NutriScreener: Retrieval-Augmented Multi-Pose Graph Attention Network for Malnourishment Screening
It addresses the problem of laborious and poorly scalable malnutrition screening for children in low-resource settings, offering a scalable and accurate solution.
The paper tackles child malnutrition screening by developing NutriScreener, a retrieval-augmented multi-pose graph attention network that uses images to detect malnutrition and predict anthropometrics, achieving 0.79 recall, 0.82 AUC, and significant RMSE reductions in clinical and cross-dataset evaluations.
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.