CI		p value
Variable	OR	Lower	Upper
Haematocrit (> 28%)	1
Haematocrit (≤ 28%)	7.114	3.000	16.869	< 0.001
Glasgow Coma Score (> 11)	1
Glasgow Coma Score (≤ 11)	13.731	3.460	54.501	< 0.001
No urine protein	1
Urine protein	1.832	0.777	4.319	0.167
Creatinine (≤ 84 μmol/l)	1
Creatinine (> 84 μmol/l)	1.471	0.509	4.247	0.476
Platelets (> 146 × 10³/μl)	1
Platelets (≤ 146 × 10³/μl)	2.334	0.946	5.763	0.066

ISSN: 1471-2431