Incidental finding of intraductal papillary mucinous tumor with adenocarcinoma focus after variceal bleeding.

Case of a young female patient with reflux symptoms. During gastroscopy, the patient presented an episode of gastrointestinal bleeding after biopsy of a fundic lesion. Imaging tests were requested, showing a 8cm pancreatic cyst causing obstruction of the splenic vein with presence of portal hypertension and secondary gastric varices.

Evaluation of Natural Language Processing for the Identification of Crohn Disease-Related Variables in Spanish Electronic Health Records: A Validation Study for the PREMONITION-CD Project.

BACKGROUND: The exploration of clinically relevant information in the free text of electronic health records (EHRs) holds the potential to positively impact clinical practice as well as knowledge regarding Crohn disease (CD), an inflammatory bowel disease that may affect any segment of the gastrointestinal tract. The EHRead technology, a clinical natural language processing (cNLP) system, was designed to detect and extract clinical information from narratives in the clinical notes contained in EHRs. OBJECTIVE: The aim of this study is to validate the performance of the EHRead technology in identifying information of patients with CD. METHODS: We used the EHRead technology to explore and extract CD-related clinical information from EHRs. To validate this tool, we compared the output of the EHRead technology with a manually curated gold standard to assess the quality of our cNLP system in detecting records containing any reference to CD and its related variables. RESULTS: The validation metrics for the main variable (CD) were a precision of 0.88, a recall of 0.98, and an F1 score of 0.93. Regarding the secondary variables, we obtained a precision of 0.91, a recall of 0.71, and an F1 score of 0.80 for CD flare, while for the variable vedolizumab (treatment), a precision, recall, and F1 score of 0.86, 0.94, and 0.90 were obtained, respectively. CONCLUSIONS: This evaluation demonstrates the ability of the EHRead technology to identify patients with CD and their related variables from the free text of EHRs. To the best of our knowledge, this study is the first to use a cNLP system for the identification of CD in EHRs written in Spanish.

Clinical characteristics and prognostic factors for Crohn's disease relapses using natural language processing and machine learning: a pilot study.

BACKGROUND: The impact of relapses on disease burden in Crohn's disease (CD) warrants searching for predictive factors to anticipate relapses. This requires analysis of large datasets, including elusive free-text annotations from electronic health records. This study aims to describe clinical characteristics and treatment with biologics of CD patients and generate a data-driven predictive model for relapse using natural language processing (NLP) and machine learning (ML). METHODS: We performed a multicenter, retrospective study using a previously validated corpus of CD patient data from eight hospitals of the Spanish National Healthcare Network from 1 January 2014 to 31 December 2018 using NLP. Predictive models were created with ML algorithms, namely, logistic regression, decision trees, and random forests. RESULTS: CD phenotype, analyzed in 5938 CD patients, was predominantly inflammatory, and tobacco smoking appeared as a risk factor, confirming previous clinical studies. We also documented treatments, treatment switches, and time to discontinuation in biologics-treated CD patients. We found correlations between CD and patient family history of gastrointestinal neoplasms. Our predictive model ranked 25 000 variables for their potential as risk factors for CD relapse. Of highest relative importance were past relapses and patients' age, as well as leukocyte, hemoglobin, and fibrinogen levels. CONCLUSION: Through NLP, we identified variables such as smoking as a risk factor and described treatment patterns with biologics in CD patients. CD relapse prediction highlighted the importance of patients' age and some biochemistry values, though it proved highly challenging and merits the assessment of risk factors for relapse in a clinical setting.

Real-life experience with 4 years of golimumab persistence in ulcerative colitis patients.

Golimumab has demonstrated its long-term efficacy and safety in ulcerative colitis in clinical trials, but no data of long-term persistence has been published from real world. To estimate long-term persistence of golimumab, as well as factors associated with longer persistence, in patients with ulcerative colitis in real life. Observational multicentre study including adult patients with ulcerative colitis treated with golimumab and with at least twelve months of follow-up. We included 190 patients, 105 (55.26%) naive to anti-TNF, with mean disease duration of 9.32 ± 8.09 years. Probability of persistence was 63%, 46%, 39% and 27% at 1, 2, 3 and 4 years, respectively. Persistence was lower in patients with primary failure to previous anti-TNF. Eighty-two (43.16%) patients needed dose intensification during follow-up, with a mean time until intensification of 8.03 ± 8.64 months. Dose intensification and lower disease duration predicted higher persistence with golimumab (p = 0.037 and p = 0.008, respectively). During a follow-up of 17.25 ± 15.83 months, 32 (16.5%) patients needed hospitalisation and 11 (6%) underwent colectomy. No unexpected adverse events were reported. Golimumab has demonstrated good persistence and safety profile for long treatment in ulcerative colitis patients.

The association between de novo inflammatory bowel disease and celiac disease.

INTRODUCTION: controversial data have been reported on the potential association between celiac disease (CeD) and inflammatory bowel disease (IBD). OBJECTIVE: to study the prevalence of CeD in patients newly diagnosed cases with IBD. METHODS: an observational, retrospective study was performed in patients with newly diagnosed IBD who were screened for CeD by anti-tissue transglutaminase antibodies (anti-tTG) measurements and an endoscopic duodenal biopsy. No patients had received corticosteroids, immunosuppressants or biologic drugs within the three months prior to gastroscopy. In the presence of Marsh 1, other causes were ruled out. CeD was diagnosed in patients positive for anti-tTG, compatible duodenal biopsy findings and a good response to a gluten-free diet. RESULTS: a total of 163 patients were screened for CeD. Of these, six (3.7%) were positive for anti-tTG and four were diagnosed with CeD (three had ulcerative colitis, one had Crohn's disease). All patients with both CeD and IBD had normal IgA levels, positive anti-tTG and CeD genetic markers. CONCLUSIONS: the prevalence of CeD in our patients with IBD was higher than that reported in the literature for other series of patients with IBD. A combination of anti-tTG testing and CeD genetics may screen patients for CeD in this population of patients with IBD.