An artificial intelligence platform for the screening and managing of strabismus

• Published in: Eye (London) 2024-11, Vol.38 (16), p.3101-3107
• Main Authors: Wu, Dawen, Li, Yanfei, Zhang, Haixian, Yang, Xubo, Mao, Yiji, Chen, Bingjie, Feng, Yi, Chen, Liang, Zou, Xingyu, Nie, Yan, Yin, Teng, Yang, Zeyi, Liu, Jingyu, Shang, Wenyi, Yang, Guoyuan, Liu, Longqian
• Format: Article
• Language: English
• Subjects: 692/699/3161/3178; 692/700/139/1735; Accuracy; Adolescent; Adult; Artificial Intelligence; Binocular vision; Child; Child, Preschool; Cornea; Female; Humans; Infant; Laboratory Medicine; Male; Medicine; Medicine & Public Health; Middle Aged; Ophthalmology; Pharmaceutical Sciences/Technology; Sensitivity and Specificity; Strabismus; Strabismus - diagnosis; Strabismus - therapy; Surgery; Surgical Oncology; Vision Screening - instrumentation; Vision Screening - methods; Vision, Binocular - physiology; Young Adult
• ISSN: 0950-222X; 1476-5454; 1476-5454
• DOI: 10.1038/s41433-024-03228-5

Objectives Considering the escalating incidence of strabismus and its consequential jeopardy to binocular vision, there is an imperative demand for expeditious and precise screening methods. This study was to develop an artificial intelligence (AI) platform in the form of an applet that facilitates the screening and management of strabismus on any mobile device. Methods The Visual Transformer (VIT_16_224) was developed using primary gaze photos from two datasets covering different ages. The AI model was evaluated by 5-fold cross-validation set and tested on an independent test set. The diagnostic performance of the AI model was assessed by calculating the Accuracy, Precision, Specificity, Sensitivity, F1-Score and Area Under the Curve (AUC). Results A total of 6194 photos with corneal light-reflection (with 2938 Exotropia, 1415 Esotropia, 739 Vertical Deviation and 1562 Orthotropy) were included. In the internal validation set, the AI model achieved an Accuracy of 0.980, Precision of 0.941, Specificity of 0.979, Sensitivity of 0.958, F1-Score of 0.951 and AUC of 0.994. In the independent test set, the AI model achieved an Accuracy of 0.967, Precision of 0.980, Specificity of 0.970, Sensitivity of 0.960, F1-Score of 0.975 and AUC of 0.993. Conclusions Our study presents an advanced AI model for strabismus screening which integrates electronic archives for comprehensive patient histories. Additionally, it includes a patient-physician interaction module for streamlined communication. This innovative platform offers a complete solution for strabismus care, from screening to long-term follow-up, advancing ophthalmology through AI technology for improved patient outcomes and eye care quality.