ARTIFICIAL INTELLIGENCE

 

Artificial intelligence (AI) for actual clinical practice in glaucoma is still fraught with numerous limitations. Tae Keun Yoo, from the B&VIIT Eye Center, Seoul, Korea, discusses the role of AI in glaucoma in this correspondence published in the Journal of Medical Artificial Intelligence (JMAI).

https://jmai.amegroups.org/article/view/7990/html

First, the criteria for glaucoma diagnosis should be standardized. As commented by Goldmann et al., there is currently a lack of a standardized “ground truth” definition of glaucoma. The spectrum of glaucoma is wide, and there is a shortage of glaucoma experts worldwide. Therefore, the clinical practice patterns in the management of glaucoma may differ from practitioner to practitioner, and the treatment regimen differ. This problem poses many obstacles to the development and clinical validation of diagnostic devices for glaucoma.

For more accurate performance, it is important to compare and standardize glaucoma diagnostic data at as many centers as possible and train the AI model based on this verified dataset.

Second, it is important to analyze the time-series and multimodal data of patients with glaucoma. The evaluation of glaucoma commonly involves measuring intraocular pressure, fundus photography, optical coherence tomography, and visual field analysis. The progression of functional or structural damage during follow-up is an important factor in the diagnosis and treatment of glaucoma. Each measurement reflects only a few clinical aspects of glaucoma.

In addition, errors often occur in one measurement domain; therefore, other domains must be complemented to evaluate glaucoma. Recently, time-series analyses and multimodal deep-learning models have been studied for glaucoma diagnosis. In the future, large-scale data analyses based on these approaches will succeed in a more accurate glaucoma evaluation.

Third, detailed data on neurodegenerative and systemic metabolic conditions should be collected along with glaucoma data to predict progression. In addition, neurodegenerative diseases have been shown to be predictable by fundus photography, and most are closely related to the optic nerve head and the retinal nerve fiber layer in glaucoma. AI technology based on multimodal deep learning is increasingly used to analyze high-definition images in every area to reveal the relationship between systemic diseases and retinal images in greater detail.

Finally, generative AI techniques should be applied to overcome the lack of pathological data. Data shortages frequently occur because of security or privacy issues. Learning about the imbalanced medical data may result in a biased diagnostic model. Data augmentation techniques are required for accurate diagnosis in the clinical field, and recently developed generative deep learning models such as generative adversarial networks (GAN) provide solutions to this problem. Although still in their infancy, diffusion models, which are newly introduced generation technologies after GAN, can generate fundus photographs. As data quality is increasingly improved based on a large amount of data, realistic generative fundus images will be synthesized based on a large amount of data in the future.

In conclusion, various strategies are required to develop AI for glaucoma diagnosis and treatment. As Goldmann et al. commented, this cannot be solved at once and should be based on the interdisciplinary integration and mutual support of all complementary approaches.