<![CDATA[Stunting affects a substantial proportion of Indonesian children under five and is monitored through routine anthropometric measurement at posyandu, community health posts staffed largely by volunteer cadres. This measurement depends on calibrated instruments and consistent technique, which are not uniformly available across sites, so a low-cost screening aid could extend coverage where conventional practice is weakest. This study aims to develop AI-StuntDetect, a web-based system that estimates children's height and weight from a single mobile-phone photograph, classifies nutritional status, and evaluates whether its image-derived estimates add value beyond simple demographic predictors. A Convolutional Neural Network estimates weight directly from the image, while MediaPipe Pose landmarks are converted into body-proportion features and regressed onto height with a Random Forest. The models were developed on 117 children (1,593 images) using child-level partitioning and validated externally on 48 children from three independent posyandu. Performance was compared against a mean-value baseline and against age-only and age-plus-sex regressions fitted to the training data, and predicted heights were classified against the WHO and Kemenkes reference standards. Height estimation achieved an MAE of 4.092 cm and an R² of 0.863, reducing error by 31.9% relative to the strongest training-derived baseline. Weight estimation achieved an MAE of 1.771 kg and an R² of 0.590 but did not improve on the age-only regression (1.675 kg). Nutritional status was classified with 70.8% accuracy and a macro-averaged F1 of 0.546, with weak sensitivity for the intermediate stunted category (0.167). A single photograph therefore supports useful height estimation, whereas image-based weight estimation adds nothing beyond what age predicts. AI-StuntDetect is best characterized as an experimental screening prototype suited to triage under manual confirmation.]]>
