Faecal calprotectin is the biomarker that best distinguishes remission from different degrees of endoscopic activity in Crohn’s disease

Penna, Francisco Guilherme Cancela e; Rosa, Rodrigo Macedo; Cunha, Pedro Ferrari Sales; Souza, Stella Cristina Silva de; Ferrari, Maria de Lourdes de Abreu

doi:10.1186/s12876-020-1183-x

Cited by 19 publications

(9 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other non-invasive diagnostic tests for IBD, such as fecal calprotectin, continue to have significant differences between the reports on the sensitivity and specificity for classifying IBD patients from non-IBD [88, 89]. While high performance levels have been reported, one recent study identified a 78% accuracy for identifying patients with IBD using fecal calprotectin [90], which is approximately 10% lower than our best model. Furthermore, while we focused solely on IBD classification, ML models using microbiome composition have wider applicability than singular biomarkers such as calprotectin.…”

Section: Discussionmentioning

confidence: 59%

Benchmark of data processing methods and machine learning models for gut microbiome-based diagnosis of inflammatory bowel disease

Kubinski¹,

Djamen-Kepaou²,

Zhanabaev³

et al. 2021

Preprint

View full text Add to dashboard Cite

BackgroundInflammatory bowel disease (IBD) patients wait months and undergo numerous invasive procedures between the initial appearance of symptoms and receiving a diagnosis. In order to reduce time until diagnosis and improve patient wellbeing, machine learning algorithms capable of diagnosing IBD from the gut microbiome’s composition are currently being explored. To date, these models have had limited clinical application due to decreased performance when applied to a new cohort of patient samples. Various methods have been developed to analyze microbiome data which may improve the generalizability of machine learning IBD diagnostic tests. With an abundance of methods, there is a need to benchmark the performance and generalizability of various machine learning pipelines (from data processing to training a machine learning model) for microbiome-based IBD diagnostic tools.ResultsWe collected fifteen 16S rRNA microbiome datasets (7707 samples) from North America to benchmark combinations of gut microbiome features, data normalization methods, batch effect reduction methods, and machine learning models. Pipeline generalizability to new cohorts of patients was evaluated with four binary classification metrics following leave-one dataset-out cross validation, where all samples from one study were left out of the training set and tested upon. We demonstrate that taxonomic features obtained from QIIME2 lead to better classification of samples from IBD patients than inferred functional features obtained from PICRUSt2. In addition, machine learning models that identify non-linear decision boundaries between labels are more generalizable than those that are linearly constrained. Prior to training a non-linear machine learning model on taxonomic features, it is important to apply a compositional normalization method and remove batch effects with the naive zero-centering method. Lastly, we illustrate the importance of generating a curated training dataset to ensure similar performance across patient demographics.ConclusionsThese findings will help improve the generalizability of machine learning models as we move towards non-invasive diagnostic and disease management tools for patients with IBD.

show abstract

Section: Discussionmentioning

confidence: 59%

Benchmark of data processing methods and machine learning models for gut microbiome-based diagnosis of inflammatory bowel disease

Kubinski¹,

Djamen-Kepaou²,

Zhanabaev³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Another limitation may be represented by the lack of colonoscopy to assess endoscopic remission. However, in accordance with previous findings [1,39,40], we opted to measure FC (cut-off 250 µg/g) as a widely recognized biomarker of endoscopic remission.…”

Section: Discussionmentioning

confidence: 94%

Efficacy of a Preparation Based on Calcium Butyrate, Bifidobacterium bifidum, Bifidobacterium lactis, and Fructooligosaccharides in the Prevention of Relapse in Ulcerative Colitis: A Prospective Observational Study

Caviglia

Blasio

Vernero³

et al. 2021

JCM

View full text Add to dashboard Cite

Several compounds based on short chain fatty acids and/or probiotics/prebiotics have shown promising results in the therapy of ulcerative colitis (UC), possibly due to its key role in restoring gut homeostasis as well as intestinal barrier integrity. Here, we investigated the efficacy of a patented preparation based on calcium butyrate, Bifidobacterium bifidum, Bifidobacterium lactis, and fructooligosaccharides (FEEDColon®, Princeps, Cuneo, Italy) in maintaining remission and improving subjective symptoms and inflammatory indices in patients with UC receiving 5-ASA therapy. A total of 42 patients were prospectively recruited and randomized in 21 patients receiving combination therapy with mesalamine (5-ASA) plus FEEDColon® and 21 patients treated with standard 5-ASA therapy. Patients were assessed at baseline, at 6-month, and 12-month follow-up (FU). Therapeutic success (defined as Mayo partial score ≤ 2 and faecal calprotectin (FC) < 250 µg/g at 12-month FU) was reached by 32 (76%) patients: 20 (95%) among those treated with 5-ASA + FeedColon®, and 12 (57%) among those treated with 5-ASA only (p = 0.009). Consistently, patients treated with combination therapy improved subjective symptoms (quality of life, abdominal pain, and stool consistency) and reduced FC values, while those treated with 5-ASA alone, improved neither subjective symptoms nor FC during the FU. In conclusion, FEEDColon® supplementation appears to be a valid add-on therapy for the maintenance of remission in patients with UC. Further multicentre, placebo-controlled, double-blind clinical trials are needed to validate our results on larger cohorts of patients with UC.

show abstract

“…Moreover, the assessment of VDZ trough levels could be interesting in order to evaluate the correlation between serum cytokines and VDZ pharmacokinetics, although this evaluation is not widely performed in real-life practice. Lastly, an endoscopic assessment at twelve months would improve the significance of the results, although faecal calprotectin < 250 mg/kg is currently well recognized as a marker of endoscopic remission [28,30]. However, performing colonoscopies would allow to collect biopsies, in order to evaluate even histological healing and tissue cytokine levels, which could be another important weakness of our study.…”

Section: Discussionmentioning

confidence: 99%

“…However, data regarding its use as a prospective biomarker in VDZ-treated patients are conflicting, since a post-hoc analysis of GEMINI-I trial showed that faecal calprotectin levels after the induction of VDZ therapy are not able to predict endoscopic response [27]. Conversely, faecal calprotectin showed in several studies in IBD setting a reliable correlation with endoscopic activity [28][29][30].…”

Section: Discussionmentioning

confidence: 99%

Serum Interleukin-6 and -8 as Predictors of Response to Vedolizumab in Inflammatory Bowel Diseases

Bertani

Caviglia

Antonioli

et al. 2020

JCM

View full text Add to dashboard Cite

Vedolizumab, a monoclonal antibody directed against integrin α4β7, is an effective treatment for inflammatory bowel diseases. However, a significant number of patients do not achieve steroid-free clinical remission in the first year of treatment. An early identification of these patients is one of the most important challenges for clinicians and offers the possibility of therapeutic optimization in order to personalize biological therapy. The aim of our study was to test the prediction ability of interleukin (IL)-6 and -8 of clinical response after 12 months of therapy with vedolizumab (T2). We performed a prospective, multicentre study in patients affected by inflammatory bowel disease by analysing cytokines level before starting vedolizumab (T0) and after 10 weeks of therapy (T1). In the overall cohort (n = 54), IL-8 decrease > 2.6 pg/mL in the first 10 weeks of therapy was able to predict clinical response (area under the curve (AUC) = 0.70, sensitivity = 66%, specificity = 75%, p = 0.010), negative C-reactive protein (CRP) (AUC = 0.71, sensitivity = 64%, specificity = 80%, p = 0.009) and calprotectin < 250 mg/kg (AUC = 0.69, sensitivity = 64%, specificity = 78%, p = 0.030) after 44 weeks of therapy. In patients with ulcerative colitis (n = 40), baseline IL-8 values > 8.6 pg/mL and a decrease of IL-6 values > 0.4 pg/mL from T0 to T1 were significant and independent predictors of clinical response after 12 months of vedolizumab therapy (odds ratio (OR) = 6.96, 95% CI 1.27–38.22, p = 0.026 and OR = 7.29, 95% CI 1.42–37.50, p = 0.017, respectively). In patients with Crohn’s disease (n = 14), baseline IL-8 values > 8.6 pg/mL and baseline IL-6 values > 1.6 pg/mL allowed the identification of patients achieving negative CRP at T2 (AUC = 0.75, sensitivity = 74%, specificity = 76%, p < 0.001) and patients with faecal calprotectin values < 250 mg/kg at T2 (AUC = 0.71, sensitivity = 78%, specificity = 63%, p = 0.004). In conclusion, our study highlights a potential clinical role of serum cytokine levels for the prediction of clinical and biochemical steroid-free response in patients treated with vedolizumab.

show abstract

Faecal calprotectin is the biomarker that best distinguishes remission from different degrees of endoscopic activity in Crohn’s disease

Cited by 19 publications

References 44 publications

Benchmark of data processing methods and machine learning models for gut microbiome-based diagnosis of inflammatory bowel disease

Benchmark of data processing methods and machine learning models for gut microbiome-based diagnosis of inflammatory bowel disease

Efficacy of a Preparation Based on Calcium Butyrate, Bifidobacterium bifidum, Bifidobacterium lactis, and Fructooligosaccharides in the Prevention of Relapse in Ulcerative Colitis: A Prospective Observational Study

Serum Interleukin-6 and -8 as Predictors of Response to Vedolizumab in Inflammatory Bowel Diseases

Contact Info

Product

Resources

About