Search

Ulcerative colitis (UC) is a chronic inflammatory bowel disease characterized by periods of exacerbation and remission, making disease monitoring and management challenging. Endoscopy, the gold standard for assessing disease activity and severity, involves invasive procedures and is associated with patient discomfort and risks. Using machine learning (ML) to combine fecal calprotectin with other clinical or biological tests can significantly enhance the non-invasive prediction of endoscopic disease activity (EDA) in UC. Aim: To prove that by fusing fecal calprotectin with other clinical data into an ML model, the performance of the non-invasive prediction of EDA can be significantly improved. Methods: We conducted a prospective, observational, single-center study encompassing 103 patients diagnosed with UC. We employed multilayer perceptron models as the core ML algorithm for predicting EDA. For the constructed models, we utilized the varImp function from the caret library in R to assess the significance of each variable in predicting the outcome. Results: Calprotectin as a sole predictor obtained an accuracy of 70% and an area under the curve (AUC) of 0.68. Combining calprotectin with the list of selected predictors that were fed to the MLP models improved accuracy and the AUC. The accuracy of the algorithm on the test set was 85%. Similarly, the AUC increased to 0.93. This is the first study to propose the use of calprotectin as a predictor in an ML model to estimate UC endoscopic disease activity. Conclusion: The deployment of this ML model can furnish doctors and patients with valuable evaluation of endoscopic disease activity which can be highly beneficial for individuals with UC who need long-term treatment. [ABSTRACT FROM AUTHOR]

A suitable, non-invasive biomarker for assessing endoscopic disease activity (EDA) in ulcerative colitis (UC) has yet to be identified. Our study aimed to develop a cost-effective and non-invasive machine learning (ML) method that utilizes the cost-free Inflammatory Bowel Disease Questionnaire (IBDQ) score and low-cost biological predictors to estimate EDA. Four random forest (RF) and four multilayer perceptron (MLP) classifiers were proposed. The results show that the inclusion of IBDQ in the list of predictors that were fed to the models improved accuracy and the AUC for both the RF and the MLP algorithms. Moreover, the RF technique performed noticeably better than the MLP method on unseen data (the independent patient cohort). This is the first study to propose the use of IBDQ as a predictor in an ML model to estimate UC EDA. The deployment of this ML model can furnish doctors and patients with valuable insights into EDA, a highly beneficial resource for individuals with UC who need long-term treatment. [ABSTRACT FROM AUTHOR]

This study aims to assess the impact of inflammatory bowel diseases (IBD): ulcerative colitis (UC) and Crohn's disease (CD) on the patients' quality of life (QoL) and to identify the significant changes in QoL depending on the developmental particularities of IBD and the epidemiological parameters. A prospective study was conducted over a period of 36 months (October 2011-October 2014) at the Institute of Gastroenterology and Hepatology, Iai. The study was conducted on 254 patients diagnosed with IBD, 187 patients with UC and 67 patients with CD. The quality of life was assessed using the questionnaire IBDQ-32 (Inflammatory Bowel Disease Questionnaire), which is one of the most widely used questionnaires in QoL assessment. The total IBDQ score was slightly more reduced in the patients with UC compared to the patients with CD. Of the 4 subscales of the IBDQ score, the scores highlighting the emotional and social component were significantly more reduced in the patients with UC, while the scores for the bowel symptoms were significantly more reduced in the patients with CD. In both the patients with UC and with CD, the correlations between the UCDAI, respectively CDAI score and the IBDQ score were indirect, highlighting reduced values of IBDQ in patients with a severe activity of the disease. The severe flare of the disease had a negative impact on the patients' QoL. The present study confirms the fact that the activity of the disease is the factor likely to have the highest impact on QoL in IBD patients. [ABSTRACT FROM AUTHOR]

Background & Aims: Identifying the risk factors for extraintestinal manifestations (EIMs) in inflammatory bowel diseases (IBD) may optimize the therapeutic decision. We aimed to assess the prevalence of EIMs in IBD patients in Romania and to determine the risk factors. Methods: We analyzed 2,626 patients registered in the Romanian IBD Prospect National Registry. We performed a descriptive cross-sectional study to assess the point prevalence of EIMs, calculating global prevalence and analyzing the different types of EIMs and their respective frequencies were carried out. Demographic and clinical risk factors were researched as possible predictors for EIMs development, based on the results of the univariate and multivariate logistic regression analysis. Results: The overall point prevalence of EIMs was 16.3%. A significantly higher frequency of EIMs in Crohn's disease (CD) was noted in comparison to ulcerative colitis (UC) and IBD unclassified (IBDU) (23.2% vs 11.3% and 16.3%, respectively, p<0.001). The most frequent type of EIM was peripheral arthropathy (8.3%), significantly associated with CD (p<0.001). Univariate analysis highlighted the significant independent common predictive risk factors for EIMs, in both CD and UC patients: female gender, patient's urban area of origin, anemia, hypoalbuminemia, and high level of C-reactive protein (CRP), while significant independent IBD phenotype-related risk factors were ileocolonic location and concomitant involvement of upper gastrointestinal tract for CD, non-smoker status and both moderate and severe disease activity for UC (p<0.05). Multivariate analysis determined that female CD patients with moderate or severe disease activity, with other than isolated ileal disease, and female UC patients with moderate or severe extensive colitis are the most likely to develop EIMs. Conclusions: IBD patients are experiencing EIMs in a large proportion, with higher rates for CD. As EIMs negatively affect patient outcomes, foreseeing the risk by identifying independent and associated predictive factors could be a first step to optimal work-up and treatment [ABSTRACT FROM AUTHOR]

Introduction. Fecal calprotectin (FC) is the most popular and well-studied non-invasive biomarker in diagnosing and monitoring inflammatory bowel disease (IBD) patients and it is routinely tested and widely used in clinical practice. Aim. to evaluate the usefulness of FC in predicting clinical relapse in IBD patients treated with anti-TNF agents, during one year of follow-up. Methods. We conducted a retrospective study including 50 IBD patients treated with anti-TNF agents (Infliximab, Adalimumab), in clinical remission (defined according to clinical Mayo and CDAI score) for at least 6 months, evaluated in a tertiary center between April 2021 through April 2022. For each patient, demographic and clinical parameters, data on the extent of the disease, type of treatment and FC value were collected. The patients included in the study were reevaluated 1 year later after the initial evaluation, regarding clinical remission/relapse. Results. There were 29 patients with ulcerative colitis (UC) (58 %) and 21 with Crohn's disease (CD) (42 %)), with a mean age of 42 years (21-63 years). 28 patients (18 with UC and 10 with CD) were treated with Infliximab and 22 (11 UC, 11 CD) with Adalimumab. Out of 50 IBD patients, 28 (56%) had FC <50 μg/g, 15 (30%) had FC between 50 - 150 μg/g and 7 (14%) had FC ≥ 150 μg/g. After 12 months, we observed persistent clinical remission rates of 82.75% (24) for UC and 71.42% (15) for CD. Clinical relapse was present in no patient with FC <50 μg/g, in 47% of patients with FC between 50 - 150 μg/g, and in 71.42% of the patients with FC ≥ 150 μg/g. All UC who relapsed had initial FC value more than 150 μg/g. There were no differences in clinical relapse in patients treated with Infliximab vs Adalimumab. Conclusion. FC more than 150 μg/g is a good noninvasive marker for 1 year clinical relapse in IBD patients treated with anti-TNF. The predictive role is more obvious for patients with UC compared to CD, regardless of the type of anti-TNF used. [ABSTRACT FROM AUTHOR]