The Development of a Real-Time Artificial Intelligence System Using a Convolutional Neural Network for the Assessment of Infant Head Control.

INTRODUCTION: To develop a real-time artificial intelligence (AI) system using a convolutional neural network for the assessment of infant head control (good or poor) during the traction response. METHODS: Infants aged 3-6 months who received community-based group health checkups and whose guardians provided informed consent were enrolled in this study. Videos were recorded during the pull-to-sit test conducted by a pediatrician. The collected videos were divided into training and test datasets. Training data were extracted as image frames and labeled according to the pediatrician's judgment. After supervised machine learning, the AI system was evaluated using the test dataset, and the sensitivity, specificity, and detection rate were calculated. RESULTS: Altogether, 184 videos were collected and divided into the training (n = 110) and test (n = 74) datasets. The training and test datasets included 103 (93.6%) and 64 (86.5%) videos, respectively, showing infants with good head control. After machine learning, the screening AI system had sensitivity and specificity (95% confidence interval) values of 50.0% (18.7%-81.3%) and 98.4% (91.6%-100%), respectively. The detection rate was 100%. CONCLUSIONS: The proposed AI-based assessment system was able to identify good head control with high specificity during the pull-to-sit test but demonstrated limited sensitivity for detecting poor head control, suggesting a supportive rather than a standalone clinical role.