Dataset Information

Machine learning identifies novel blood protein predictors of penetrating and stricturing complications in newly diagnosed paediatric Crohn's disease.

ABSTRACT:

Background

There is a need for improved risk stratification in Crohn's disease.

Aim

To identify novel blood protein biomarkers associated with future Crohn's disease complications METHODS: We performed a case-cohort study utilising a paediatric inception cohort, the Risk Stratification and Identification of Immunogenetic and Microbial Markers of Rapid Disease Progression in Children with Crohn's disease (RISK) study. All patients had inflammatory disease (B1) at baseline. Outcomes were development of stricturing (B2) or penetrating (B3) complications. We assayed 92 inflammation-related proteins in baseline plasma using a proximity extension assay (Olink Proteomics). An ensemble machine learning technique, random survival forests (RSF), selected variables predicting B2 and B3 complications. Selected analytes were compared to clinical variables and serology only models. We examined selected proteins in a single-cell sequencing cohort to analyse differential cell expression in blood and ileum.

Results

We included 265 patients with mean age 11.6 years (standard deviation [SD] 3.2). Seventy-three and 34 patients, respectively, had B2 and B3 complications within mean 1123 (SD 477) days for B2 and 1251 (442) for B3. A model with 5 protein markers predicted B3 complications with an area under the curve (AUC) of 0.79 (95% confidence interval [CI] 0.76-0.82) compared to 0.69 (95% CI 0.66-0.72) for serologies and 0.74 (95% CI 0.71-0.77) for clinical variables. A model with 4 protein markers predicted B2 complications with an AUC of 0.68 (95% CI 0.65-0.71) compared to 0.62 (95% CI 0.59-0.65) for serologies and 0.52 (95% CI 0.50-0.55) for clinical variables. B2 analytes were highly expressed in ileal stromal cells while B3 analytes were prominent in peripheral blood and ileal T cells.

Conclusions

We identified novel blood proteomic markers, distinct for B2 and B3, associated with progression of paediatric Crohn's disease.

SUBMITTER: Ungaro RC

PROVIDER: S-EPMC7770008 | biostudies-literature | 2021 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine learning identifies novel blood protein predictors of penetrating and stricturing complications in newly diagnosed paediatric Crohn's disease.

Ungaro Ryan C RC Hu Liangyuan L Ji Jiayi J Nayar Shikha S Kugathasan Subra S Denson Lee A LA Hyams Jeffrey J Dubinsky Marla C MC Sands Bruce E BE Cho Judy H JH

Alimentary pharmacology & therapeutics 20201101 2

<h4>Background</h4>There is a need for improved risk stratification in Crohn's disease.<h4>Aim</h4>To identify novel blood protein biomarkers associated with future Crohn's disease complications METHODS: We performed a case-cohort study utilising a paediatric inception cohort, the Risk Stratification and Identification of Immunogenetic and Microbial Markers of Rapid Disease Progression in Children with Crohn's disease (RISK) study. All patients had inflammatory disease (B1) at baseline. Outcomes ...[more]

PMID: 33131065

Similar Datasets

Project description:BACKGROUND & AIMS:It is a challenge to predict how patients with small bowel Crohn's disease (CD) will respond to intensified medical therapy. We aimed to identify factors that predicted surgery within 2 years of hospitalization for CD, to guide medical versus surgical management decisions. METHODS:We performed a retrospective review of adults hospitalized for small bowel CD from 2004 through 2012 at a single academic referral center. Subjects underwent abdominal computed tomography or magnetic resonance imaging within 3 weeks of hospitalization. Imaging characteristics of small bowel dilation, bowel wall thickness, and disease activity were assessed by a single, blinded radiologist. Multivariate analysis by Cox proportional hazards regression techniques was used to generate a prediction model of intestinal resection within 2 years. RESULTS:A total of 221 subjects met selection criteria, with 32.6% undergoing surgery within 2 years of index admission. Bivariate analysis showed high-dose steroid use (>40 mg), ongoing treatment with anti-tumor necrosis factor agents at admission, platelet count, platelet:albumin ratio, small bowel dilation (?35 mm), and bowel wall thickness to predict surgery (P ? .01). Multivariate modeling demonstrated small bowel dilation >35 mm (hazard ratio, 2.92; 95% confidence interval, 1.73-4.94) and a platelet:albumin ratio ?125 (hazard ratio, 2.13; 95% confidence interval, 1.15-3.95) to predict surgery. Treatment with anti-tumor necrosis factor agents at admission conferred a nonsignificant increased trend for risk of surgery (hazard ratio, 1.61; 95% confidence interval, 0.994-2.65). CONCLUSIONS:Small bowel dilation >35 mm and high platelet:albumin ratios are independent and synergistic risk factors for future surgery in patients with structuring small bowel CD. Platelet:albumin ratios may capture the relationship between acute inflammation and cumulative damage and serve as markers of intestinal disease that cannot be salvaged with medical therapy.

Dataset Information

Machine learning identifies novel blood protein predictors of penetrating and stricturing complications in newly diagnosed paediatric Crohn's disease.

Background

Aim

Results

Conclusions

Publications

Machine learning identifies novel blood protein predictors of penetrating and stricturing complications in newly diagnosed paediatric Crohn's disease.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets