Artificial intelligence-based classification of cardiac autonomic neuropathy from retinal fundus images in patients with diabetes: The Silesia Diabetes Heart Study.

BACKGROUND: Cardiac autonomic neuropathy (CAN) in diabetes mellitus (DM) is independently associated with cardiovascular (CV) events and CV death. Diagnosis of this complication of DM is time-consuming and not routinely performed in the clinical practice, in contrast to fundus retinal imaging which is accessible and routinely performed. Whether artificial intelligence (AI) utilizing retinal images collected through diabetic eye screening can provide an efficient diagnostic method for CAN is unknown. METHODS: This was a single center, observational study in a cohort of patients with DM as a part of the Cardiovascular Disease in Patients with Diabetes: The Silesia Diabetes-Heart Project (NCT05626413). To diagnose CAN, we used standard CV autonomic reflex tests. In this analysis we implemented AI-based deep learning techniques with non-mydriatic 5-field color fundus imaging to identify patients with CAN. Two experiments have been developed utilizing Multiple Instance Learning and primarily ResNet 18 as the backbone network. Models underwent training and validation prior to testing on an unseen image set. RESULTS: In an analysis of 2275 retinal images from 229 patients, the ResNet 18 backbone model demonstrated robust diagnostic capabilities in the binary classification of CAN, correctly identifying 93% of CAN cases and 89% of non-CAN cases within the test set. The model achieved an area under the receiver operating characteristic curve (AUCROC) of 0.87 (95% CI 0.74-0.97). For distinguishing between definite or severe stages of CAN (dsCAN), the ResNet 18 model accurately classified 78% of dsCAN cases and 93% of cases without dsCAN, with an AUCROC of 0.94 (95% CI 0.86-1.00). An alternate backbone model, ResWide 50, showed enhanced sensitivity at 89% for dsCAN, but with a marginally lower AUCROC of 0.91 (95% CI 0.73-1.00). CONCLUSIONS: AI-based algorithms utilising retinal images can differentiate with high accuracy patients with CAN. AI analysis of fundus images to detect CAN may be implemented in routine clinical practice to identify patients at the highest CV risk. TRIAL REGISTRATION: This is a part of the Silesia Diabetes-Heart Project (Clinical-Trials.gov Identifier: NCT05626413).

Strategies to address inequity of uncorrected refractive error in the Western Pacific: A modified Delphi process.

PURPOSE: Uncorrected refractive error is the leading cause of vision impairment globally; however, little attention has been given to equity and access to services. This study aimed to identify and prioritise: (1) strategies to address inequity of access to refractive error services and (2) population groups to target with these strategies in five sub-regions within the Western Pacific. METHODS: We invited eye care professionals to complete a two-round online prioritisation process. In round 1, panellists nominated population groups least able to access refractive error services, and strategies to improve access. Responses were summarised and presented in round 2, where panellists ranked the groups (by extent of difficulty and size) and strategies (in terms of reach, acceptability, sustainability, feasibility and equity). Groups and strategies were scored according to their rank within each sub-region. RESULTS: Seventy five people from 17 countries completed both rounds (55% women). Regional differences were evident. Indigenous peoples were a priority group for improving access in Australasia and Southeast Asia, while East Asia identified refugees and Oceania identified rural/remote people. Across the five sub-regions, reducing out-of-pocket costs was a commonly prioritised strategy for refraction and spectacles. Australasia prioritised improving cultural safety, East Asia prioritised strengthening school eye health programmes and Oceania and Southeast Asia prioritised outreach to rural areas. CONCLUSION: These results provide policy-makers, researchers and funders with a starting point for context-specific actions to improve access to refractive error services, particularly among underserved population groups who may be left behind in existing private sector-dominated models of care.