Comparison of Artificial Intelligent Clinic and Normal Clinic

In this study, the investigators provide participants≤14 years old the artificial intelligent clinic or normal clinic in the purpose of seeking out a better way to make a definite diagnosis with high efficiency and accuracy, and report a prospective, randomized controlled study aiming at comparison of artificial intelligent clinic and normal clinic for diagnosing congenital cataract.

Children ≤14 years old from ophthalmic clinic without treatment were enrolled to a prospective, randomized controlled study. Patients were assigned to two groups: participants in group A went to the artificial intelligent clinic and get the initial diagnosis, while in Group B, the participants went to the normal clinic. Investigators provide the final definite diagnosis from experts for two groups. Investigators compared the accuracy of the diagnosis, time consuming and the satisfaction level between two groups, aiming at comparison of artificial intelligent clinic and normal clinic for diagnosing congenital cataract.

Slit-lamp photography and patient recruitment will be performed in each participating clinic by trained clinical staffs. The clinical staffs, investigators involved in data management and analysis, and experts providing the gold standard diagnosis by consensus in each clinic will be blinded to the group assignment. The study participants, the coordinator, senior consultants, and study personnel responsible for randomisation will not be masked.

Procedure: the initial diagnosis from artificial intelligent clinic Participants in group A assigned to artificial intelligent clinic to get the initial diagnosis after the eye examinations, including images of ocular anterior segment. Procedure: the final definite diagnosis from experts After making the initial diagnosis in artificial intelligent clinic, participants in group A went to get the final definite diagnosis from experts with more than 10 years of clinical experience.

Procedure: the initial diagnosis from normal clinic Participants in group B assigned to normal clinic to get the initial diagnosis after the eye examinations, including images of ocular anterior segment. Procedure: the final definite diagnosis from experts After making the initial diagnosis in normal clinic, participants in group B went to get the final definite diagnosis from experts with more than 10 years of clinical experience.

Participants in group A assigned to artificial intelligent clinic to get the initial diagnosis after the eye examinations, including images of ocular anterior segment.

Participants in group B assigned to normal clinic to get the initial diagnosis after the eye examinations, including images of ocular anterior segment.

After making the initial diagnosis, participants went to get the final definite diagnosis from experts with more than 10 years of clinical experience.

Inclusion Criteria: Paediatric patients from collaborating eye clinics Written informed consents provided Exclusion Criteria: Definitive diagnosis of cataract or other ocular abnormalities Previous eye surgery Can not cooperate with the slip lamp examination Unwilling to participate in this trail

Lin H, Li R, Liu Z, Chen J, Yang Y, Chen H, Lin Z, Lai W, Long E, Wu X, Lin D, Zhu Y, Chen C, Wu D, Yu T, Cao Q, Li X, Li J, Li W, Wang J, Yang M, Hu H, Zhang L, Yu Y, Chen X, Hu J, Zhu K, Jiang S, Huang Y, Tan G, Huang J, Lin X, Zhang X, Luo L, Liu Y, Liu X, Cheng B, Zheng D, Wu M, Chen W, Liu Y. Diagnostic Efficacy and Therapeutic Decision-making Capacity of an Artificial Intelligence Platform for Childhood Cataracts in Eye Clinics: A Multicentre Randomized Controlled Trial. EClinicalMedicine. 2019 Mar 17;9:52-59. doi: 10.1016/j.eclinm.2019.03.001. eCollection 2019 Mar.