The increasing prevalence of diabetes has been a global health issue for decades.¹ According to the latest investigation in the Diabetes Atlas, there are 425 million adults with diabetes worldwide.² Although newer therapies have increased the life expectancy of patients with diabetes, macrovascular and microvascular complications still cause substantial morbidity.³ In 2012, the total estimated medical cost for treating patients with diabetes in the United States was $176 billion, and diabetes was especially costly if associated with any complications.⁴

In this study, we aimed to develop a deep learning model for identifying bacterial keratitis (BK) and fungal keratitis (FK) by using slit-lamp images. We retrospectively collected slit-lamp images of patients with culture-proven microbial keratitis between 1 January 2010 and 31 December 2019 from two medical centers in Taiwan. We constructed a deep learning algorithm consisting of a segmentation model for cropping cornea images and a classification model that applies different convolutional neural networks (CNNs) to differentiate between FK and BK. The CNNs included DenseNet121, DenseNet161, DenseNet169, DenseNet201, EfficientNetB3, InceptionV3, ResNet101, and ResNet50. The model performance was evaluated and presented as the area under the curve (AUC) of the receiver operating characteristic curves. A gradient-weighted class activation mapping technique was used to plot the heat map of the model. By using 1330 images from 580 patients, the deep learning algorithm achieved the highest average accuracy of 80.0%. Using different CNNs, the diagnostic accuracy for BK ranged from 79.6% to 95.9%, and that for FK ranged from 26.3% to 65.8%. The CNN of DenseNet161 showed the best model performance, with an AUC of 0.85 for both BK and FK. The heat maps revealed that the model was able to identify the corneal infiltrations. The model showed a better diagnostic accuracy than the previously reported diagnostic performance of both general ophthalmologists and corneal specialists.

To evaluate the surgical technique using autologous retinal graft (ARG) and autologous blood clot (ABC) for the management of refractory macular holes (MHs). This study was a retrospective, consecutive, interventional case series. Six eyes of 6 patients who underwent vitrectomy combined with ARG and ABC for the treatment of refractory MH were reviewed. Visual and anatomic outcomes were evaluated. The mean age was 59.0 ± 9.9 years. All cases had multiple vitreoretinal procedures including vitrectomy and gas fluid exchange before patient presentation. The average numbers of vitrectomies were 2.3 ± 0.5, and those of gas fluid exchange were 3 ± 1.7. Closure of the macular hole was achieved in four (66.7%) cases at last follow-up. The mean follow-up time was 25.2 ± 15.6 months. The averaged BCVA before and after 12 months of the surgery improved from 20/591 to 20/244. This surgical technique using ARG and ABC provide an option for the treatment of refractory MHs.

Background: Retinal imaging has been applied for detecting eye diseases and cardiovascular risks using deep learning–based methods. Furthermore, retinal microvascular and structural changes were found in renal function impairments. However, a deep learning–based method using retinal images for detecting early renal function impairment has not yet been well studied. Objective: This study aimed to develop and evaluate a deep learning model for detecting early renal function impairment using retinal fundus images. Methods: This retrospective study enrolled patients who underwent renal function tests with color fundus images captured at any time between January 1, 2001, and August 31, 2019. A deep learning model was constructed to detect impaired renal function from the images. Early renal function impairment was defined as estimated glomerular filtration rate 6.5%, >7.5%, and >10%, respectively. Conclusions: The deep learning model in this study enables the detection of early renal function impairment using retinal fundus images. The model was more accurate for patients with elevated serum HbA1c levels.