AI Workflow, External Validation, and Development in Eye Disease Diagnosis

作者：Qingyu Chen, Tiarnán D L Keenan, Elvira Agrón, Alexis Allot, Emily Guan, Bryant Duong, Amr Elsawy, Benjamin Hou, Cancan Xue, S. Bhandari, Geoffrey Broadhead, Chantal Cousineau-Krieger, Ellen Davis, William G. Gensheimer, Cyrus A. Golshani, David Josip Grašić, Seema Gupta, Luis J. Haddock, Eleni K. Konstantinou, Tania Lamba, Michele Maiberger, Dimosthenis Mantopoulos, Mitul C. Mehta, Ayman G. Elnahry, Mutaz AL-Nawaflh, Arnold Oshinsky, Brittany E. Powell, Boonkit Purt, Soo Young Shin, Hillary C. Stiefel, Alisa T. Thavikulwat, Keith James Wroblewski, Yih Chung Tham, Chui Ming Gemmy Cheung, Ching‐Yu Cheng, Emily Y. Chew, Michelle R. Hribar, Michael F. Chiang, Zhiyong Lu · 发表于：JAMA Network Open · 年份：2025 · DOI：10.1001/jamanetworkopen.2025.17204 · 被引用次数：11 · 研究领域：Retinal Imaging and Analysis、Retinal Diseases and Treatments、Artificial Intelligence in Healthcare and Education

Importance: Timely disease diagnosis is challenging due to limited clinical availability and growing burdens. Although artificial intelligence (AI) has shown expert-level diagnostic accuracy, a lack of downstream accountability, including workflow integration, external validation, and further development, continues to hinder its clinical adoption. Objective: To address gaps in the downstream accountability of medical AI through a case study on age-related macular degeneration (AMD) diagnosis and severity classification. Design, Setting, and Participants: This diagnostic study developed and evaluated an AI-assisted diagnostic and classification workflow for AMD. Four rounds of diagnostic assessments (accuracy and time) were conducted with 24 clinicians from 12 institutions. Each round was randomized and alternated between manual (clinician diagnosis) and manual plus AI (clinician assisted by AI diagnosis), with a 1-month washout period. In total, 2880 AMD risk features were evaluated across 960 images from 240 Age-Related Eye Disease Study patient samples, both with and without AI assistance. For further development, the original DeepSeeNet model was enhanced into the DeepSeeNet+ model using 39 196 additional images from the US population and tested on 3 datasets, including an external set from Singapore. Exposure: Age-related macular degeneration risk features. Main Outcomes and Measures: The F1 score for accuracy (Wilcoxon rank sum test) and diagnostic time (linear mixed-eff...