Linking gene expression to clinical outcomes in pediatric Crohn's disease using machine learning.

Autor: Chen KA; Center for Gastrointestinal Biology and Disease, University of North Carolina at Chapel Hill, 7314 Medical Biomolecular Research Building, 111 Mason Farm Road, Chapel Hill, NC, 27599, USA.; Department of Surgery, University of North Carolina at Chapel Hill, Chapel Hill, USA., Nishiyama NC; Center for Gastrointestinal Biology and Disease, University of North Carolina at Chapel Hill, 7314 Medical Biomolecular Research Building, 111 Mason Farm Road, Chapel Hill, NC, 27599, USA.; Departments of Genetics and Biology, Curriculum in Bioinformatics and Computational Biology, University of North Carolina at Chapel Hill, 5022 Genetic Medicine Building, 120 Mason Farm Road, Chapel Hill, NC, 27599, USA., Kennedy Ng MM; Center for Gastrointestinal Biology and Disease, University of North Carolina at Chapel Hill, 7314 Medical Biomolecular Research Building, 111 Mason Farm Road, Chapel Hill, NC, 27599, USA.; Departments of Genetics and Biology, Curriculum in Bioinformatics and Computational Biology, University of North Carolina at Chapel Hill, 5022 Genetic Medicine Building, 120 Mason Farm Road, Chapel Hill, NC, 27599, USA., Shumway A; Joint Department of Biomedical Engineering, University of North Carolina at Chapel Hill, Chapel Hill, USA., Joisa CU; Department of Biomedical Sciences, College of Veterinary Medicine, Cornell University, Ithaca, USA., Schaner MR; Center for Gastrointestinal Biology and Disease, University of North Carolina at Chapel Hill, 7314 Medical Biomolecular Research Building, 111 Mason Farm Road, Chapel Hill, NC, 27599, USA., Lian G; Center for Gastrointestinal Biology and Disease, University of North Carolina at Chapel Hill, 7314 Medical Biomolecular Research Building, 111 Mason Farm Road, Chapel Hill, NC, 27599, USA., Beasley C; Center for Gastrointestinal Biology and Disease, University of North Carolina at Chapel Hill, 7314 Medical Biomolecular Research Building, 111 Mason Farm Road, Chapel Hill, NC, 27599, USA., Zhu LC; Department of Pathology and Laboratory Medicine, University of North Carolina at Chapel Hill, Chapel Hill, USA., Bantumilli S; Department of Pathology and Laboratory Medicine, University of North Carolina at Chapel Hill, Chapel Hill, USA., Kapadia MR; Department of Surgery, University of North Carolina at Chapel Hill, Chapel Hill, USA., Gomez SM; Department of Biomedical Sciences, College of Veterinary Medicine, Cornell University, Ithaca, USA., Furey TS; Center for Gastrointestinal Biology and Disease, University of North Carolina at Chapel Hill, 7314 Medical Biomolecular Research Building, 111 Mason Farm Road, Chapel Hill, NC, 27599, USA. tsfurey@email.unc.edu.; Departments of Genetics and Biology, Curriculum in Bioinformatics and Computational Biology, University of North Carolina at Chapel Hill, 5022 Genetic Medicine Building, 120 Mason Farm Road, Chapel Hill, NC, 27599, USA. tsfurey@email.unc.edu., Sheikh SZ; Center for Gastrointestinal Biology and Disease, University of North Carolina at Chapel Hill, 7314 Medical Biomolecular Research Building, 111 Mason Farm Road, Chapel Hill, NC, 27599, USA. shehzad_sheikh@med.unc.edu.
Jazyk: angličtina
Zdroj: Scientific reports [Sci Rep] 2024 Feb 01; Vol. 14 (1), pp. 2667. Date of Electronic Publication: 2024 Feb 01.
DOI: 10.1038/s41598-024-52678-0
Abstrakt: Pediatric Crohn's disease (CD) is characterized by a severe disease course with frequent complications. We sought to apply machine learning-based models to predict risk of developing future complications in pediatric CD using ileal and colonic gene expression. Gene expression data was generated from 101 formalin-fixed, paraffin-embedded (FFPE) ileal and colonic biopsies obtained from treatment-naïve CD patients and controls. Clinical outcomes including development of strictures or fistulas and progression to surgery were analyzed using differential expression and modeled using machine learning. Differential expression analysis revealed downregulation of pathways related to inflammation and extra-cellular matrix production in patients with strictures. Machine learning-based models were able to incorporate colonic gene expression and clinical characteristics to predict outcomes with high accuracy. Models showed an area under the receiver operating characteristic curve (AUROC) of 0.84 for strictures, 0.83 for remission, and 0.75 for surgery. Genes with potential prognostic importance for strictures (REG1A, MMP3, and DUOX2) were not identified in single gene differential analysis but were found to have strong contributions to predictive models. Our findings in FFPE tissue support the importance of colonic gene expression and the potential for machine learning-based models in predicting outcomes for pediatric CD.
(© 2024. The Author(s).)
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje