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 [WES] from paediatric/adult IBD patients was processed using an in-house bioinformatics pipeline. These data were condensed into the per-gene, per-individual genomic burden score, GenePy. Data were split into training and testing datasets [80/20]. Feature selection with a linear support vector classifier, and hyperparameter tuning with Bayesian Optimisation, were performed [training data]. The supervised ML method random forest was utilised to classify patients as CD or UC, using three panels: 1] all available genes; 2] autoimmune genes; 3] 'IBD' genes. ML results were assessed using area under the receiver operating characteristics curve [AUROC], sensitivity, and specificity on the testing dataset.

RESULTS

A total of 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 using random forest and WES data. Focusing on specific subgroups of patients, with larger datasets, may result in better classification.

Spatiotemporal and genetic regulation of A-to-I editing throughout human brain development

Posttranscriptional RNA modifications by adenosine-to-inosine (A-to-I) editing are abundant in the brain, yet elucidating functional sites remains challenging. To bridge this gap, we investigate spatiotemporal and genetically regulated A-to-I editing sites across prenatal and postnatal stages of human brain development. More than 10,000 spatiotemporally regulated A-to-I sites were identified that occur predominately in 3' UTRs and introns, as well as 37 sites that recode amino acids in protein coding regions with precise changes in editing levels across development. Hyper-edited transcripts are also enriched in the aging brain and stabilize RNA secondary structures. These features are conserved in murine and non-human primate models of neurodevelopment. Finally, thousands of cis-editing quantitative trait loci (edQTLs) were identified with unique regulatory effects during prenatal and postnatal development. Collectively, this work offers a resolved atlas linking spatiotemporal variation in editing levels to genetic regulatory effects throughout distinct stages of brain maturation.

A Systematic Review of Artificial Intelligence and Machine Learning Applications to Inflammatory Bowel Disease, with Practical Guidelines for Interpretation

BACKGROUND

Inflammatory bowel disease (IBD) is a gastrointestinal chronic disease with an unpredictable disease course. Computational methods such as machine learning (ML) have the potential to stratify IBD patients for the provision of individualized care. The use of ML methods for IBD was surveyed, with an additional focus on how the field has changed over time.

METHODS

On May 6, 2021, a systematic review was conducted through a search of MEDLINE and Embase databases, with the search structure ("machine learning" OR "artificial intelligence") AND ("Crohn* Disease" OR "Ulcerative Colitis" OR "Inflammatory Bowel Disease"). Exclusion criteria included studies not written in English, no human patient data, publication before 2001, studies that were not peer reviewed, nonautoimmune disease comorbidity research, and record types that were not primary research.

RESULTS

Seventy-eight (of 409) records met the inclusion criteria. Random forest methods were most prevalent, and there was an increase in neural networks, mainly applied to imaging data sets. The main applications of ML to clinical tasks were diagnosis (18 of 78), disease course (22 of 78), and disease severity (16 of 78). The median sample size was 263. Clinical and microbiome-related data sets were most popular. Five percent of studies used an external data set after training and testing for additional model validation.

DISCUSSION

Availability of longitudinal and deep phenotyping data could lead to better modeling. Machine learning pipelines that consider imbalanced data and that feature selection only on training data will generate more generalizable models. Machine learning models are increasingly being applied to more complex clinical tasks for specific phenotypes, indicating progress towards personalized medicine for IBD.

A systematic review of the applications of artificial intelligence and machine learning in autoimmune diseases

Autoimmune diseases are chronic, multifactorial conditions. Through machine learning (ML), a branch of the wider field of artificial intelligence, it is possible to extract patterns within patient data, and exploit these patterns to predict patient outcomes for improved clinical management. Here, we surveyed the use of ML methods to address clinical problems in autoimmune disease. A systematic review was conducted using MEDLINE, embase and computers and applied sciences complete databases. Relevant papers included "machine learning" or "artificial intelligence" and the autoimmune diseases search term(s) in their title, abstract or key words. Exclusion criteria: studies not written in English, no real human patient data included, publication prior to 2001, studies that were not peer reviewed, non-autoimmune disease comorbidity research and review papers. 169 (of 702) studies met the criteria for inclusion. Support vector machines and random forests were the most popular ML methods used. ML models using data on multiple sclerosis, rheumatoid arthritis and inflammatory bowel disease were most common. A small proportion of studies (7.7% or 13/169) combined different data types in the modelling process. Cross-validation, combined with a separate testing set for more robust model evaluation occurred in 8.3% of papers (14/169). The field may benefit from adopting a best practice of validation, cross-validation and independent testing of ML models. Many models achieved good predictive results in simple scenarios (e.g. classification of cases and controls). Progression to more complex predictive models may be achievable in future through integration of multiple data types.

Analysis and Hierarchical Clustering of Blood Results Before Diagnosis in Pediatric Inflammatory Bowel Disease

BACKGROUND

Pediatric inflammatory bowel disease (PIBD) is associated with a diagnostic delay. Blood tests are a routine part of the work-up in children with chronic abdominal symptoms (pain, diarrhea). Normal blood tests cannot exclude PIBD. We analyzed blood results at diagnosis over a 5-year period.

METHODS

Patients diagnosed from 2013 to 2017 were identified from the Southampton-PIBD database. Results were obtained up to 100 days before diagnostic endoscopy. Erythrocyte sedimentation rate (ESR), C-reactive protein (CRP), albumin, hemoglobin, platelets, packed cell volume (PCV), white cell count (WCC), and alanine transferase (ALT) were analyzed. Hierarchical clustering was applied to normalized results.

RESULTS

Two hundred fifty-six patients were included (Crohn's disease [CD], 151; ulcerative colitis [UC], 95; IBD-unclassified, 10; median age, 13.48 years; 36.7% female). Hierarchical clustering of patients revealed novel groupings enriched for CD and UC, characterized by specific patterns of results. In PIBD, 9% presented with all normal blood tests, 21.9% with normal CRP and ESR. Abnormal results were seen in all tests (ESR, 56.4% of patients; CRP, 53.4%; albumin, 28%; hemoglobin, 61.9%; platelets, 55.6%; PCV, 64.6%; WCC, 22.7%; and ALT, 7.2%). Normal inflammatory markers were more common in UC compared with CD (UC, 34%; CD, 15.8%; P = 0.0035). UC (14.4% normal) presented with all normal results more frequently than CD (CD, 5.3%; P = 0.02). CRP, ESR, and platelets were significantly higher in CD compared with UC. Albumin and hemoglobin were significantly lower.

CONCLUSIONS

Most cases of PIBD present with >1 abnormal blood result, although 1/11 patients presents with normal blood tests and 1/5 present with normal inflammatory markers. Hierarchical clustering offers the potential to produce novel groupings to inform disease categorization and best management.

Genetic Sequencing of Pediatric Patients Identifies Mutations in Monogenic Inflammatory Bowel Disease Genes that Translate to Distinct Clinical Phenotypes

OBJECTIVES

Monogenic inflammatory bowel disease (IBD) comprises rare Mendelian causes of gut inflammation, often presenting in infants with severe and atypical disease. This study aimed to identify clinically relevant variants within 68 monogenic IBD genes in an unselected pediatric IBD cohort.

METHODS

Whole exome sequencing was performed on patients with pediatric-onset disease. Variants fulfilling the American College of Medical Genetics criteria as "pathogenic" or "likely pathogenic" were assessed against phenotype at diagnosis and follow-up. Individual patient variants were assessed and processed to generate a per-gene, per-individual, deleteriousness score.

RESULTS

Four hundred one patients were included, and the median age of disease-onset was 11.92 years. In total, 11.5% of patients harbored a monogenic variant. TRIM22-related disease was implicated in 5 patients. A pathogenic mutation in the Wiskott-Aldrich syndrome (WAS) gene was confirmed in 2 male children with severe pancolonic inflammation and primary sclerosing cholangitis. In total, 7.3% of patients with Crohn's disease had apparent autosomal recessive, monogenic NOD2-related disease. Compared with non-NOD2 Crohn's disease, these patients had a marked stricturing phenotype (odds ratio 11.52, significant after correction for disease location) and had undergone significantly more intestinal resections (odds ratio 10.75). Variants in ADA, FERMT1, and LRBA did not meet the criteria for monogenic disease in any patients; however, case-control analysis of mutation burden significantly implicated these genes in disease etiology.

DISCUSSION

Routine whole exome sequencing in pediatric patients with IBD results in a precise molecular diagnosis for a subset of patients with IBD, providing the opportunity to personalize therapy. NOD2 status informs risk of stricturing disease requiring surgery, allowing clinicians to direct prognosis and intervention.

Increased prevalence of anti-TNF therapy in paediatric inflammatory bowel disease is associated with a decline in surgical resections during childhood

BACKGROUND

Anti-tumour necrosis factor-α (anti-TNF) therapy use has risen in paediatric-onset inflammatory bowel disease (PIBD). Whether this has translated into preventing/delaying childhood surgery is uncertain. The Wessex PIBD cohort was analysed for trends in anti-TNF-therapy and surgery.

AIM

To assess patients diagnosed with PIBD within Wessex from 1997 to 2017. The prevalence of anti-TNF-therapy and yearly surgery rates (resection and perianal) during childhood (<18 years) were analysed (Pearson's correlation, multivariate regression, Fisher's exact).

RESULTS

Eight-hundred-and-twenty-five children were included (498 Crohn's disease, 272 ulcerative colitis, 55 IBD-unclassified), mean age at diagnosis 13.6 years (1.6-17.6), 39.6% female. The prevalence of anti-TNF-treated patients increased from 5.1% to 27.1% (2007-2017), P = 0.0001. Surgical resection-rate fell (7.1%-1.5%, P = 0.001), driven by a decrease in Crohn's disease resections (8.9%-2.3%, P = 0.001). Perianal surgery and ulcerative colitis resection-rates were unchanged. Time from diagnosis to resection increased (1.6-2.8 years, P = 0.028) but mean age at resection was unchanged. Patients undergoing resections during childhood were diagnosed at a younger age in the most recent 5 years (2007-2011 = 13.1 years, 2013-2017 = 11.9 years, P = 0.014). Resection-rate in anti-TNF-therapy treated (16.1%) or untreated (12.2%) was no different (P = 0.25). Patients started on anti-TNF-therapy <3 years post-diagnosis (11.6%) vs later (28.6%) had a reduction in resections, P = 0.047. Anti-TNF-therapy prevalence was the only significant predictor of resection-rate using multivariate regression (P = 0.011).

CONCLUSIONS

The prevalence of anti-TNF-therapy increased significantly, alongside a decrease in surgical resection-rate. Patients diagnosed at younger ages still underwent surgery during childhood. Anti-TNF-therapy may reduce the need for surgical intervention in childhood, thereby influencing the natural history of PIBD.

Personalising medicine in inflammatory bowel disease-current and future perspectives

Up to 25% of inflammatory bowel disease (IBD) presents during childhood, often with severe and extensive disease, leading to significant morbidity including delayed growth and nutritional impairment. The classical approach to management has centred on differentiation into Crohn's disease (CD) or ulcerative colitis (UC), with subsequent treatment based on symptoms, results and complications. However, IBD is a heterogeneous condition with substantial variation in phenotype, disease course and outcome, so whilst effective treatment exists one size does not fit all. The ability to predict disease course at diagnosis, alongside tailoring medications based on response gives the potential for a more 'personalised approach'. The move to a pre-emptive strategy to prevent IBD-related complications, whilst simultaneously minimising side effects and long-term toxicity from therapy, particularly in those with relatively indolent disease, has the potential to revolutionise care. In very early-onset IBD, personalised approaches to diagnosis and management have become the standard of treatment enabling clinicians to significantly alter the outcomes of the few children with monogenic disease. However, the promise of discoveries in genomics, microbiome and transcriptomics in paediatric IBD has not yet translated to clinical application for the vast majority of patients. Despite this, the opportunity presents itself to apply data gathered at diagnosis and follow-up to predict which patients are likely to progress to complicated disease, which will respond well and which will require additional therapy. Using complex mathematics and innovative, cutting-edge machine learning (ML) techniques gives the potential to use this data to develop personalised clinical care algorithms to treat patients more effectively, reduce toxicity and improve outcome. In this review, we will consider current management of paediatric IBD, discuss how precision medicine is making inroads into clinical practice already, examine the contemporary studies applying data to stratify patients and explore how future management may be revolutionised by personalisation with clinical, genomic and other multi-omic data.

Classification of Paediatric Inflammatory Bowel Disease using Machine Learning

Paediatric inflammatory bowel disease (PIBD), comprising Crohn's disease (CD), ulcerative colitis (UC) and inflammatory bowel disease unclassified (IBDU) is a complex and multifactorial condition with increasing incidence. An accurate diagnosis of PIBD is necessary for a prompt and effective treatment. This study utilises machine learning (ML) to classify disease using endoscopic and histological data for 287 children diagnosed with PIBD. Data were used to develop, train, test and validate a ML model to classify disease subtype. Unsupervised models revealed overlap of CD/UC with broad clustering but no clear subtype delineation, whereas hierarchical clustering identified four novel subgroups characterised by differing colonic involvement. Three supervised ML models were developed utilising endoscopic data only, histological only and combined endoscopic/histological data yielding classification accuracy of 71.0%, 76.9% and 82.7% respectively. The optimal combined model was tested on a statistically independent cohort of 48 PIBD patients from the same clinic, accurately classifying 83.3% of patients. This study employs mathematical modelling of endoscopic and histological data to aid diagnostic accuracy. While unsupervised modelling categorises patients into four subgroups, supervised approaches confirm the need of both endoscopic and histological evidence for an accurate diagnosis. Overall, this paper provides a blueprint for ML use with clinical data.

Commercial chicken breeds exhibit highly divergent patterns of linkage disequilibrium

The analysis of linkage disequilibrium (LD) underpins the development of effective genotyping technologies, trait mapping and understanding of biological mechanisms such as those driving recombination and the impact of selection. We apply the Malécot-Morton model of LD to create additive LD maps that describe the high-resolution LD landscape of commercial chickens. We investigated LD in chickens (Gallus gallus) at the highest resolution to date for broiler, white egg and brown egg layer commercial lines. There is minimal concordance between breeds of fine-scale LD patterns (correlation coefficient <0.21), and even between discrete broiler lines. Regions of LD breakdown, which may align with recombination hot spots, are enriched near CpG islands and transcription start sites (P<2.2 × 10^-16), consistent with recent evidence described in finches, but concordance in hot spot locations between commercial breeds is only marginally greater than random. As in other birds, functional elements in the chicken genome are associated with recombination but, unlike evidence from other bird species, the LD landscape is not stable in the populations studied. The development of optimal genotyping panels for genome-led selection programmes will depend on careful analysis of the LD structure of each line of interest. Further study is required to fully elucidate the mechanisms underlying highly divergent LD patterns found in commercial chickens.