Tien-En Tan, FRCOphth, Ayesha Anees, MSc, Cheng Chen, MSc, Shaohua Li, PhD, Xinxing Xu, PhD, Zengxiang Li, PhD, Zhe Xiao, PhD, Yechao Yang, BSc, Xiaofeng Lei, MSc, Marcus Ang, FRCS (Ed), Audrey Chia, FRANZCO, Shu Yen Lee, FRCS (Ed), Edmund Yick Mun Wong, FRCS (Ed), Ian Yew San Yeo, ProfFRCS (Ed), Yee Ling Wong, PhD, Quan V Hoang, MD, Ya Xing Wang, MD, Mukharram M Bikbov, MD, Vinay Nangia, MD, Jost B Jonas, ProfMD, Yen-Po Chen, MD, Wei-Chi Wu, ProfMD, Kyoko Ohno-Matsui, ProfMD, Tyler Hyungtaek Rim, MD, Yih-Chung Tham, PhD, Rick Siow Mong Goh, PhD, Haotian Lin, ProfMD, Hanruo Liu, MD, Ningli Wang, ProfMD, Weihong Yu, ProfMD, Donald Tiang Hwee Tan, ProfFRCS (Ed), Leopold Schmetterer, ProfPhD, Ching-Yu Cheng, ProfMD, Youxin Chen, ProfMD, Chee Wai Wong, MBBS, Gemmy Chui Ming Cheung, ProfFRCOphth, Seang-Mei Saw, ProfPhD, Tien Yin Wong, ProfMD, Yong Liu, PhD, and Daniel Shu Wei Ting, MD
Summary: Background: By 2050, almost 5 billion people globally are projected to have myopia, of whom 20% are likely to have high myopia with clinically significant risk of sight-threatening complications such as myopic macular degeneration. These are diagnoses that typically require specialist assessment or measurement with multiple unconnected pieces of equipment. Artificial intelligence (AI) approaches might be effective for risk stratification and to identify individuals at highest risk of visual loss. However, unresolved challenges for AI medical studies remain, including paucity of transparency, auditability, and traceability. Methods: In this retrospective multicohort study, we developed and tested retinal photograph-based deep learning algorithms for detection of myopic macular degeneration and high myopia, using a total of 226 686 retinal images. First we trained and internally validated the algorithms on datasets from Singapore, and then externally tested them on datasets from China, Taiwan, India, Russia, and the UK. We also compared the performance of the deep learning algorithms against six human experts in the grading of a randomly selected dataset of 400 images from the external datasets. As proof of concept, we used a blockchain-based AI platform to demonstrate the real-world application of secure data transfer, model transfer, and model testing across three sites in Singapore and China. Findings: The deep learning algorithms showed robust diagnostic performance with areas under the receiver operating characteristic curves [AUC] of 0·969 (95% CI 0·959–0·977) or higher for myopic macular degeneration and 0·913 (0·906–0·920) or higher for high myopia across the external testing datasets with available data. In the randomly selected dataset, the deep learning algorithms outperformed all six expert graders in detection of each condition (AUC of 0·978 [0·957–0·994] for myopic macular degeneration and 0·973 [0·941–0·995] for high myopia). We also successfully used blockchain technology for data transfer, model transfer, and model testing between sites and across two countries. Interpretation: Deep learning algorithms can be effective tools for risk stratification and screening of myopic macular degeneration and high myopia among the large global population with myopia. The blockchain platform developed here could potentially serve as a trusted platform for performance testing of future AI models in medicine. Funding: None.