Chest radiography is a relatively cheap, widely available medical procedure that conveys key information for making diagnostic decisions. Chest X-rays are frequently used in the diagnosis of respiratory diseases such as pneumonia or COVID-19. In this paper, we propose a self-supervised deep neural network that is pretrained on an unlabeled chest X-ray dataset. Pretraining is achieved through the contrastive learning approach by comparing representations of differently augmented input images. The learned representations are transferred to downstream tasks – the classification of respiratory diseases. We evaluate the proposed approach on two tasks for pneumonia classification, one for COVID-19 recognition and one for discrimination of different pneumonia types. The results show that our approach yields competitive results without requiring large amounts of labeled training data.

Background. Primary biliary cholangitis (PBC) is a chronic autoimmune cholestatic liver disease with wide ranges of reported incidence and prevalence. Aim. To map the incidence and prevalence of PBC in European countries from 2000 through 2020. Methods. Following PRISMA recommendations, we searched the Medline and Scopus databases for studies with information on either the incidence or prevalence of PBC. After data extraction, we used a random‐effects model to estimate both the pooled annual incidence rate and pooled point‐prevalence rate and performed subgroup analyses to identify components contributing to between‐study heterogeneity. Results. We performed a qualitative and quantitative analysis of 18 studies. The pooled point‐prevalence rate was 22.27 cases per 100,000 inhabitants (95% CI: 17.98–27.01), and the pooled annual incidence rate was 1.87 new cases per 100,000 inhabitants (95% CI: 1.46–2.34). In the subgroup analyses, we proved that a small part of the between‐study heterogeneity is significantly associated with a history of being part of the Eastern Bloc.

Patients with chronic hepatitis C have both higher prevalence of diabetes mellitus type 2 (T2DM) and increased cardiovascular risk compared to never infected people. Sustained viral response (SVR) achievement led to decreasing incidence and prevalence of T2DM during the interferon era of HCV treatment. Currently, direct-acting antiviral drugs (DAA) are the gold standard for treating HCV infection, while yielding SVR in nearly all patients. In chronic HCV patients with T2DM (prediabetes most likely too), DAA therapy is associated with both better fasting glucose and glycated hemoglobin (HbA1C) controls; thus reducing pharmacotherapy in a certain part of patients is possible. Papers mentioned in the review confirmed DAA role in both total cholesterol (TC) and low-density lipoprotein cholesterol (LDL-C) increase. This alteration was accompanied by an increase in high-density lipoprotein cholesterol (HDL-C) and a decrease in triglycerides (TG) verified by most of the studies. However, the clinical significance of lipoprotein alterations caused by DAA therapy has not been explained yet. Moreover, DAA treatment of chronic hepatitis C improves hypertension control and atherosclerotic plaques. It is very likely that DAA therapeutic regimens will decrease both T2DM prevalence and cardiovascular risk in chronic hepatitis C patients; further research, however, is needed.

Background and Aims: Liver cirrhosis leads to clinically significant portal hypertension. Transjugular intrahepatic portosystemic shunt (TIPS) has been shown to effectively reduce the degree of portal hypertension and treat its complications. However, poor nutritional status has been shown to be associated with hepatic encephalopathy, acute on chronic liver failure, and mortality following TIPS placement. The purpose of this systematic review is to create another perspective and evaluate the effect of TIPS placement on the nutritional status of patients with liver cirrhosis. Methods: A comprehensive search of four major electronic databases was conducted to identify studies that assessed the nutritional status of cirrhotic patients before and after TIPS placement. The risk of bias was evaluated using ROBINS-I guidelines. Results: Fifteen studies were analyzed in this review. The results indicate that among the 11 studies that evaluated changes in ascites-free weight and body mass index or body cell mass, 10 reported an improvement in one or more measures. Furthermore, all seven studies that evaluated changes in muscle mass demonstrated an increase in muscle mass. Among the four studies that evaluated subcutaneous fat tissue, three showed a significant expansion, while two out of three studies evaluating visceral fat tissue reported a significant reduction. Conclusions: The results of this systematic review suggest that TIPS placement is associated with improvement in the nutritional status of cirrhotic patients, indicated by an increase in ascites-free weight, body mass index, and muscle mass. Additionally, TIPS placement leads to a shift in the distribution of fat mass, with a preference for subcutaneous over visceral adipose tissue. Notably, sarcopenic patients seem to benefit the most from TIPS placement in terms of nutritional status.

IgG4‐related sclerosing cholangitis, a biliary manifestation of an IgG4‐related disease, belongs to the spectrum of sclerosing cholangiopathies which result in biliary stenosis. It presents with signs of cholestasis and during differential diagnosis it should be distinguished from cholangiocarcinoma or from other forms of sclerosing cholangitis (primary and secondary sclerosing cholangitis). Despite increasing information and recently established diagnostic criteria, IgG4‐related sclerosing cholangitis remains underdiagnosed in routine clinical practice. The diagnosis is based on a combination of the clinical picture, laboratory parameters, histological findings, and a cholangiogram. Increased serum IgG4 levels are nonspecific but are indeed a part of the diagnostic criteria proposed by the Japan Biliary Association and the HISORt criteria for IgG4‐SC. High serum IgG4 retains clinical utility depending on the magnitude of elevation. Approximately 90% of patients have concomitant autoimmune pancreatitis, while 10% present with isolated biliary involvement only. About 26% of patients have other organ involvement, such as IgG4‐related dacryoadenitis/sialadenitis, IgG4‐related retroperitoneal fibrosis, or IgG4‐related renal lesions. A full‐blown histological finding characterized by IgG4‐enriched lymphoplasmacytic infiltrates, obliterative phlebitis, and storiform fibrosis is difficult to capture in practice because of its subepithelial localization. However, the histological yield is increased by immunohistochemistry, with evidence of IgG4‐positive plasma cells. Based on a cholangiogram, IgG‐4 related sclerosing cholangitis is classified into four subtypes according to the localization of stenoses. The first‐line treatment is corticosteroids. The aim of the initial treatment is to induce clinical and laboratory remission and cholangiogram normalization. Even though 30% of patients have a recurrent course, in the literature data, there is no consensus on chronic immunosuppressive maintenance therapy. The disease has a good prognosis when diagnosed early.