Artificial intelligence applications in inflammatory bowel disease: Emerging technologies and future directions

Inflammatory bowel disease (IBD) is a chronic, incurable disease involving the gastrointestinal tract. It is characterized by complex, unclear pathogenesis, increased prevalence worldwide, and a wide spectrum of extraintestinal manifestations and comorbidities. Recognition of IBD remains challenging and delays in disease diagnosis still poses a significant clinical problem as it negatively impacts disease outcome. The main diagnostic tool in IBD continues to be invasive endoscopy. We aimed to create an IBD machine learning prediction model based on routinely performed blood, urine, and fecal tests. Based on historical patients’ data (702 medical records: 319 records from 180 patients with ulcerative colitis (UC) and 383 records from 192 patients with Crohn’s disease (CD)), and using a few simple machine learning classificators, we optimized necessary hyperparameters in order to get reliable few-features prediction models separately for CD and UC. Most robust classificators belonging to the random forest family obtained 97% and 91% mean average precision for CD and UC, respectively. For comparison, the commonly used one-parameter approach based on the C-reactive protein (CRP) level demonstrated only 81% and 61% average precision for CD and UC, respectively. Results of our study suggest that machine learning prediction models based on basic blood, urine, and fecal markers may with high accuracy support the diagnosis of IBD. However, the test requires validation in a prospective cohort.

show abstract

“…A broad spectrum of applications of AI in inflammatory bowel disease was also reviewed by Gubatan et al [ 21 ] as we demonstrated in Figure 7 .…”

Section: Discussionmentioning

confidence: 66%

“… Location of artificial intelligence (AI) in the medical management of inflammatory bowel disease as proposed by Gubatan et al [ 21 ]. IBD, inflammatory bowel disease.…”

Section: Figurementioning

confidence: 99%

Machine Learning Prediction Model for Inflammatory Bowel Disease Based on Laboratory Markers. Working Model in a Discovery Cohort Study

Kraszewski

Szczurek

Szymczak

et al. 2021

JCM

View full text Add to dashboard Cite

show abstract

“…43 In recent years, there has been an increasing emphasis on identifying clinical and biological markers that accurately predict patient response to certain IBD treatments. 44 This is particularly important for tailoring the treatment regimen to each patient. Several studies have evaluated utility of prediction models for response to vedolizumab therapy.…”

Section: Anti-integrin Therapy: Vedolizumab (Anti-α4β7)mentioning

confidence: 99%

Anti-Integrins for the Treatment of Inflammatory Bowel Disease: Current Evidence and Perspectives

Gubatan¹,

Keyashian²,

Rubin³

et al. 2021

CEG

Self Cite

View full text Add to dashboard Cite

Leukocyte trafficking to the gastrointestinal tract is recognized to play a role in the pathogenesis of inflammatory bowel disease (IBD). Integrins are expressed on immune cells and interact with cell adhesion molecules (CAM) to mediate leukocyte trafficking. Blockade of the gut-tropic integrin α4β7 and its subunits has been exploited as a therapeutic target in IBD. Natalizumab (anti-α4) is approved for moderate to severe Crohn’s disease (CD), but its use is limited due to potential risk of progressive multifocal leukoencephalopathy. Vedolizumab (anti-α4β7) is approved for the treatment of ulcerative colitis (UC) and CD. It is the most widely used anti-integrin therapy in IBD and has been shown to be effective in both induction and maintenance therapy, with a favorable safety profile. Several models incorporating clinical, genetic, immune, gut microbial, and vitamin D markers to predict response to vedolizumab in IBD have been developed. Etrolizumab (anti-β7) blocks leukocyte trafficking via α4β7 and cell adhesion via αEβ7 integrins. Large phase 3 clinical trials evaluating efficacy of etrolizumab in the induction and maintenance of patients with IBD are underway. Other investigational anti-integrin therapies include abrilumab (anti-α4β7 IgG2), PN-943 (orally administered and gut-restricted α4β7 antagonist peptide), AJM300 (orally active small molecule inhibitor of α4), and ontamalimab (anti-MAdCAM-1 IgG).

show abstract

“…The integration of data from individual IBD-relevant ‘omes’ is currently considered as the approach that would significantly improve the understanding of IBD pathogenesis and management [ 1 , 13 , 21 ]. One of the key challenges in this process is to effectively utilize information obtained in omics studies with patients’ data stored in electronic medical records (biochemistry tests, various imaging data, symptoms at diagnosis and lifestyle specifics) [ 38 , 91 ]. Machine learning approaches offer the ability to effectively deal with the high dimensionality of these data with the final aim to translate discoveries into clinical practice.…”

Section: Future Perspectivesmentioning

confidence: 99%

“…The underlying genetic predisposition to IBD has not been completely revealed employing only the candidate gene approach or genome wide association studies (GWAS). For that reason, there is great interest in the application of AI in IBD research with the goal to improve: patient identification, differential diagnosis, disease risk prediction and clinical outcomes and classification of disease subtypes, as well as identification of disease biomarkers that could be targeted for advancing therapeutic management ( Figure 1 ) [ 1 , 28 , 38 , 39 ].…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Modeling from Omics Data as Prospective Tool for Improvement of Inflammatory Bowel Disease Diagnosis and Clinical Classifications

Stanković

Kotur

Nikčević

et al. 2021

Genes

View full text Add to dashboard Cite

Research of inflammatory bowel disease (IBD) has identified numerous molecular players involved in the disease development. Even so, the understanding of IBD is incomplete, while disease treatment is still far from the precision medicine. Reliable diagnostic and prognostic biomarkers in IBD are limited which may reduce efficient therapeutic outcomes. High-throughput technologies and artificial intelligence emerged as powerful tools in search of unrevealed molecular patterns that could give important insights into IBD pathogenesis and help to address unmet clinical needs. Machine learning, a subtype of artificial intelligence, uses complex mathematical algorithms to learn from existing data in order to predict future outcomes. The scientific community has been increasingly employing machine learning for the prediction of IBD outcomes from comprehensive patient data-clinical records, genomic, transcriptomic, proteomic, metagenomic, and other IBD relevant omics data. This review aims to present fundamental principles behind machine learning modeling and its current application in IBD research with the focus on studies that explored genomic and transcriptomic data. We described different strategies used for dealing with omics data and outlined the best-performing methods. Before being translated into clinical settings, the developed machine learning models should be tested in independent prospective studies as well as randomized controlled trials.

show abstract

Artificial intelligence applications in inflammatory bowel disease: Emerging technologies and future directions

Cited by 73 publications

References 92 publications

Machine Learning Prediction Model for Inflammatory Bowel Disease Based on Laboratory Markers. Working Model in a Discovery Cohort Study

Machine Learning Prediction Model for Inflammatory Bowel Disease Based on Laboratory Markers. Working Model in a Discovery Cohort Study

Anti-Integrins for the Treatment of Inflammatory Bowel Disease: Current Evidence and Perspectives

Machine Learning Modeling from Omics Data as Prospective Tool for Improvement of Inflammatory Bowel Disease Diagnosis and Clinical Classifications

Contact Info

Product

Resources

About