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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Khan, Misaal, Vatsa, Mayank, Singh, Kuldeep, Singh, Richa
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912721324212224
author Khan, Misaal
Vatsa, Mayank
Singh, Kuldeep
Singh, Richa
author_facet Khan, Misaal
Vatsa, Mayank
Singh, Kuldeep
Singh, Richa
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_16566
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle NutriScreener: Retrieval-Augmented Multi-Pose Graph Attention Network for Malnourishment Screening
Khan, Misaal
Vatsa, Mayank
Singh, Kuldeep
Singh, Richa
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title NutriScreener: Retrieval-Augmented Multi-Pose Graph Attention Network for Malnourishment Screening
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2511.16566