Supervised machine learning classifies inflammatory bowel disease patients by subtype using whole exome sequencing data.

BACKGROUND: Inflammatory bowel disease (IBD) is a chronic inflammatory disorder with two main subtypes: Crohn's disease (CD) and Ulcerative Colitis (UC). Prompt subtype diagnosis enables the correct treatment to be administered. Using genomic data, we aimed to assess machine learning (ML) to classify patients according to IBD subtype.

METHODS: Whole exome sequencing from paediatric/adult IBD patients was processed using an in-house bioinformatics pipeline. This data was condensed into the per-gene, per-individual genomic burden score, GenePy. Data was split into training and testing datasets (80/20). Feature selection with a linear support vector classifier, and hyperparameter tuning with Bayesian Optimisation was performed (training data). The supervised ML method random forest was utilised to classify patients as CD or UC using three panels: I) all available genes, 2) autoimmune genes, 3) 'IBD' genes. ML results were assessed using AUROC, sensitivity and specificity on the testing dataset.

RESULTS: 906 patients were included in analysis (600 CD, 306 UC). Training data included 488 patients, balanced according to the minority class of UC. The autoimmune gene panel generated the best performing ML model (AUROC=0.68), outperforming an IBD gene panel (AUROC =0.61). NOD2 was the top gene for discriminating CD and UC, regardless of the gene panel used. Lack of variation in genes with high GenePy scores in CD patients was the best classifier of a diagnosis of UC.

DISCUSSION: We demonstrate promising classification of patients by subtype utilising random forest and WES data. Focussing on specific subgroups of patients, with larger datasets may result in better classification.