Background and Aim
It is necessary to establish universal methods for endoscopic diagnosis of Helicobacter pylori (HP) infection, such as computer‐aided diagnosis. In the present study, we propose a multistage diagnosis algorithm for HP infection.
Methods
The aims of this study are to: (i) to construct an interpretable automatic diagnostic system using a support vector machine for HP infection; and (ii) to compare the diagnosis capability of our artificial intelligence (AI) system with that of endoscopists. Presence of an HP infection determined through linked color imaging (LCI) was learned through machine learning. Trained classifiers automatically diagnosed HP‐positive and ‐negative patients examined using LCI. We retrospectively analyzed the new images from 105 consecutive patients; 42 were HP positive, 46 were post‐eradication, and 17 were uninfected. Five endoscopic images per case taken from different areas were read into the AI system, and used in the HP diagnosis.
Results
Accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of the diagnosis of HP infection using the AI system were 87.6%, 90.4%, 85.7%, 80.9%, and 93.1%, respectively. Accuracy of the AI system was higher than that of an inexperienced doctor, but there was no significant difference between the diagnosis of experienced physicians and the AI system.
Conclusions
The AI system can diagnose an HP infection with significant accuracy. There remains room for improvement, particularly for the diagnosis of post‐eradication patients. By learning more images and considering a diagnosis algorithm for post‐eradication patients, our new AI system will provide diagnostic support, particularly to inexperienced physicians.
Taken together, the results indicated that the inhibition of endogenous H(2)S generation caused the deterioration of DSS-induced colitis. We conclude that physiological H(2)S might act as an anti-inflammatory molecule in colitis.
Diabetic ketoacidosis (DKA) in children is associated with intracranial vascular complications, possibly due to leukocyte-endothelial interactions. Our aim was to determine whether DKA-induced inflammation promoted leukocyte adhesion to activated human cerebrovascular endothelium. Plasma was obtained from children with type 1 diabetes either in acute DKA or in an insulin-controlled state (CON). Plasma concentrations of 21 inflammatory analytes were compared between groups. DKA was associated with altered circulating levels of ↑CXCL1 (GROα), ↑CXCL8 (IL-8), ↑IL-6, ↑IFNα2, and ↓CXCL10 (IP-10) compared with CON. These plasma analyte measurements were then used to create physiologically relevant cytokine mixtures (CM). Human cerebral microvascular endothelial cells (hCMEC/D3) were stimulated with either plasma (DKA-P or CON-P) or CM (DKA-CM or CON-CM) and assessed for polymorphonuclear leukocyte (PMN) adhesion. Stimulation of hCMEC/D3 with DKA-P or DKA-CM increased PMN adhesion to hCMEC/D3 under “flow” conditions. PMN adhesion to hCMEC/D3 was suppressed with neutralizing antibodies to CXCL1/CXCL8 or their hCMEC/D3 receptors CXCR1/CXCR2. DKA-P, but not DKA-CM, initiated oxidative stress in hCMEC/D3. Expression of ICAM-1, VCAM-1, and E-selectin were unaltered on hCMEC/D3 by either DKA-P or DKA-CM. In summary, DKA elicits inflammation in children associated with changes in circulating cytokines/chemokines. Increased CXCL1/CXCL8 instigated PMN adhesion to hCMEC/D3, possibly contributing to DKA-associated intracranial vascular complications.
The inhalation of CO protected mice from developing intestinal inflammation. Based on these data, the beneficial effects of CO in a murine colitis model may be attributed to its anti-inflammatory properties.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.