Computational Modules

Management of IBS (Irritable Bowel Syndrome)

IBS is a common gastrointestinal disorder affecting the large intestine. It is estimated to affect 10 to 15 percent of the world’s population and 25 to 45 million people in the US alone. Symptoms of IBS include cramping, abdominal pain, bloating, constipation, diarrhea, or both. There are no definitive causes for IBS nor is there a definitive way to diagnose patients with IBS. Doctors base their diagnosis on patient-doctor discussions and the elimination of other possible conditions. This long and often tedious process is a reason why this research group sought out to see if any specific conditions within the body were consistent for certain subtypes of IBS, specifically the microbiome of the gut.

Machine Learning Method: Random Forest Model was created and optimized using a training and testing split of 70% and 30%, respectively

This research utilized random forest modeling to find correlations within data provided by Cooper Medical School to accurately diagnose patients with IBS based on their gut microbiome. The random forest model, made up of multiple decision trees, determined the top six gut bacteria found to be most important in determining a patient’s subtype of IBS. This will allow for healthcare clinicians to provide the best diets and supplements as studies have proven that the diet of a patient has a large influence on the symptoms a patient experiences as well as their severity.

With this research, an online application was developed where the user can input their own values for these top 6 gut bacteria and get a prediction for the subtype of IBS the patient could have. The figure below depicts what the user will see when values are inputted and a prediction is made.

The IBS Diagnosis Application can be accessed publicly at https://ibsdiagnosis.shinyapps.io/IBSDiagnosis/

A tutorial on how to use the IBS Diagnosis Application is provided below.