Development and Validation of a Pediatric Hospital-Acquired Malnutrition (PHaM) Risk Score to Predict Nutritional Deterioration in Hospitalized Pediatric Patients: A Secondary Analysis Based on a Multicenter Prospective Cohort Study

Abstract

(1) Background: Hospital-acquired malnutrition in pediatric patients leads to adverse outcomes. This study aimed to develop and validate a pediatric hospital-acquired malnutrition (PHaM) risk score to predict nutritional deterioration. (2) Methods: This was a derivative retrospective cohort study for developing a PHaM risk score. The study included data from children aged 1 month-18 years admitted to pediatric wards in four tertiary care hospitals for at least 72 h between December 2018 and May 2019. Data on pediatric patients' characteristics, medical history, nutritional status, gastrointestinal symptoms, and outcomes were used for tool development. Logistic regression identified risk factors for nutritional deterioration, defined as a decline in BMI z-score ≥ 0.25 SD and/or ≥2% weight loss. A PHaM risk score was developed based on these factors and validated with an independent prospective cohort from July 2020 to March 2021. (3) Results: The study used a derivative cohort of 444 patients and a validation cohort of 373 patients. Logistic regression identified gastrointestinal symptoms, disease severity, fever, lower respiratory tract infection, and reduced food intake as predictors. The PHaM risk score (maximum 9 points) showed good discrimination and calibration (AUC 0.852, 95% CI: 0.814-0.891). Using a cut-off at 2.5 points, the scale had 63.0% sensitivity, 88.6% specificity, 76.1% positive predictive value, and 80.6% negative predictive value (NPV) when applied to the derivative cohort. The accuracy improved on the validation cohort, with 91.9% sensitivity and 93.0% NPV. (4) Conclusions: This PHaM risk score is a novel and probably effective tool for predicting nutritional deterioration in hospitalized pediatric patients, and its implementation in clinical practice could enhance nutritional care and optimize outcomes.

Keywords: children; hospital-acquired malnutrition; nutritional deterioration; predictive score; validation.

Figure 1

(a) Derivation and (b) validation sets’ receiver operating characteristic (ROC) curves for the pediatric hospital-acquired malnutrition (PHaM) risk score relative to hospital-acquired malnutrition.

Figure 2

Calibration curves of (a) the derivative model and the (b) validation model. The x-axis represents the model-predicted frequency of hospital-acquired malnutrition, and the y-axis represents the actual frequency of hospital-acquired malnutrition.