BACKGROUND & AIMS: Q6Although coronavirus disease 2019 (COVID-19) is characterized by fever and respiratory symptoms, some patients have no or mild symptoms. Severe acute respiratory syndromecoronavirus (SARS-CoV-2) has been detected in feces of patients. We investigated gastrointestinal symptoms and shedding of virus into feces of patients with asymptomatic or mild COVID-19. METHODS:We collected data from 46 patients (median age, 26 y; 46% men) with asymptomatic or mild COVID-19 (without fever and pneumonia) and prolonged respiratory shedding of SARS-CoV-2, quarantined from April 4, 2020, through April 24, 2020, in Korea. Respiratory specimens included upper respiratory specimens (nasopharyngeal and oropharyngeal swabs) and lower respiratory specimens (sputum), and were collected twice per week. The median interval between COVID-19 diagnosis to the start of fecal sample collection was 37 days (range, 29-41 d); 213 stool specimens were collected from 46 patients. We used real-time reverse-transcription polymerase chain reaction to detect SARS-CoV-2 in the respiratory and fecal specimens. RESULTS:Gastrointestinal manifestations were observed in 16 of the 46 patients (35%); diarrhea was the most common (15%), followed by abdominal pain (11%), dyspepsia (11%), and nausea (2%).Virus RNA was detected in feces from 2 patients without gastrointestinal symptoms (4%). Mean cycle threshold values from the time of quarantine to the time of fecal collection tended to be lower in patients with virus detected in fecal samples than in patients without virus in fecal samples (29.91 vs 33.67 in the first week, 29.47 vs 35.71 in the fifth week, respectively). Shedding of virus into feces persisted until day 50 after diagnosis; fecal samples began to test negative before or at approximately the time that respiratory specimens also began to test negative. CONCLUSIONS:In an analysis of fecal and respiratory specimens from patients with COVID-19 in quarantine in Korea, we found that the gastrointestinal tract could be a route of transmission of SARS-CoV-2 even in patients with asymptomatic or mild disease, with no gastrointestinal symptoms. The viral load of the respiratory specimens appears be related to shedding of the virus into feces in this group of patients.

PurposeTo build a deep learning model to diagnose glaucoma using fundus photography.DesignCross sectional case study Subjects, Participants and Controls: A total of 1,542 photos (786 normal controls, 467 advanced glaucoma and 289 early glaucoma patients) were obtained by fundus photography.MethodThe whole dataset of 1,542 images were split into 754 training, 324 validation and 464 test datasets. These datasets were used to construct simple logistic classification and convolutional neural network using Tensorflow. The same datasets were used to fine tune pre-trained GoogleNet Inception v3 model.ResultsThe simple logistic classification model showed a training accuracy of 82.9%, validation accuracy of 79.9% and test accuracy of 77.2%. Convolutional neural network achieved accuracy and area under the receiver operating characteristic curve (AUROC) of 92.2% and 0.98 on the training data, 88.6% and 0.95 on the validation data, and 87.9% and 0.94 on the test data. Transfer-learned GoogleNet Inception v3 model achieved accuracy and AUROC of 99.7% and 0.99 on training data, 87.7% and 0.95 on validation data, and 84.5% and 0.93 on test data.ConclusionBoth advanced and early glaucoma could be correctly detected via machine learning, using only fundus photographs. Our new model that is trained using convolutional neural network is more efficient for the diagnosis of early glaucoma than previously published models.

Background This study is to evaluate the accuracy of machine learning for differentiation between optic neuropathies, pseudopapilledema (PPE) and normals. Methods Two hundred and ninety-five images of optic neuropathies, 295 images of PPE, and 779 control images were used. Pseudopapilledema was defined as follows: cases with elevated optic nerve head and blurred disc margin, with normal visual acuity (> 0.8 Snellen visual acuity), visual field, color vision, and pupillary reflex. The optic neuropathy group included cases of ischemic optic neuropathy (177), optic neuritis (48), diabetic optic neuropathy (17), papilledema (22), and retinal disorders (31). We compared four machine learning classifiers (our model, GoogleNet Inception v3, 19-layer Very Deep Convolution Network from Visual Geometry group (VGG), and 50-layer Deep Residual Learning (ResNet)). Accuracy and area under receiver operating characteristic curve (AUROC) were analyzed. Results The accuracy of machine learning classifiers ranged from 95.89 to 98.63% (our model: 95.89%, Inception V3: 96.45%, ResNet: 98.63%, and VGG: 96.80%). A high AUROC score was noted in both ResNet and VGG (0.999). Conclusions Machine learning techniques can be combined with fundus photography as an effective approach to distinguish between PPE and elevated optic disc associated with optic neuropathies.

No abstract

No abstract