Aims: To identify the characteristic retinal neurovascular changes in patients in different stages of nondiabetic chronic kidney disease (CKD) and to develop a model for the accurate diagnosis of nondiabetic CKD.
Methods: Peripapillary retinal nerve fiber layer (pRNFL) thickness and average macular ganglion cell-inner plexiform layer (GC-IPL) thickness of nondiabetic CKD patients and healthy controls (HC) were evaluated by spectral-domain optical coherence tomography (OCT). The vessel density (VD) and perfusion density (PD) of the macula were obtained from optical coherence tomography angiography (OCTA). The estimated glomerular filtration rate (eGFR) was obtained to access the kidney function of CKD patients. Multiple linear regression models were used to adjust for confounding factors in statistical analyzes. The diagnostic capabilities of the parameters were evaluated by logistic regression models.
Results: 131 nondiabetic CKD patients and 62 HC entered the study. eGFR was found significantly associated with parafoveal VD and PD (average PD: β = 0.000 4, P_adjusted < 0.001) in various sectors. Thinning of pRNFL (β = -6.725, P_adjusted < 0.001) and GC-IPL (β = -4.542, P_adjusted < 0.001), as well as decreased VD (β = -2.107, P_- adjusted < 0.001) and PD (β = -0.057, P_adjusted = 0.032 8) were found in CKD patients. Thinning of pRNFL and deteriorated perifoveal vasculature were found in early CKD, and the parafoveal and foveal VD significantly declined in advanced CKD. Logistic regression models were employed, and selected neurovascular parameters showed an AUC of 0.853 (95% Confidence Interval [CI]: 0.795 to 0.910) in distinguishing CKD patients from HC.
Conclusions: Distinctive retinal neurovascular characteristics could be observed in nondiabetic CKD patients of different severities. Our results suggest that retinal manifestations could be valuable in the screening, diagnosis, and follow-up evaluation of patients with CKD.

Aims: To identify the characteristic retinal neurovascular changes in patients in different stages of nondiabetic chronic kidney disease (CKD) and to develop a model for the accurate diagnosis of nondiabetic CKD.
Methods: Peripapillary retinal nerve fiber layer (pRNFL) thickness and average macular ganglion cell-inner plexiform layer (GC-IPL) thickness of nondiabetic CKD patients and healthy controls (HC) were evaluated by spectral-domain optical coherence tomography (OCT). The vessel density (VD) and perfusion density (PD) of the macula were obtained from optical coherence tomography angiography (OCTA). The estimated glomerular filtration rate (eGFR) was obtained to access the kidney function of CKD patients. Multiple linear regression models were used to adjust for confounding factors in statistical analyzes. The diagnostic capabilities of the parameters were evaluated by logistic regression models.
Results: 131 nondiabetic CKD patients and 62 HC entered the study. eGFR was found significantly associated with parafoveal VD and PD (average PD: β = 0.000 4, P_adjusted < 0.001) in various sectors. Thinning of pRNFL (β = -6.725, P_adjusted < 0.001) and GC-IPL (β = -4.542, P_adjusted < 0.001), as well as decreased VD (β = -2.107, P_adjusted < 0.001) and PD (β = -0.057, P_adjusted = 0.032 8) were found in CKD patients. Thinning of pRNFL and deteriorated perifoveal vasculature were found in early CKD, and the parafoveal and foveal VD significantly declined in advanced CKD. Logistic regression models were employed, and selected neurovascular parameters showed an AUC of 0.853 (95% Confidence Interval [CI]: 0.795 to 0.910) in distinguishing CKD patients from HC.
Conclusions: Distinctive retinal neurovascular characteristics could be observed in nondiabetic CKD patients of different severities. Our results suggest that retinal manifestations could be valuable in the screening, diagnosis, and follow-up evaluation of patients with CKD.

Background: Research innovations inoculardisease screening, diagnosis, and management have been boosted by deep learning (DL) in the last decade. To assess historical research trends and current advances, we conducted an artifcial intelligence (AI)–human hybrid analysis of publications on DL in ophthalmology.

Methods: All DL-related articles in ophthalmology, which were published between 2012 and 2022 from Web of Science, were included. 500 high-impact articles annotated with key research information were used to fne-tune alarge language models (LLM) for reviewing medical literature and extracting information. After verifying the LLM's accuracy in extracting diseases and imaging modalities, we analyzed trend of DL in ophthalmology with 2 535 articles. 

Results: Researchers using LLM for literature analysis were 70% (p= 0.000 1) faster than those who did not, while achieving comparable accuracy (97% versus 98%, p = 0.768 1). The field of DL in ophthalmology has grown 116% annually, paralleling trends of the broader DL domain. The publications focused mainly on diabetic retinopathy (p = 0.000 3), glaucoma (p = 0.001 1), and age-related macular diseases (p = 0.000 1) using retinal fundus photographs (FP, p = 0.001 5) and optical coherence tomography (OCT, p = 0.000 1). DL studies utilizing multimodal images have been growing, with FP and OCT combined being the most frequent. Among the 500 high-impact articles, laboratory studies constituted the majority at 65.3%. Notably, a discernible decline in model accuracy was observed when categorizing by study design, notwithstanding its statistical insignificance. Furthermore, 43 publicly available ocular image datasets were summarized. 

Conclusion: This study has characterized the landscape of publications on DL in ophthalmology, by identifying the trends and breakthroughs among research topics and the fast-growing areas. This study provides an efcient framework for combined AI–human analysis to comprehensively assess the current status and future trends in the feld. 

Background: Research innovations inoculardisease screening, diagnosis, and management have been boosted by deep learning (DL) in the last decade. To assess historical research trends and current advances, we conducted an artifcial intelligence (AI)–human hybrid analysis of publications on DL in ophthalmology.

Methods: All DL-related articles in ophthalmology, which were published between 2012 and 2022 from Web of Science, were included. 500 high-impact articles annotated with key research information were used to fne-tune alarge language models (LLM) for reviewing medical literature and extracting information. After verifying the LLM's accuracy in extracting diseases and imaging modalities, we analyzed trend of DL in ophthalmology with 2 535 articles. 

Results: Researchers using LLM for literature analysis were 70% (p = 0.000 1) faster than those who did not, while achieving comparable accuracy (97% versus 98%, p = 0.768 1). The field of DL in ophthalmology has grown 116% annually, paralleling trends of the broader DL domain. The publications focused mainly on diabetic retinopathy (p = 0.000 3), glaucoma (p = 0.001 1), and age-related macular diseases (p = 0.000 1) using retinal fundus photographs (FP, p = 0.001 5) and optical coherence tomography (OCT, p = 0.000 1). DL studies utilizing multimodal images have been growing, with FP and OCT combined being the most frequent. Among the 500 high-impact articles, laboratory studies constituted the majority at 65.3%. Notably, a discernible decline in model accuracy was observed when categorizing by study design, notwithstanding its statistical insignificance. Furthermore, 43 publicly available ocular image datasets were summarized. 

Conclusion: This study has characterized the landscape of publications on DL in ophthalmology, by identifying the trends and breakthroughs among research topics and the fast-growing areas. This study provides an efcient framework for combined AI–human analysis to comprehensively assess the current status and future trends in the feld. 

Artificial intelligence (AI) is about simulating and expanding human intelligence. AI based on deep learning (DL) can analyze images well by using their inherent features, such as outlines, frames and so on. As researchers generally diagnoses ocular fundus diseases by images, it makes sense to apply AI to fundus examination. In ophthalmology, AI has achieved doctor-like performance in detecting multiple ocular fundus diseases through optical coherence tomography (OCT) images, fundus photographs, and ultra-wide-field (UWF) images. It has also been widely used in disease progression prediction. Nonetheless, there are also some potential challenges with AI application in ophthalmology, one of which is the black-box problem. Researchers are devoted to developing more interpretable deep learning systems (DLS) and confirming their clinical feasibility. This review describes a summary of the state-of-the-art AI application in the most popular ocular fundus diseases, potential challenges and the path forward.

Artificial intelligence (AI) is about simulating and expanding human intelligence. AI based on deep learning (DL) can analyze images well by using their inherent features, such as outlines, frames and so on. As researchers generally diagnoses ocular fundus diseases by images, it makes sense to apply AI to fundus examination. In ophthalmology, AI has achieved doctor-like performance in detecting multiple ocular fundus diseases through optical coherence tomography (OCT) images, fundus photographs, and ultra-wide-field (UWF) images. It has also been widely used in disease progression prediction. Nonetheless, there are also some potential challenges with AI application in ophthalmology, one of which is the black-box problem. Researchers are devoted to developing more interpretable deep learning systems (DLS) and confirming their clinical feasibility. This review describes a summary of the state-of-the-art AI application in the most popular ocular fundus diseases, potential challenges and the path forward.