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.

Solvent Recovery for Reuse and Recycling

Background: Solvents are mainly used in the pharmaceutical, fine, and specialty chemicals industries for cleaning, extraction, dissolution, and as reaction media. Thus, they are also a major constituent in the waste streams of these industries. Incineration, on-, and off-site disposal are the traditional solvent waste handling methods. These conventional disposal techniques increase the carbon and environmental footprint of industrial processes. Instead of disposal, there can be a more preferable way to recover these solvents for reuse. Therefore, having a framework to help recover solvents for reuse will help reduce the cost and environmental footprint of these production processes.

Proposed Solution and Projections: To help recover solvents from industrial waste streams, a proposed framework leading to a software application was developed that has the potential to help industries save capital and reduce their environmental footprint.

Techno-economic Analysis and Environmental Impact Assessment

Computational Tool: Through support from the U.S. Environmental Protection Agency Pollution Prevention program, we have developed a computational tool to help industries find potential optimal pathways to recover solvents from waste streams for reuse. Through this tool, industries can estimate the annual capital and operating costs and reduce life cycle emissions when solvent recovery is implemented. Comparative assessment can be made with conventional disposal technique such as incineration. The standalone tool can be accessed on GitHub.

Application Design Architecture

More information about the development can be found in the publication:

Stengel, J.P., Lehr, A.L., Aboagye, E.A., Chea, J.D., Yenkie, K.M., 2023. Ind. Eng. Chem. Res. https://doi.org/10.1021/acs.iecr.2c02920

%d bloggers like this: