Experimental eye research · 2025
Advancements in strabismus diagnosis: A comprehensive systematic review of artificial intelligence and digital health applications.
СтатьяСистематический обзорНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Rajavi Zhale, Hatami Firouze, Khosravi Mirzaei Sina, Lateef Mohammed, Khorrami Zahra, Jaldian Hemn Baghban, Haseli-Mofrad Azadeh, Sheibani Kourosh, Yazdanpanah Mahdi, Shahriari Mohammad Hasan, Sabbaghi Hamideh
Аннотация
PURPOSE: To review the accuracy of artificial intelligence (AI) and digital health applications in the screening and diagnosis of strabismus.
METHODS: In this systematic review, we searched for articles addressing the use of AI in the screening and diagnosis of strabismus across several databases, including ScienceDirect, Scopus, Web of Science (WoS), PubMed, Association for Computing Machinery Digital Library (ACM DL), and the Institute of Electrical and Electronics Engineers (IEEE). The full texts of the 37 most relevant articles were selected and reviewed. The methodological quality of each study was independently assessed by two authors using the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool.
RESULTS: Out of the 37 articles reviewed, 24 pertained to AI-based applications, while 13 focused on other digital health applications for screening and diagnosing strabismus. Studies centered on digital health applications utilizing AI techniques commonly reported accuracy, sensitivity, and specificity, with ranges of 0.42-1.0, 0.33-1.0, and 0.76-1.0, respectively. Additionally, the area under the curve (AUC) was found to be between 0.98 and 0.99. In contrast, the studies investigating digital health applications without an AI basis reported parameters for the Intraclass Correlation Coefficient, kappa, and AUC, with ranges spanning 60 %-100 %, 61 %-100 %, and 53 %-74 %, respectively.
CONCLUSIONS: Our review highlights the promising potential of AI and digital health applications in diagnosing strabismus. AI algorithms have proven capable of achieving high levels of accuracy in detecting strabismus, analyzing features such as eye position, alignment, and movement meticulously.
METHODS: In this systematic review, we searched for articles addressing the use of AI in the screening and diagnosis of strabismus across several databases, including ScienceDirect, Scopus, Web of Science (WoS), PubMed, Association for Computing Machinery Digital Library (ACM DL), and the Institute of Electrical and Electronics Engineers (IEEE). The full texts of the 37 most relevant articles were selected and reviewed. The methodological quality of each study was independently assessed by two authors using the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool.
RESULTS: Out of the 37 articles reviewed, 24 pertained to AI-based applications, while 13 focused on other digital health applications for screening and diagnosing strabismus. Studies centered on digital health applications utilizing AI techniques commonly reported accuracy, sensitivity, and specificity, with ranges of 0.42-1.0, 0.33-1.0, and 0.76-1.0, respectively. Additionally, the area under the curve (AUC) was found to be between 0.98 and 0.99. In contrast, the studies investigating digital health applications without an AI basis reported parameters for the Intraclass Correlation Coefficient, kappa, and AUC, with ranges spanning 60 %-100 %, 61 %-100 %, and 53 %-74 %, respectively.
CONCLUSIONS: Our review highlights the promising potential of AI and digital health applications in diagnosing strabismus. AI algorithms have proven capable of achieving high levels of accuracy in detecting strabismus, analyzing features such as eye position, alignment, and movement meticulously.