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.

Crohn’s disease (CD) and ulcerative colitis (UC) can be difficult to differentiate. As differential diagnosis is important in establishing a long-term treatment plan for patients, we aimed to develop a machine learning model for the differential diagnosis of the two diseases using RNA sequencing (RNA-seq) data from endoscopic biopsy tissue from patients with inflammatory bowel disease (n = 127; CD, 94; UC, 33). Biopsy samples were taken from inflammatory lesions or normal tissues. The RNA-seq dataset was processed via mapping to the human reference genome (GRCh38) and quantifying the corresponding gene models that comprised 19,596 protein-coding genes. An unsupervised learning model showed distinct clusters of four classes: CD inflammatory, CD normal, UC inflammatory, and UC normal. A supervised learning model based on partial least squares discriminant analysis was able to distinguish inflammatory CD from inflammatory UC after pruning the strong classifiers of normal CD vs. normal UC. The error rate was minimal and affected only two components: 20 and 50 genes for the first and second components, respectively. The corresponding overall error rate was 0.147. RNA-seq analysis of tissue and the two components revealed in this study may be helpful for distinguishing CD from UC.

Patients with COVID-19 have been reported to experience gastrointestinal symptoms as well as respiratory symptoms, but the effects of COVID-19 on the gut microbiota are poorly understood. We explored gut microbiome profiles associated with the respiratory infection of SARS-CoV-2 during the recovery phase in patients with asymptomatic or mild COVID-19. A longitudinal analysis was performed using the same patients to determine whether the gut microbiota changed after recovery from COVID-19. We applied 16S rRNA amplicon sequencing to analyze two paired fecal samples from 12 patients with asymptomatic or mild COVID-19. Fecal samples were selected at two time points: during SARS-CoV-2 infection (infected state) and after negative conversion of the viral RNA (recovered state). We also compared the microbiome data with those from 36 healthy controls. Microbial evenness of the recovered state was significantly increased compared with the infected state. SARS-CoV-2 infection induced the depletion of Bacteroidetes, while an abundance was observed with a tendency to rapidly reverse in the recovered state. The Firmicutes/Bacteroidetes ratio in the infected state was markedly higher than that in the recovered state. Gut dysbiosis was observed after infection even in patients with asymptomatic or mild COVID-19, while the composition of the gut microbiota was recovered after negative conversion of SARS-CoV-2 RNA. Modifying intestinal microbes in response to COVID-19 might be a useful therapeutic alternative.

Early intestinal resection in patients with Crohn’s disease (CD) is necessary due to a severe and complicating disease course. Herein, we aim to predict which patients with CD need early intestinal resection within 3 years of diagnosis, according to a tree-based machine learning technique. The single-nucleotide polymorphism (SNP) genotype data for 337 CD patients recruited from 15 hospitals were typed using the Korea Biobank Array. For external validation, an additional 126 CD patients were genotyped. The predictive model was trained using the 102 candidate SNPs and seven sets of clinical information (age, sex, cigarette smoking, disease location, disease behavior, upper gastrointestinal involvement, and perianal disease) by employing a tree-based machine learning method (CatBoost). The importance of each feature was measured using the Shapley Additive Explanations (SHAP) model. The final model comprised two clinical parameters (age and disease behavior) and four SNPs (rs28785174, rs60532570, rs13056955, and rs7660164). The combined clinical–genetic model predicted early surgery more accurately than a clinical-only model in both internal (area under the receiver operating characteristic (AUROC), 0.878 vs. 0.782; n = 51; p < 0.001) and external validation (AUROC, 0.836 vs. 0.805; n = 126; p < 0.001). Identification of genetic polymorphisms and clinical features enhanced the prediction of early intestinal resection in patients with CD.

Limited studies have examined the intestinal microbiota composition in relation to Crohn’s disease (CD) prognosis. We analyzed the differences in microbial communities and relevant metabolic pathways associated with prognostic variables in patients with CD. We applied 16S rRNA gene sequencing to analyze a cohort of 1110 CD and healthy control (HC) fecal samples. We categorized patients with CD into good (CD-G), intermediate (CD-I) and poor (CD-P) prognosis groups, according to the history of using biologics and intestinal resection. Microbiota α-diversity decreased more in CD-P than CD-G and CD-I. Microbiota ß-diversity in CD-P differed from that in CD-G and CD-I. Thirteen genera and 10 species showed differential abundance between CD-G and CD-P groups. Escherichia coli (p = 0.001) and species Producta (p = 0.01) and genera Lactobacillus (p = 0.003) and Coprococcus (p = 0.01) consistently showed differences between CD-G and CD-P groups after adjusting for confounding variables. Functional profiling suggested that the microbial catabolic pathways and pathways related to enterobacterial common antigen and lipopolysaccharide biosynthesis were better represented in the CD-P group than in the CD-G group, and E. coli were the top contributors to these pathways. CD prognosis is associated with altered microbiota composition and decreased diversity, and E. coli might be causally involved in CD progression, and may have adapted to live in inflammatory environments.