A new machine learning tool was created by researchers from Ohio State University (OSU) that can detect colorectal cancer, according to a release. Specifically, the equipment can “identify metabolism-related molecular profile differences between patients with colorectal cancer and healthy people.”
Additionally, the researchers discovered “metabolic shifts associated with changing disease severity and with genetic mutations known to increase the risk for colorectal cancer.” The scientists say they can use this information to observe treatment efficacy.
The tool, called PANDA, is a combination of two machine learning methods: “partial least squares-discriminant analysis (PLS-DA) for big-picture differentiation of molecular profiles, and an artificial neural network (ANN) that, in this case, pinpoints molecules that improve the platform’s predictive value.”
While the “biomarker discovery pipeline” has the ability to detect and supervise colorectal cancer in a nonintrusive way, the authors warn this technique should not replace conventional colonoscopies.
The study can be found in iMetaOmics.
