Donate to Science & Enterprise

S&E on Mastodon

S&E on LinkedIn

S&E on Flipboard

Please share Science & Enterprise

A.I. to Identify Treatment Drivers for Colorectal Cancer

Data and person graphic

(Gerd Altmann, Pixabay)

7 September 2018. A study will soon get underway with artificial intelligence and simulation analyzing data from clinical trials to identify factors behind responses to a treatment for colorectal cancer. The project brings together drug maker Amgen with the Alliance for Clinical Trials in Oncology and bioinformatics company GNS Healthcare to better understand factors that predict a patient’s response to the cancer therapy panitumumab, marketed as Vectiblix by Amgen.

Panitumumab is a synthetic antibody approved for treating colorectal cancer that metastasizes or spreads from its original site. The treatments, given as infusions, work by targeting and binding to proteins known as epidermal growth factor receptors on the surface of tumor cells, blocking a pathway that supports the tumor, thus preventing the cells from proliferating and killing them off. The project aims to identify factors in colorectal cancer patients that support panitumumab’s actions.

According to American Cancer Society, more than 97,000 cases of colon cancer in the U.S. are expected in 2018, along with 43,000 cases of rectal cancer. The group says colorectal cancer is the third most common cancer diagnosed, and the third-ranked cause of cancer-related deaths in the U.S., with more than 50,000 deaths expected in 2018.

For this task, GNS Healthcare’s technology is being enlisted to analyze data from clinical trials of patients with colorectal cancer. GNS Healthcare offers a technology that applies machine learning to health care information, but with a process designed to reveal causal factors in the data, not just associations. That process, which the company calls reverse engineering and forward simulation or REFS, starts by reverse engineering of data with deep-learning algorithms in large data sets from genomics, electronic health records, demographics, pharmacy and medical claims records, imaging, and mobile devices.

These algorithms yield models with potential causal factors addressing the therapy targets. GNS Healthcare, in Cambridge, Massachusetts then tests the models with a series of “what-if” simulations to find the optimum solutions, such as best therapies for specific individuals.

In this case, REFS is used to analyze data from a late-stage clinical trial sponsored by Alliance for Clinical Trials in Oncology and an intermediate-stage clinical study sponsored by Amgen testing panitumumab with other drugs, in both cases among people with metastatic colorectal cancer. Data from the trials are expected to help train REFS to identify sub-groups of patients most likely to respond to panitumumab treatments. In June 2018, GNS Healthcare reported on an analysis of factors driving colorectal cancer treatment responses at the American Society of Clinical Oncology meeting, and at the 2017 meeting reported on predictive models revealed in the study’s first phase.

GNS Healthcare applies its technology to more than cancer. As reported by Science & Enterprise in September 2017, the company described in the journal The Lancet Neurology factors predicting the decline of motor functions in individuals with Parkinson’s disease.

More from Science & Enterprise:

*     *     *

2 comments to A.I. to Identify Treatment Drivers for Colorectal Cancer