This study will establish a clinical cohort of children with congenital diarrhea and enteropathy (CODE), mine biomarkers of CODE through multi-omics technology and construct a clinical risk prediction model.
This study will establish a clinical cohort and a clinical phenotype database of children with congenital diarrhea and enteropathy (CODE), The investigator will mine biomarkers of CODE through multi-omics technology. This study is designed to construct a clinical risk prediction model by combining artificial intelligence technology.
Study Type
OBSERVATIONAL
Enrollment
60
Yanqiu Wang
Shanghai, Shanghai Municipality, China
RECRUITINGClinical phenotype of congenital diarrhea and enteropathy in China
Describe the clinical phenotype(Birth status, family history, clinical features of diarrhea, laboratory examination, endoscopic and histological evaluation results, growth and development indicators, previous treatment and effect were collected) of congenital diarrhea and enteropathy in China,We will use our own mobile application or to collect the relevant data, which will be filled in by the parents of the child.
Time frame: Within approximately 2 years of enrollment
Biomarkers of congenital diarrhea and enteropathy with diagnostic value through microbiome, metabolome and proteome features
Plasma and stool were collected from patients and healthy control children for multi-omics screening to identify biomarkers, of which differential expression were mined through proteome(olink), microbiome(metagenomic sequencing) and metabolome( untargeted metabolomics),relevant statistical analyses were performed using non-parametric tests, such as the Wilcoxon signed-rank test.
Time frame: Within approximately 2 years of enrollment
Cinical risk prediction model for congenital diarrhea and enteropathy built by artificial intelligence and machine learning
Using artificial intelligence and machine learning to construct predictive models for congenital diarrhea and enteropathy by combining children's clinical phenotypes and multi-omics results,such as the random forest model
Time frame: Within approximately 30 months of enrollment
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.