# An exploratory machine learning study on paediatric abdominal pain phenotyping and prediction

## TL;DR

This study uses machine learning to identify different types of pediatric abdominal pain and finds factors that predict its occurrence, which could help guide future research and interventions.

## Contribution

The study introduces a machine learning approach to phenotype pediatric abdominal pain and develop a predictive model for its occurrence.

## Key findings

- Three distinct AP phenotypes were identified: allergic predisposition, maternal comorbidities, and minimal comorbidities.
- Ethnicity, allergic diseases, and maternal comorbidities were key predictive factors for AP.
- The predictive model showed moderate performance (AUC 0.67) and enabled risk stratification for AP.

## Abstract

The exact mechanisms underlying paediatric abdominal pain (AP) remain unclear due to patient heterogeneity. This preliminary study aimed to identify AP phenotypes and develop predictive models to explore associated factors, with the goal of guiding future research.

In 13,790 children from a large birth cohort, data on paediatric and maternal demographics and comorbidities were extracted from general practitioner records. Machine learning (ML) clustering was used to identify distinct AP phenotypes, and an ML-based predictive model was developed using demographics and clinical features.

1,274 children experienced AP (9.2%) (average age: 8.4 ± 1.1 years, male/female: 615/659), who clustered into three distinct phenotypes: Phenotype 1 with an allergic predisposition (n = 137), Phenotype 2 with maternal comorbidities (n = 676), and Phenotype 3 with minimal other comorbidities (n = 340). As the number of allergic diseases or maternal comorbidities increased, so did the frequency of AP, with 17.6% of children with ≥ 3 allergic diseases and 25.6% of children with ≥ 3 maternal comorbidities. The predictive model demonstrated moderate performance in predicting paediatric AP (AUC 0.67), showing that a child’s ethnicity, paediatric allergic diseases, and maternal comorbidities were key predictive factors. When stratified by ML-predicted probability, observed AP rates were 18.9% in the < 40% group, 44.8% in the 40–50% group, 60.6% in the 50–60% group, and 100.0% in the > 60% group.

This study identified distinct AP phenotypes and key risk factors using ML. Furthermore, the predictive ML model enabled risk stratification for paediatric AP. These analyses provide valuable insights to guide future investigations into the mechanisms of AP and may facilitate research aimed at identifying targeted interventions to improve patient outcomes.