Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators publish new report on Ey e Diseases and Conditions - Keratoconus. According to news reporting from Beijin g, People's Republic of China, by NewsRx journalists, research stated, "This stu dy aims to evaluate the diagnostic performance of a machine learning model (ML m odel) to train junior ophthalmologists in detecting preclinical keratoconus (PKC ). A total of 1,334 corneal topography images (The Pentacam HR system) from 413 keratoconus eyes, 32 PKC eyes and 222 normal eyes were collected." The news correspondents obtained a quote from the research from Peking Union Med ical College Hospital, "Five junior ophthalmologists were trained and annotated the images with or without the suggestions proposed by the ML model. The diagnos tic performance of PKC was evaluated among three groups: junior ophthalmologist group (control group), ML model group and ML model-training junior ophthalmologi st group (test group). The accuracy of the ML model between the eyes of patients with KC and NEs in all three clinics (99% accuracy, area under th e receiver operating characteristic (ROC) curve AUC of 1.00, 99 % s ensitivity, 99% specificity) was higher than that for Belin-Ambr & oacute;sio enhanced ectasia display total deviation (BAD-D) (86% a ccuracy, AUC of 0.97, 97% sensitivity, 69% specifici ty). The accuracy of the ML model between eyes with PKC and NEs in all three cli nics (98% accuracy, AUC of 0.96, 98% sensitivity, 98 % specificity) was higher than that of BAD-D (69% ac curacy, AUC of 0.73, 67% sensitivity, 69% specificit y). The diagnostic accuracy of PKC was 47.5% (95%CI, 0.5-71.6%), 100% (95%CI, 100-100 % ) and 94.4% (95%CI, 14.7-94.7%) in the c ontrol group, ML model group and test group. With the assistance of the proposed ML model, the diagnostic accuracy of junior ophthalmologists improved with stat istical significance (p <0.05). According to the questionn aire of all the junior ophthalmologists, the average score was 4 (total 5) regar ding to the comprehensiveness that the AI model has been in their keratoconus di agnosis learning; the average score was 4.4 (total 5) regarding to the convenien ce that the AI model has been in their keratoconus diagnosis learning."
NETL
NSTL