Usefulness of Machine Learning-Based Gut Microbiome Analysis for Identifying Patients with Irritable Bowels Syndrome.

Irritable bowel syndrome (IBS) is diagnosed by subjective clinical symptoms. We aimed to establish an objective IBS prediction model based on gut microbiome analyses employing machine learning. We collected fecal samples and clinical data from 85 adult patients who met the Rome III criteria for IBS, as well as from 26 healthy controls. The fecal gut microbiome profiles were analyzed by 16S ribosomal RNA sequencing, and the determination of short-chain fatty acids was performed by gas chromatography-mass spectrometry. The IBS prediction model based on gut microbiome data after machine learning was validated for its consistency for clinical diagnosis. The fecal microbiome alpha-diversity indices were significantly smaller in the IBS group than in the healthy controls. The amount of propionic acid and the difference between butyric acid and valerate were significantly higher in the IBS group than in the healthy controls (p < 0.05). Using LASSO logistic regression, we extracted a featured group of bacteria to distinguish IBS patients from healthy controls. Using the data for these featured bacteria, we established a prediction model for identifying IBS patients by machine learning (sensitivity >80%; specificity >90%). Gut microbiome analysis using machine learning is useful for identifying patients with IBS.

Potential for differential diagnosis of autoimmune pancreatitis and pancreatic cancer using carbonic anhydrase II antibody.

OBJECTIVES: Pancreatic ductal epithelia contain an abundance of carbonic anhydrase (CA), and the presence of antibodies to this enzyme has been described in autoimmune disorders. We previously found a small amount of an immunoglobulin G-like material in purchased CAII reagents, which led to pseudopositive reactions. METHODS: We determined the optimum measurement conditions for detecting anti-CAII antibody using an enzyme-linked immunosorbent assay and sera from 140 patients with pancreatic diseases. RESULTS: Compared with the prevalence of anti-CAII antibody in healthy subjects, a significantly higher seroprevalence of the antibody was detected in patients with autoimmune pancreatitis (AIP) (88.9%, P < 0.02), Sjögren syndrome (67.6%, P < 0.01), and alcoholic chronic pancreatitis (45.8%, P < 0.01). No positive results were obtained among patients with pancreatic cancer. Moreover, the antibody value obtained in the pancreatic cancer patients was actually lower than that obtained in healthy subjects. CONCLUSIONS: The anti-CAII antibody is probably not a specific marker of AIP because it was present at a higher frequency in the sera of patients with other pancreatic diseases. Nevertheless, the anti-CAII antibody may be a useful tool for the differential diagnosis of AIP and pancreatic cancer.

Postmarketing surveillance of rabeprazole in upper gastrointestinal peptic lesions in Japanese patients with coexisting hepatic disorders.

BACKGROUND: Many Japanese patients with hepatic disorders confirmed on diagnostic imaging and coexisting upper gastrointestinal (GI) peptic lesions receive treatment with proton pump inhibitors. Some pharmacotherapies used to treat peptic ulcers have been associated with adverse drug reactions (ADRs), including elevated liver enzyme levels. OBJECTIVE: The aim of this study was to determine the tolerability and effectiveness of rabeprazole sodium in treating peptic lesions in patients with coexisting hepatic disorders. METHODS: This open-label, practice-based, postmarketing surveillance investigation was conducted at 15 centers across Japan. Male and female patients aged ≥18 years with peptic lesions confirmed on upper GI endoscopy and with underlying hepatic disease were enrolled. Patients were randomly assigned to receive rabeprazole 10 or 20 mg PO (tablet) QD after a meal for up to 8 weeks. Tolerability was assessed using monitoring of the incidence of ADRs determined by direct patient questioning, spontaneous reporting, and laboratory assessment. All patients who received at least 1 dose of study drug were included in the tolerability assessment. Effectiveness was assessed at baseline and study end using the rates of achievement of improvement on endoscopy, relief of subjective/objective symptoms (rates of improvement in epigastric pain and heartburn), and global improvement. The effectiveness analysis included all patients with complete data before and after treatment. Subanalyses were conducted to determine the effectiveness of drug by identification of the proportion of patients with coexisting hepatic disorders (cirrhosis, chronic hepatitis, and other hepatic diseases [eg, alcoholic hepatitis, fatty liver]) and by peptic lesion (gastric ulcer, duodenal ulcer, stomal ulcer, and reflux esophagitis) who achieved improvement. RESULTS: A total of 114 patients were enrolled; 108 patients were included in the tolerability analysis (81 men, 27 women; mean age, 59.9 years; 10-mg dose, 90 patients; 20-mg dose, 18 patients) and 98 patients were included in the analysis of effectiveness. Twenty-one ADRs occurred in 11 (10.2%) patients. Serious ADRs occurred in 2 patients (elevated bilirubin level and hepatic encephalopathy, 1 patient each). Administration of rabeprazole was discontinued in 5 patients due to the occurrence of the following ADRs: constipation (1 patient); epigastric pain (1); dyslalia, disorientation, tremor, sleep disorder, and hepatic encephalopathy (1); diarrhea (1); and elevated alkaline phosphatase and y-glutamyl transpeptidase levels (1). On endoscopy, the proportion of patients achieving improvement with either dose was 30/33 (90.9%). The relief rates assessed using subjective symptoms were 47/55 (85.5%) and 47/56 (83.9%) for epigastric pain and heartburn, respectively. The proportion of patients achieving global improvement with either dose was 80/98 (81.6%) patients (49/62 [79.0%] for cirrhosis, 11/16 [68.8%] for chronic hepatitis, and 20/20 [100.0%] for other hepatic diseases [alcoholic hepatitis, fatty liver]). CONCLUSION: In this study in Japanese patients with hepatic disorders, rabeprazole was well tolerated and appeared effective for the treatment of upper GI peptic lesions.