External validation of a deep learning detection system for glaucomatous optic neuropathy: a real-world multicentre study

OBJECTIVES

To conduct an external validation of an automated artificial intelligence (AI) diagnostic system using fundus photographs from a real-life multicentre cohort.

METHODS

We designed external validation in multiple scenarios, consisting of 3049 images from Qilu Hospital of Shandong University in China (QHSDU, validation dataset 1), 7495 images from three other hospitals in China (validation dataset 2), and 516 images from high myopia (HM) population of QHSDU (validation dataset 3). The corresponding sensitivity, specificity and accuracy of this AI diagnostic system to identify glaucomatous optic neuropathy (GON) were calculated.

RESULTS

In validation datasets 1 and 2, the algorithm yielded accuracy of 93.18% and 91.40%, area under the receiver operating curves (AUC) of 95.17% and 96.64%, and significantly higher sensitivity of 91.75% and 91.41%, respectively, compared to manual graders. On the subsets complicated with retinal comorbidities, such as diabetic retinopathy or age-related macular degeneration, in validation datasets 1 and 2, the algorithm achieved accuracy of 87.54% and 93.81%, and AUC of 97.02% and 97.46%, respectively. In validation dataset 3, the algorithm achieved comparable accuracy of 81.98% and AUC of 87.49%, with a sensitivity of 83.61% and specificity of 81.76% on GON recognition specifically in the HM population.

CONCLUSIONS

With acceptable generalization capability across varying levels of image quality, different clinical centres, or certain retinal comorbidities, such as HM, the automatic AI diagnostic system had the potential to provide expert-level glaucoma detection.