Dataset Information

Development of a Clinical and Genetic Prediction Model for Early Intestinal Resection in Patients with Crohn's Disease: Results from the IMPACT Study.

ABSTRACT: Early intestinal resection in patients with Crohn's disease (CD) is necessary due to a severe and complicating disease course. Herein, we aim to predict which patients with CD need early intestinal resection within 3 years of diagnosis, according to a tree-based machine learning technique. The single-nucleotide polymorphism (SNP) genotype data for 337 CD patients recruited from 15 hospitals were typed using the Korea Biobank Array. For external validation, an additional 126 CD patients were genotyped. The predictive model was trained using the 102 candidate SNPs and seven sets of clinical information (age, sex, cigarette smoking, disease location, disease behavior, upper gastrointestinal involvement, and perianal disease) by employing a tree-based machine learning method (CatBoost). The importance of each feature was measured using the Shapley Additive Explanations (SHAP) model. The final model comprised two clinical parameters (age and disease behavior) and four SNPs (rs28785174, rs60532570, rs13056955, and rs7660164). The combined clinical-genetic model predicted early surgery more accurately than a clinical-only model in both internal (area under the receiver operating characteristic (AUROC), 0.878 vs. 0.782; n = 51; p < 0.001) and external validation (AUROC, 0.836 vs. 0.805; n = 126; p < 0.001). Identification of genetic polymorphisms and clinical features enhanced the prediction of early intestinal resection in patients with CD.

SUBMITTER: Kang EA

PROVIDER: S-EPMC7915022 | biostudies-literature | 2021 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Development of a Clinical and Genetic Prediction Model for Early Intestinal Resection in Patients with Crohn's Disease: Results from the IMPACT Study.

Kang Eun Ae EA Jang Jongha J Choi Chang Hwan CH Kang Sang Bum SB Bang Ki Bae KB Kim Tae Oh TO Seo Geom Seog GS Cha Jae Myung JM Chun Jaeyoung J Jung Yunho Y Kim Hyun Gun HG Im Jong Pil JP Kim Sangsoo S Ahn Kwang Sung KS Lee Chang Kyun CK Kim Hyo Jong HJ Kim Min Suk MS Park Dong Il DI

Journal of clinical medicine 20210207 4

Early intestinal resection in patients with Crohn's disease (CD) is necessary due to a severe and complicating disease course. Herein, we aim to predict which patients with CD need early intestinal resection within 3 years of diagnosis, according to a tree-based machine learning technique. The single-nucleotide polymorphism (SNP) genotype data for 337 CD patients recruited from 15 hospitals were typed using the Korea Biobank Array. For external validation, an additional 126 CD patients were geno ...[more]

PMID: 33562363

Similar Datasets

Project description:OBJECTIVES:Distinguishing intestinal tuberculosis (ITB) from Crohn's disease (CD) is difficult, although studies have reported clinical, endoscopic, imaging, and laboratory findings that help to differentiate these two diseases. We aimed to produce estimates of the predictive power of these findings and construct a comprehensive model to predict the probability of ITB vs. CD. METHODS:A systematic literature search for studies differentiating ITB from CD was conducted in MEDLINE, PUBMED, and EMBASE from inception until September 2015. Fifty-five distinct meta-analyses were performed to estimate the odds ratio of each predictive finding. Estimates with a significant difference between CD and ITB and low to moderate heterogeneity (I2<50%) were incorporated into a Bayesian prediction model incorporating the local pretest probability. RESULTS:Thirty-eight studies comprising 2,117 CD and 1,589 ITB patients were included in the analyses. Findings in the model that significantly favored CD included male gender, hematochezia, perianal disease, intestinal obstruction, and extraintestinal manifestations; endoscopic findings of longitudinal ulcers, cobblestone appearance, luminal stricture, mucosal bridge, and rectal involvement; pathological findings of focally enhanced colitis; and computed tomographic enterography (CTE) findings of asymmetrical wall thickening, intestinal wall stratification, comb sign, and fibrofatty proliferation. Findings that significantly favored ITB included fever, night sweats, lung involvement, and ascites; endoscopic findings of transverse ulcers, patulous ileocecal valve, and cecal involvement; pathological findings of confluent or submucosal granulomas, lymphocyte cuffing, and ulcers lined by histiocytes; a CTE finding of short segmental involvement; and a positive interferon-? release assay. The model was validated by gender, clinical manifestations, endoscopic, and pathological findings in 49 patients (27 CD, 22 ITB). The sensitivity, specificity, and accuracy for diagnosis of ITB were 90.9%, 92.6%, and 91.8%, respectively. CONCLUSIONS:A Bayesian model based on the meta-analytic results is presented to estimate the probability of ITB and CD calibrated to local prevalence. This model can be applied to patients using a publicly available web application.

Project description:BackgroundCardiovascular disease (CVD) has evolved into a serious public health issue that demands the use of suitable methods to estimate the risk of the disease. As a result, in a sample of individuals who completed a 3-year low-sodium salt or conventional salt intervention in a hypertensive environment, we constructed a 13-year cardiovascular (CV) event risk prediction model with a 10-year follow-up.MethodsA Cox proportional hazards model was used to build a prediction model based on data from 306 participants who matched the inclusion criteria. Both the discriminating power and the calibration of the prediction models were assessed. The discriminative power of the prediction model was measured using the area under the curve (AUC). Brier scores and calibration plots were used to assess the prediction model's calibration. The model was internally validated using the tenfold cross-validation method. The nomogram served as a tool for visualising the model.ResultsAmong the 306 total individuals, there were 100 cases and 206 control. In the model, there were six predictors including age, smoking, LDL-C (low-density lipoprotein cholesterol), baseline SBP (systolic blood pressure), CVD (cardiovascular history), and CNV (genomic copy number variation) nsv483076. The fitted model has an AUC of 0.788, showing strong model discrimination, and a Brier score of 0.166, indicating that it was well-calibrated. According to the results of internal validation, the prediction model utilised in this study had a good level of repeatability. According to the model integrating the interaction of CNVs and baseline blood pressure, the effect of baseline SBP on CV events may be greater when nsv483076 was normal double copies than when nsv483076 was copy number variation.ConclusionsThe efficacy of risk prediction models for CV events that include environmental and genetic components is excellent, and they may be utilised as risk assessment tools for CV events in specific groups to offer a foundation for tailored intervention strategies.

Dataset Information

Development of a Clinical and Genetic Prediction Model for Early Intestinal Resection in Patients with Crohn's Disease: Results from the IMPACT Study.

Publications

Development of a Clinical and Genetic Prediction Model for Early Intestinal Resection in Patients with Crohn's Disease: Results from the IMPACT Study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets