Study: Artificial Intelligence for Early Detection of Pediatric Eye Diseases Using Mobile Photos
In a study published online in JAMA Network Open on August 6, an AI model demonstrates high performance in correctly recognizing myopia, strabismus, and ptosis using smartphone images.
In a cross-sectional study, Qin Shu, M.D., of Shanghai Jiao Tong University School of Medicine, and associates created an AI model to recognize myopia, strabismus, and ptosis using cellphone photos. The model was constructed from 1,419 pictures, representing 476 patients. Of the pictures, 473 binocular and 946 monocular images were utilized to diagnose strabismus and myopia, respectively.
The model’s sensitivity for identifying ptosis, strabismus, and myopia was shown to be good (0.84, 0.73, and 0.85, respectively). The model demonstrated similar effectiveness in diagnosing eye diseases in children, both male and female, during sex subgroup analysis. There were variations in the ability to diagnose eye conditions among various age groups.
“The detection model using AI showed strong performance in accurately identifying myopia, strabismus, and ptosis using only smartphone images,” the authors write. “These results suggest that it can assist families in screening children for myopia, strabismus, and ptosis, facilitating early identification and reducing the risk of visual function loss and severe problems due to delayed screening.”
For more information: Artificial Intelligence for Early Detection of Pediatric Eye Diseases Using Mobile Photos, JAMA Network Open , DOI: 10.1001/jamanetworkopen.2024.25124
more recommended stories
SBRT and Sorafenib: A New Hope for Liver Cancer PatientsRecent findings from the Phase III.
Surgeons Slow to Adopt Biomaterials for Bone DefectsTwo million bone transplants are performed.
First-of-Its-Kind Gene-Edited Pig Kidney: Towana’s New LifeSurgeons at NYU Langone Health have.
AI Advancing Mammography Density predictionIn a new article published in.
Innovative Head and Neck Reconstruction with Pedicled FlapsResearchers at Osaka Metropolitan University have.
purpleDx App for Remote Lung MonitoringelectronRx, a leading digital medicine and.
New tool accelerates drug discoveryDrug Discovery with new tool – The.
New Pipeline Identifies Alzheimer’s Disease BiomarkersColumbia University Mailman School of Public.
Novel Drug Design for Parkinson’s Disease via GPR6 InhibitionResearchers at the University of Southern.
AI Boosts Organoid Research with Quality PredictionResearchers from Kyushu University and Nagoya.
Leave a Comment