Prediction of cardiovascular risk factors from retinal fundus photographs: Validation of a deep learning algorithm in a prospective non-interventional study in Kenya.

AIM: Hypertension and diabetes mellitus (DM) are major causes of morbidity and mortality, with growing burdens in low-income countries where they are underdiagnosed and undertreated. Advances in machine learning may provide opportunities to enhance diagnostics in settings with limited medical infrastructure. MATERIALS AND METHODS: A non-interventional study was conducted to develop and validate a machine learning algorithm to estimate cardiovascular clinical and laboratory parameters. At two sites in Kenya, digital retinal fundus photographs were collected alongside blood pressure (BP), laboratory measures and medical history. The performance of machine learning models, originally trained using data from the UK Biobank, were evaluated for their ability to estimate BP, glycated haemoglobin, estimated glomerular filtration rate and diagnoses from fundus images. RESULTS: In total, 301 participants were enrolled. Compared with the UK Biobank population used for algorithm development, participants from Kenya were younger and would probably report Black/African ethnicity, with a higher body mass index and prevalence of DM and hypertension. The mean absolute error was comparable or slightly greater for systolic BP, diastolic BP, glycated haemoglobin and estimated glomerular filtration rate. The model trained to identify DM had an area under the receiver operating curve of 0.762 (0.818 in the UK Biobank) and the hypertension model had an area under the receiver operating curve of 0.765 (0.738 in the UK Biobank). CONCLUSIONS: In a Kenyan population, machine learning models estimated cardiovascular parameters with comparable or slightly lower accuracy than in the population where they were trained, suggesting model recalibration may be appropriate. This study represents an incremental step toward leveraging machine learning to make early cardiovascular screening more accessible, particularly in resource-limited settings.

Identification of ocular refraction based on deep learning algorithm as a novel retinoscopy method.

BACKGROUND: The evaluation of refraction is indispensable in ophthalmic clinics, generally requiring a refractor or retinoscopy under cycloplegia. Retinal fundus photographs (RFPs) supply a wealth of information related to the human eye and might provide a promising approach that is more convenient and objective. Here, we aimed to develop and validate a fusion model-based deep learning system (FMDLS) to identify ocular refraction via RFPs and compare with the cycloplegic refraction. In this population-based comparative study, we retrospectively collected 11,973 RFPs from May 1, 2020 to November 20, 2021. The performance of the regression models for sphere and cylinder was evaluated using mean absolute error (MAE). The accuracy, sensitivity, specificity, area under the receiver operating characteristic curve, and F1-score were used to evaluate the classification model of the cylinder axis. RESULTS: Overall, 7873 RFPs were retained for analysis. For sphere and cylinder, the MAE values between the FMDLS and cycloplegic refraction were 0.50 D and 0.31 D, representing an increase of 29.41% and 26.67%, respectively, when compared with the single models. The correlation coefficients (r) were 0.949 and 0.807, respectively. For axis analysis, the accuracy, specificity, sensitivity, and area under the curve value of the classification model were 0.89, 0.941, 0.882, and 0.814, respectively, and the F1-score was 0.88. CONCLUSIONS: The FMDLS successfully identified the ocular refraction in sphere, cylinder, and axis, and showed good agreement with the cycloplegic refraction. The RFPs can provide not only comprehensive fundus information but also the refractive state of the eye, highlighting their potential clinical value.

Performance of deep learning for detection of chronic kidney disease from retinal fundus photographs: A systematic review and meta-analysis.

OBJECTIVE: Deep learning has been used to detect chronic kidney disease (CKD) from retinal fundus photographs. We aim to evaluate the performance of deep learning for CKD detection. METHODS: The original studies in CKD patients detected by deep learning from retinal fundus photographs were eligible for inclusion. PubMed, Embase, the Cochrane Library, and Web of Science were searched up to October 31, 2022. The Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool was used to assess the risk of bias. RESULTS: Four studies enrolled 114,860 subjects were included. The pooled sensitivity and specificity were 87.8% (95% confidence interval (CI): 61.6% to 98.3%), and 62.4% (95% CI: 44.9% to 78.7%). The area under the curve (AUC) was 0.864 (95%CI: 0.769, 0.986). CONCLUSION: Deep learning based on retinal fundus photographs has the ability to detect CKD, but it currently has a lot of room for improvement. It is still a long way from clinical application.

Automatic Detection of Diabetic Retinopathy in Retinal Fundus Photographs Based on Deep Learning Algorithm.

PURPOSE: To achieve automatic diabetic retinopathy (DR) detection in retinal fundus photographs through the use of a deep transfer learning approach using the Inception-v3 network. METHODS: A total of 19,233 eye fundus color numerical images were retrospectively obtained from 5278 adult patients presenting for DR screening. The 8816 images passed image-quality review and were graded as no apparent DR (1374 images), mild nonproliferative DR (NPDR) (2152 images), moderate NPDR (2370 images), severe NPDR (1984 images), and proliferative DR (PDR) (936 images) by eight retinal experts according to the International Clinical Diabetic Retinopathy severity scale. After image preprocessing, 7935 DR images were selected from the above categories as a training dataset, while the rest of the images were used as validation dataset. We introduced a 10-fold cross-validation strategy to assess and optimize our model. We also selected the publicly independent Messidor-2 dataset to test the performance of our model. For discrimination between no referral (no apparent DR and mild NPDR) and referral (moderate NPDR, severe NPDR, and PDR), we also computed prediction accuracy, sensitivity, specificity, area under the receiver operating characteristic curve (AUC), and κ value. RESULTS: The proposed approach achieved a high classification accuracy of 93.49% (95% confidence interval [CI], 93.13%-93.85%), with a 96.93% sensitivity (95% CI, 96.35%-97.51%) and a 93.45% specificity (95% CI, 93.12%-93.79%), while the AUC was up to 0.9905 (95% CI, 0.9887-0.9923) on the independent test dataset. The κ value of our best model was 0.919, while the three experts had κ values of 0.906, 0.931, and 0.914, independently. CONCLUSIONS: This approach could automatically detect DR with excellent sensitivity, accuracy, and specificity and could aid in making a referral recommendation for further evaluation and treatment with high reliability. TRANSLATIONAL RELEVANCE: This approach has great value in early DR screening using retinal fundus photographs.