Validation of risk stratification for children with febrile neutropenia in a pediatric oncology unit in India.

PURPOSE: The study aims to validate a score predicting risk of complications in pediatric patients with chemotherapy-related febrile neutropenia (FN) and evaluate the performance of previously published models for risk stratification.

PATIENTS AND METHODS: Children diagnosed with cancer and presenting with FN were evaluated in a prospective single-center study. A score predicting the risk of complications, previously derived in the unit, was validated on a prospective cohort. Performance of six predictive models published from geographically distinct settings was assessed on the same cohort.

RESULTS: Complications were observed in 109 (26.3%) of 414 episodes of FN over 15 months. A risk score based on undernutrition (two points), time from last chemotherapy (<7 days = two points), presence of a nonupper respiratory focus of infection (two points), C-reactive protein (>60 mg/l = five points), and absolute neutrophil count (<100 per μl = two points) was used to stratify patients into "low risk" (score <7, n = 208) and assessed using the following parameters: overall performance (Nagelkerke R2 = 34.4%), calibration (calibration slope = 0.39; P = 0.25 in Hosmer-Lemeshow test), discrimination (c-statistic = 0.81), overall sensitivity (86%), negative predictive value (93%), and clinical net benefit (0.43). Six previously published rules demonstrated inferior performance in this cohort.

CONCLUSION: An indigenous decision rule using five simple predefined variables was successful in identifying children at risk for complications. Prediction models derived in developed nations may not be appropriate for low-middle-income settings and need to be validated before use.