Related Experiment Video
Updated: Jun 6, 2025
A Method of Trigonometric Modelling of Seasonal Variation Demonstrated with Multiple Sclerosis Relapse Data
Published on: December 9, 2015
Predictive modelling of linear growth faltering among pediatric patients with Diarrhea in Rural Western Kenya: an
Billy Ogwel1,2, Vincent H Mzazi3, Alex O Awuor4
1Kenya Medical Research Institute- Center for Global Health Research (KEMRI-CGHR), P.O Box 1578-40100, Kisumu, Kenya. ogwelbill@gmail.com.
Insights
Machine learning models can predict linear growth faltering (LGF) in children with diarrhea using key factors like age and temperature. This aids in early identification of at-risk children for timely interventions.
Area of Science:
- Pediatric Health
- Global Health
- Machine Learning in Medicine
Background:
- Stunting affects 20% of children globally; diarrhea contributes significantly to linear growth faltering (LGF).
- Predictive models for LGF are crucial for developing effective interventions.
- Recent data and advanced methods can improve LGF prediction accuracy and insights.
Purpose of the Study:
- To develop and validate a machine learning (ML) predictive model for LGF in children experiencing diarrhea.
- To identify key predictors of LGF using recent data from African cohorts.
Main Methods:
- Utilized 7 ML algorithms to build prognostic models for LGF prediction in children aged 6-35 months.
- Combined data from VIDA and EFGH-Shigella studies for model development and temporal validation.
- Employed Boruta feature selection to identify 6 key predictors: age, temperature, respiratory rate, severe acute malnutrition (SAM), rotavirus vaccination, and skin turgor.
Main Results:
- LGF prevalence was 16.9% in the development cohort and 22.4% in the validation cohort.
- The gradient boosting model demonstrated the best performance, with an AUC of 83.5% (development) and 65.6% (validation).
- Key predictors identified were age, temperature, respiratory rate, SAM, rotavirus vaccination, and skin turgor.
Conclusions:
- Established predictors of LGF remain relevant.
- ML algorithms offer a practical approach for the rapid identification of children at risk of LGF.
Introduction:
Stunting affects one-fifth of children globally with diarrhea accounting for an estimated 13.5% of stunting. Identifying risk factors for its precursor, linear growth faltering (LGF), is critical to designing interventions. Moreover, developing new predictive models for LGF using more recent data offers opportunity to enhance model accuracy, interpretability and capture new insights. We employed machine learning (ML) to derive and validate a predictive model for LGF among children enrolled with diarrhea in the Vaccine Impact on Diarrhea in Africa (VIDA) study and the Enterics for Global Heath (EFGH) - Shigella study in rural western Kenya.
Methods:
We used 7 diverse ML algorithms to retrospectively build prognostic models for the prediction of LGF (≥ 0.5 decrease in height/length for age z-score [HAZ]) among children 6-35 months. We used de-identified data from the VIDA study (n = 1,106) combined with synthetic data (n = 8,894) in model development, which entailed split-sampling and K-fold cross-validation with over-sampling technique, and data from EFGH-Shigella study (n = 655) for temporal validation. Potential predictors (n = 65) included demographic, household-level characteristics, illness history, anthropometric and clinical data were identified using boruta feature selection with an explanatory model analysis used to enhance interpretability.
Results:
The prevalence of LGF in the development and temporal validation cohorts was 187 (16.9%) and 147 (22.4%), respectively. Feature selection identified the following 6 variables used in model development, ranked by importance: age (16.6%), temperature (6.0%), respiratory rate (4.1%), SAM (3.4%), rotavirus vaccination (3.3%), and skin turgor (2.1%). While all models showed good prediction capability, the gradient boosting model achieved the best performance (area under the curve % [95% Confidence Interval]: 83.5 [81.6-85.4] and 65.6 [60.8-70.4]) on the development and temporal validation datasets, respectively.
Conclusion:
Our findings accentuate the enduring relevance of established predictors of LGF whilst demonstrating the practical utility of ML algorithms for rapid identification of at-risk children.
Related Concept Videos
01:18Steps in Outbreak Investigation
01:23Mechanistic Models: Compartment Models in Individual and Population Analysis
01:27Microbial Growth Measurement: Indirect Methods