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

Abstract

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.

Artificial‐intelligence‐based decision support tools for the differential diagnosis of colitis

“…That the algorithm was established on a tertiary care dataset only, is a potential limitation of this algorithm. In a recently published study, the authors established a machine learning prediction model based on 702 IBD patients and 315 healthy controls 25 . The best classifier based on 16 parameters (including age, haemoglobin, and faecal calprotectin) achieved a mean average precision of 91% for UC and 97% for MC but could not distinguish various types of colitis either.…”

Machine Learning‐Based Quantification of Patient Factors Impacting Remission in Patients With Ulcerative Colitis: Insights from Etrolizumab Phase III Clinical Trials

“…Among the key factors identified from the induction phase ML model, are the variables BCRP and MADCAM1: the former being a well-established marker in IBD 27 and has been identified as an influential prediction in prior ML analyses 28,29 ; the latter being the ligand of lymphocyte migration which is thought to be a key disease process in IBD. Furthermore, the ML model demonstrated that adalimumab treatment contributed to remission at the end of induction.…”

Canine chronic enteropathy—Current state-of-the-art and emerging concepts

“…Artificial intelligence (AI) describes a variety of digital applications where human tasks (e.g., decision trees) are performed computer-based ( 238 ). As a particular AI application, machine learning (ML) algorithms can be developed to predict data (e.g., disease, disease subclassification) or outcomes based on previously generated patient data ( 239 ). The availability of novel biomarkers in addition to established clinical, endoscopic, and histologic scoring systems lends itself to integrating all these variables (potentially together with the results of other diagnostics such as abdominal ultrasonography) into meaningful ML algorithms ( 240 ) for the diagnosis and subclassification of canine CIE or the prediction of individual outcomes.…”