NutriScreener: Retrieval-Augmented Multi-Pose Graph Attention Network for Malnourishment Screening

TL;DR

NutriScreener is a novel retrieval-augmented multi-pose graph attention network that accurately detects child malnutrition from images, demonstrating high accuracy, efficiency, and robustness across diverse populations and settings.

Contribution

It introduces NutriScreener, combining CLIP embeddings, knowledge retrieval, and context awareness for scalable malnutrition screening from images.

Findings

Achieves 0.79 recall and 0.82 AUC in clinical tests.

Demonstrates up to 25% recall improvement with demographically matched knowledge.

Reduces anthropometric measurement errors significantly.

Abstract

Child malnutrition remains a global crisis, yet existing screening methods are laborious and poorly scalable, hindering early intervention. In this work, we present NutriScreener, a retrieval-augmented, multi-pose graph attention network that combines CLIP-based visual embeddings, class-boosted knowledge retrieval, and context awareness to enable robust malnutrition detection and anthropometric prediction from children's images, simultaneously addressing generalizability and class imbalance. In a clinical study, doctors rated it 4.3/5 for accuracy and 4.6/5 for efficiency, confirming its deployment readiness in low-resource settings. Trained and tested on 2,141 children from AnthroVision and additionally evaluated on diverse cross-continent populations, including ARAN and an in-house collected CampusPose dataset, it achieves 0.79 recall, 0.82 AUC, and significantly lower anthropometric RMSEs, demonstrating reliable measurement in unconstrained pediatric settings. Cross-dataset results show up to 25% recall gain and up to 3.5 cm RMSE reduction using demographically matched knowledge bases. NutriScreener offers a scalable and accurate solution for early malnutrition detection in low-resource environments.