Peer-reviewed article
Using deep learning to monitor children’s nutritional status for child stunting identification
Shijia Luo, Yuan Wang, Rongrong Wu, Yang Zhaoxin, Hui Gao et al. ·
Summary
Written by AI, not yet AICS's view · claude-haiku-4-5-20251001This study develops a deep learning model called the Intelligent Nutritional Monitoring Model (INMM) to identify child stunting using demographic and anthropometric data. The model uses age, sex, height, weight, and body mass index to classify whether children are stunted. Testing on two large public health datasets (NHANES from the US and NFHS-5 from India) shows the model performs better than traditional machine learning approaches. The framework is designed to be computationally efficient and scalable for use in health screening programs.
Key points
- The model formulates stunting identification as a binary classification problem using routinely available demographic and anthropometric variables
- The INMM uses feature extraction, fusion, and hierarchical attention mechanisms to model interactions among child-level attributes
- Comparative testing shows the proposed method achieves stronger classification performance than traditional machine learning, mainstream deep learning, and transformer-based baselines
- The model was evaluated on two public health survey datasets: NHANES and NFHS-5, under a unified protocol
- The framework maintains computational efficiency while achieving high effectiveness
Limitations
The study evaluates the model only on structured survey data with pre-existing anthropometric measurements; it does not address real-world implementation challenges such as data collection in resource-limited settings, nor does it validate whether earlier identification through this method actually leads to improved health outcomes for stunted children. The document does not report specific performance metrics or discuss how the model performs across different age groups or populations.
Abstract
Introduction: Children's nutritional health remains a major public health concern, and accurate early identification of growth related risks is essential for timely screening and intervention. This study proposes a deep learning based framework for monitoring children's nutritional status for child stunting identification. Methods: The task is formulated as a supervised binary classification problem, in which each child is represented by routinely available demographic and anthropometric variables, including age, sex, height, weight, and body mass index. Based on these structured inputs, the proposed Intelligent Nutritional Monitoring Model (INMM) learns discriminative latent representations and predicts whether a child is stunted. The model adopts a compact feature extraction architecture with feature fusion and hierarchical attention, enabling effective modeling of informative interactions among child level attributes while maintaining computational efficiency. To evaluate the proposed method, experiments are conducted on two public health survey datasets, NHANES and NFHS 5, under a unified preprocessing, training, and evaluation protocol. Results and Discussion: Comparative results against traditional machine learning, mainstream deep learning, lightweight tabular modeling, and transformer based tabular baselines show that the proposed method achieves the strongest overall classification performance on both datasets while preserving a favorable effectiveness efficiency trade off. Additional ablation results further confirm the contribution of feature extraction, fusion, attention, and prediction design to the final performance. These findings indicate that the proposed framework provides an effective and scalable solution for data driven child stunting identification from structured health survey data.