Machine Learning in Predicting Child Malnutrition: A Meta-Analysis of Demographic and Health Surveys Data
Bhagyajyothi Rao1, Muhammad Rashid2,3, Md Gulzarull Hasan1
1Department of Applied Statistics & Data Science, Prasanna School of Public Health, Manipal Academy of Higher Education, Manipal 576104, India.
Insights
Machine learning models show promise in predicting childhood malnutrition using Demographic and Health Surveys data. These AI tools offer moderate to good performance for identifying at-risk children under five.
Area of Science:
- Public Health
- Data Science
- Pediatrics
Background:
- Childhood malnutrition is a critical global health issue.
- Demographic and Health Surveys (DHS) offer valuable child health data.
- Assessing machine learning (ML) applications in DHS data for malnutrition prediction is essential.
Purpose of the Study:
- To conduct a meta-analysis on machine learning applications in DHS data for predicting childhood malnutrition.
- To evaluate the performance of ML models in identifying malnutrition in children under five years.
Main Methods:
- Systematic literature search of PubMed, Embase, and Scopus databases (January 2024).
- Inclusion of studies using ML algorithms on DHS data for child malnutrition prediction.
- Quality assessment using PROBAST and meta-analysis using Review Manager 5.4.
Main Results:
- 11 studies (2019-2023) were included, with a focus on Bangladesh.
- Pooled accuracy for ML models predicting stunting: 68.92% (10 studies).
- Pooled accuracy for ML models predicting wasting: 84.39% (3 studies).
- Pooled accuracy for ML models predicting underweight: 73.60% (4 studies).
Conclusions:
- ML models demonstrate moderate to good performance in predicting childhood malnutrition.
- DHS data, when analyzed with ML, can be a valuable tool for public health initiatives.
- Further research can refine ML models for more accurate malnutrition prediction.
Background:
Childhood malnutrition remains a significant global public health concern. The Demographic and Health Surveys (DHS) program provides specific data on child health across numerous countries. This meta-analysis aims to comprehensively assess machine learning (ML) applications in DHS data to predict malnutrition in children.
Methods:
A comprehensive search of the peer-reviewed literature in PubMed, Embase, and Scopus databases was conducted in January 2024. Studies employing ML algorithms on DHS data to predict malnutrition in children under 5 years were included. Using PROBAST (Prediction model Risk Of Bias Assessment Tool), the quality of the listed studies was evaluated. To conduct meta-analyses, Review Manager 5.4 was used.
Results:
A total of 11 out of 789 studies were included in this review. The studies were published between 2019 and 2023, with the major contribution from Bangladesh (n = 6, 55%). Of these, ten studies reported stunting, three reported wasting, and four reported underweight. A meta-analysis of ten studies reported a pooled accuracy of 68.92% (95% CI: 66.04, 71.80; I2 = 100%) among ML models for predicting stunting in children. Three studies indicated a pooled accuracy of 84.39% (95% CI: 80.90, 87.87; I2 = 100%) in predicting wasting. A meta-analysis of four studies indicated a pooled accuracy of 73.60% (95% CI: 70.01, 77.20; I2 = 100%) for ML models predicting underweight status in children.
Conclusions:
This meta-analysis indicated that ML models were observed to have moderate to good performance metrics in predicting malnutrition using DHS data among children under five years.
Related Concept Videos
01:18Steps in Outbreak Investigation
01:10Nature and Nurture
01:23Mechanistic Models: Compartment Models in Individual and Population Analysis