Prediction models for childhood asthma: A systematic review

Abstract

Background The inability to objectively diagnose childhood asthma before age five often results in both under‐treatment and over‐treatment of asthma in preschool children. Prediction tools for estimating a child's risk of developing asthma by school‐age could assist physicians in early asthma care for preschool children. This review aimed to systematically identify and critically appraise studies which either developed novel or updated existing prediction models for predicting school‐age asthma. Methods Three databases (MEDLINE, Embase and Web of Science Core Collection) were searched up to July 2019 to identify studies utilizing information from children ≤5 years of age to predict asthma in school‐age children (6‐13 years). Validation studies were evaluated as a secondary objective. Results Twenty‐four studies describing the development of 26 predictive models published between 2000 and 2019 were identified. Models were either regression‐based (n = 21) or utilized machine learning approaches (n = 5). Nine studies conducted validations of six regression‐based models. Fifteen (out of 21) models required additional clinical tests. Overall model performance, assessed by area under the receiver operating curve (AUC), ranged between 0.66 and 0.87. Models demonstrated moderate ability to either rule in or rule out asthma development, but not both. Where external validation was performed, models demonstrated modest generalizability (AUC range: 0.62‐0.83). Conclusion Existing prediction models demonstrated moderate predictive performance, often with modest generalizability when independently validated. Limitations of traditional methods have shown to impair predictive accuracy and resolution. Exploration of novel methods such as machine learning approaches may address these limitations for future school‐age asthma prediction.

Asthma susceptible genes in children

“…[ 7 ] Due to the heterogeneity of asthma, there are differences in the clinical manifestations of children at different ages, which may make it harder to diagnose asthma in children. [ 8 ] Both genetic and environmental factors contribute to inception and evolution of asthma, while genes play a greater role in pediatric asthma than adults. A genome-wide association study (GWAS) found that the genes associated with childhood asthma are almost 3 times that of adults.…”

Comments on Kothalawala et al.

“…As correctly noted by Kothalawala et al 1 in their recent review “Prediction models for childhood asthma: A systematic review,” exemplary reviews of such prognostic models are not widely available. We praise the authors for their rigor of review methods used to summarize existing literature on school‐age asthma prediction models.…”

Reply to Owora et al.

“…As detailed in our inclusion criteria, we only considered studies which offered predictions for children aged ≤5 years on their risk of developing the future outcome of childhood asthma or wheeze persistence at school age (6-13 years old). 2 Following their meta-analysis of externally validated regressionbased models, Owora et al concluded that based on their pooled estimates of sensitivity, specificity and area under the receiver operating curve (AUC), existing models offer poor predictive performance, particularly among clinically relevant ranges of sensitivity and specificity. We are pleased that Owora et al were able to offer quantitative support for our initial inference that existing models offer moderate performance with modest generalizability.…”