Development and validation of a novel clinical risk score to predict hypoxaemia in children with pneumonia using the WHO PREPARE dataset

Abstract

Background: Hypoxaemia predicts mortality at all levels of care, and appropriate management can reduce preventable deaths. However, pulse oximetry and oxygen therapy remain inaccessible in many primary care health facilities. We aimed to develop and validate a simple risk score comprising commonly evaluated clinical features to predict hypoxaemia in 2-59-month-old children with pneumonia.

Methods: Data from seven studies conducted in five countries from the Pneumonia Research Partnership to Assess WHO Recommendations (PREPARE) dataset were included. Readily available clinical features and demographic variables were used to develop a multivariable logistic regression model to predict hypoxemia (oxygen saturation <90%) at presentation to care. The adjusted log coefficients were transformed to derive the PREPARE hypoxemia risk score and its diagnostic value was assessed in a held-out, temporal validation dataset. The model and risk score were analysed by evaluating the area under the receiver operating characteristic curve (AUC), sensitivity and specificity.

Results: We included 14 509 children in the analysis; 9.8% (n=2515) were hypoxemic at presentation. The multivariable regression model to predict hypoxemia included age, sex, respiratory distress (nasal flaring, grunting and/or head nodding), lower chest indrawing, respiratory rate, body temperature and weight-for-age z-score. The model showed fair discrimination (AUC 0.70, 95% CI 0.67 to 0.73) and calibration in the validation dataset. The simplified PREPARE hypoxaemia risk score includes five variables: age, respiratory distress, lower chest indrawing, respiratory rate and weight-for-age z-score.

Conclusion: The PREPARE hypoxemia risk score, comprising five easily available characteristics, has the potential to be used to identify hypoxemia in children with pneumonia with a fair degree of certainty for use in health facilities without pulse oximetry. Its implementation would require careful consideration to limit the burden of inappropriate referrals on patients and the health system. Further external validation in community settings in low- and middle-income countries is required.

Keywords: Child health; Global Health; Pneumonia.

Figure 1. Flow diagram of PREPARE study dataset describing which datasets were excluded/included, the split between development and validation datasets and proportion of patients meeting the primary outcome (SpO₂<90%). Danger signs were defined by the IMCI chartbook (ie, inability to drink, lethargy or unconsciousness, convulsions, vomiting everything or stridor in a calm child). IMCI, Integrated Management of Childhood Illnesses; PREPARE, Pneumonia Research Partnership to Assess WHO Recommendations.

Figure 2. Receiver operating characteristic curve for the PREPARE hypoxemia clinical prediction model for children 2–59 months of age with pneumonia: A. Development dataset (n=10,884), B Validation dataset (n=3,625). AUROC, area under the receiver operating characteristic curve; PREPARE, Pneumonia Research Partnership to Assess WHO Recommendations.