NutriAI: AI-Powered Child Malnutrition Assessment in Low-Resource Environments

Abstract

Malnutrition among infants and young children is a pervasive public health concern, particularly in developing countries where resources are limited. Millions of children globally suffer from malnourishment and its complications1. Despite the best efforts of governments and organizations, malnourishment persists and remains a leading cause of morbidity and mortality among children under five. Physical measurements, such as weight, height, middle-upper-arm-circumference (muac), and head circumference are commonly used to assess the nutritional status of children. However, this approach can be resource-intensive and challenging to carry out on a large scale. In this research, we are developing NutriAI, a low-cost solution that leverages small sample size classification approach to detect malnutrition by analyzing 2D images of the subjects in multiple poses. The proposed solution will not only reduce the workload of health workers but also provide a more efficient means of monitoring the nutritional status of children. On the dataset prepared as part of this research, the baseline results highlight that the modern deep learning approaches can facilitate malnutrition detection via anthropometric indicators in the presence of diversity with respect to age, gender, physical characteristics, and accessories including clothing.

Classification of stunted and normal children using novel facial image database and convolutional neural network

“…For example, the accuracy of AlexNet with epochs 60 was obtained by averaging the accuracy of each class, i. The work in [21] introduced a method with similar aims, yet with a broader approach, using facial and body images with five different body poses in parallel. Because of the parallel approach, the image database prepared for training and validation supposedly consists of face and body images.…”

“…Based on reports from recent literature, research interest in predicting people's nutritional status based on images and CNNs is growing [9,17,20,21]. However, research using children's facial images as input to deep learning architecture is limited.…”

“…However, research using children's facial images as input to deep learning architecture is limited. These images are not available for other researchers to use for further research [9] or are captured under uncontrolled settings [21]. These factors can lead to difficulty in analyzing, comparing, and benchmarking the performances of several CNNs.…”

“…Research on deep learning used for the detection/classification of nutritional status based on body and facial images has been proposed by several researchers [9,17,20,21]. In [20], researchers proposed a system to predict body dimensions based on height and waist circumference.…”

“…In [21], a method to assess children's malnutrition status using facial images, several full-body images, and CNNs was proposed. The proposed system was applied to three image databases: 1. malnutrition database consisting of children's facial and body images collected from the internet, 2. adult facial and full body images with six different poses, and 3. school-age children's facial and full body images with six different poses.…”