RESUMO
BACKGROUND: Infection is one of the major problems in neonates. The diagnosis of neonatal septicemia is difficult to establish based on the clinical criteria alone. However, empirical treatment should not be delayed because of the high mortality. Laboratory tests used to support diagnosis have shown variable predictive values. C-reactive protein (CRP), an acute phase protein, increases in inflammatory disorders and tissue injury. Serial CRP have been shown to be more useful than a single measured CRP in the diagnostic evaluation of neonates with suspected infection. OBJECTIVES: 1. To evaluate the diagnostic accuracy of serial CRP in neonatal sepsis. 2. To compare the diagnostic values between CRP and leukocyte index from a complete blood count (CBC). METHOD: A prospective observational study included newborn infants, aged > 3 days and diagnosed with clinical sepsis, who were admitted in the newborn intensive care unit and special care nursery at Ramathibodi Hospital during a 14-months period. Newborn infants who received antibiotics prior to septic work up were excluded. CRP levels were measured initially at the time of septic work-up and at 24-48 hours later. Investigations for infection included CBC, blood culture and urine culture. Radiological study and lumbar puncture were performed if clinically indicated. Based on clinical and biological data, diagnosis of infants can be categorized into 4 groups as follows; (1) proven sepsis with positive culture, (2) localized infection with negative culture, (3) probable infection (clinically consistent with sepsis, negative culture without localized infection), and (4) no infection (findings not consistent with sepsis and antibiotics were discontinued within 3 days). Diagnosis was made before the CRP results were known. RESULTS: Of 76 newborn infants with 90 episodes of clinical sepsis, there were 24 episodes of proven sepsis, 11 episodes of localized infection with negative culture, 18 episodes of probable infection and 37 episodes of no infection. Serial CRP had better predictive values than those of CBC. The sensitivity, specificity, positive predictive value, and negative predictive value of CRP for proven sepsis and localized infection at cutoff point > or = 5 mg/L were 100 per cent, 94 per cent, 91.6 per cent and 100 per cent respectively. False positive CRP were found in post-operative patent ductus arteriosus ligation, intracerebral hemorrhage, and post resuscitation with chest compression. To improve the predictive value of CBC, analysis of the receiver operating characteristic (ROC) curve showed that the predictive value of CBC for sepsis would be enhanced by using abnormal leukocyte index 2 2 parameters. CONCLUSIONS: Predictive value of CRP could be enhanced by serial rather than a single measurement. Serial CRP showed very high predictive values for diagnosis of neonatal sepsis and were better than those of leukocyte indices of CBC.