September 3, 2024
By Dwight Akerman, OD, MBA, FAAO, FBCLA, FIACLE
Photo Credit: Dreamstime Photos
The study “Artificial Intelligence for Early Detection of Pediatric Eye Diseases Using Mobile Photos” by Shu Q, Pang J, Liu Z, et al., published in JAMA Network Open in 2024, discusses the development of an A.I. model aimed at identifying pediatric eye diseases using mobile photographs. The importance of early detection of pediatric eye diseases is highlighted, as traditional screening procedures can be expensive and time consuming. Utilizing artificial intelligence to assess children’s eye conditions from mobile photographs could enable convenient and early identification of eye disorders in a home setting.
The study aimed to develop an A.I. model capable of identifying myopia, strabismus, and ptosis using mobile photographs. It was conducted at the Department of Ophthalmology of Shanghai Ninth People’s Hospital and included children who were diagnosed with myopia, strabismus, or ptosis. The researchers used a deep learning-based model to identify these eye conditions. Its performance was evaluated using various metrics such as sensitivity, specificity, accuracy, the area under the curve (AUC), positive predictive values (PPV), negative predictive values (NPV), positive likelihood ratios (P-LR), negative likelihood ratios (N-LR), and the F1-score.
The study utilized a total of 1,419 images obtained from 476 patients, of which 225 were female, and 299 were aged between 6 and 12 years. Among these images, 946 monocular images were used to identify myopia and ptosis, and 473 binocular images were used to identify strabismus. The A.I. model demonstrated good sensitivity in detecting myopia, strabismus, and ptosis, with values of 0.84, 0.73, and 0.85, respectively. Furthermore, the model showed comparable performance in identifying eye disorders in both female and male children during sex subgroup analysis.
The researchers also conducted age subgroup analysis and found differences in the identification of eye disorders among different age subgroups. Overall, the A.I. model exhibited strong performance in accurately identifying myopia, strabismus, and ptosis using only smartphone images. These results suggest that the developed model could facilitate the early detection of pediatric eye diseases in a convenient manner at home.
In conclusion, the study demonstrates the potential of A.I. in the early detection of pediatric eye diseases using mobile photos. The development of the A.I. model represents a significant advancement in the field, as it has shown promising results in accurately identifying common pediatric eye disorders. If validated and implemented on a larger scale, such a model could potentially revolutionize pediatric eye disease screening and contribute to early interventions that improve patient outcomes.
Abstract
Artificial Intelligence for Early Detection of Pediatric Eye Diseases Using Mobile Photos
Qin Shu, MD, Jiali Pang, MS, Zijia Liu, PhD, et al.
Importance: Identifying pediatric eye diseases at an early stage is a worldwide issue. Traditional screening procedures depend on hospitals and ophthalmologists, which are expensive and time-consuming. Using artificial intelligence (AI) to assess children’s eye conditions from mobile photographs could facilitate convenient and early identification of eye disorders in a home setting.
Objective: To develop an AI model to identify myopia, strabismus, and ptosis using mobile photographs.
Design, Setting, and Participants: This cross-sectional study was conducted at the Department of Ophthalmology of Shanghai Ninth People’s Hospital from October 1, 2022, to September 30, 2023, and included children who were diagnosed with myopia, strabismus, or ptosis.
Main Outcomes and Measures: A deep learning-based model was developed to identify myopia, strabismus, and ptosis. The performance of the model was assessed using sensitivity, specificity, accuracy, the area under the curve (AUC), positive predictive values (PPV), negative predictive values (NPV), positive likelihood ratios (P-LR), negative likelihood ratios (N-LR), and the F1-score. GradCAM++ was utilized to visually and analytically assess the impact of each region on the model. A sex subgroup analysis and an age subgroup analysis were performed to validate the model’s generalizability.
Results: A total of 1419 images obtained from 476 patients (225 female [47.27%]; 299 [62.82%] aged between 6 and 12 years) were used to build the model. Among them, 946 monocular images were used to identify myopia and ptosis, and 473 binocular images were used to identify strabismus. The model demonstrated good sensitivity in detecting myopia (0.84 [95% CI, 0.82-0.87]), strabismus (0.73 [95% CI, 0.70-0.77]), and ptosis (0.85 [95% CI, 0.82-0.87]). The model showed comparable performance in identifying eye disorders in both female and male children during sex subgroup analysis. There were differences in identifying eye disorders among different age subgroups.
Conclusions and Relevance: In this cross-sectional study, the AI model demonstrated strong performance in accurately identifying myopia, strabismus, and ptosis using only smartphone images. These results suggest that such a model could facilitate the early detection of pediatric eye diseases in a convenient manner at home.
Shu, Q., Pang, J., Liu, Z., Liang, X., Chen, M., Tao, Z., … & Li, L. (2024). Artificial Intelligence for Early Detection of Pediatric Eye Diseases Using Mobile Photos. JAMA Network Open, 7(8), e2425124-e2425124.
DOI: http://doi.org/10.1001/jamanetworkopen.2024.25124
For more on A.I. in Eye Care, download this proceedings piece: “The Artificial Intelligence Revolution: Practical Applications in Eye Care.”
