New Digital Twin Predicts Outcomes of Brain Cancer Treatments

Researchers at the University of Michigan (U-M) have developed a system that leverages both AI and machine learning to create a digital twin of a patient’s brain cancer in order to predict how that patient will respond to different treatments. This tool promises to take personalized cancer care a step higher. 

The study, whose findings appeared in the journal Cell Metabolism, focused on gliomas. The team sought to establish how to distinguish between patients that are likely to benefit when their diets exclude certain amino acids (proteins) and those who are unlikely to benefit from such dietary changes. Some gliomas starve when these nutrients aren’t available in the food that a patient consumes, but some gliomas can “scavenge” for those amino acids from within their surroundings and therefore continue growing. 

The challenge has been how to identify which particular patients diagnosed with gliomas can benefit from amino acid restrictions in their diet and which patients are unlikely to benefit from such approaches. 

The study team leveraged synthetic metabolic data of patients and used it to train the convolutional neural network. The data used included information on chemical and biological processes that take place as food is metabolized in the body. Eight glioma patients that were undergoing brain surgery were given labeled glucose so that data could be obtained on how this and other nutrients were metabolized and utilized within the tumor environment. 

The model then created digital twins for each of those patients and this model got to work predicting the different ways in which the tumors processed and consumed those nutrients. Attention was focused on metabolic flux, which is the variation in the speed at which the body processes and utilizes nutrients. Data from blood samples and the genetic profile of each patient’s tumor aided the training process. 

The digital twin of each patient was accurate in pointing out which patients could benefit from metabolic therapies and which ones were unlikely to benefit. These results were confirmed when tests were done on mice, proving that the digital twins could be a valuable tool in determining which individuals stood a chance of benefiting from certain treatments even before such treatments have been administered. 

The potential of this approach is immense, because it could save valuable time and other resources that could have been expended in treating patients who are unlikely to benefit from a given treatment approach. The method could also find application in a lot of other conditions beyond gliomas or brain cancers in general. 

Given that many companies like CNS Pharmaceuticals Inc. (NASDAQ: CNSP) are hard at work developing new treatments against brain cancers, the machine learning model could be instrumental in getting any new commercialized treatments to patients whose digital twins indicate that the treatment will be effective in killing the tumor cells. Those unlikely to respond could then be given other treatments, helping patients save time, money and the challenges associated with any attendant treatment side effects. 

NOTE TO INVESTORS: The latest news and updates relating to CNS Pharmaceuticals Inc. (NASDAQ: CNSP) are available in the company’s newsroom at https://ibn.fm/CNSP 

About BioMedWire

BioMedWire (“BMW”) is a specialized communications platform with a focus on the latest developments in the Biotechnology (BioTech), Biomedical Sciences (BioMed) and Life Sciences sectors. It is one of 75+ brands within the Dynamic Brand Portfolio @ IBN that delivers: (1) access to a vast network of wire solutions via InvestorWire to efficiently and effectively reach a myriad of target markets, demographics and diverse industries; (2) article and editorial syndication to 5,000+ outlets; (3) enhanced press release enhancement to ensure maximum impact; (4) social media distribution via IBN to millions of social media followers; and (5) a full array of tailored corporate communications solutions. With broad reach and a seasoned team of contributing journalists and writers, BMW is uniquely positioned to best serve private and public companies that want to reach a wide audience of investors, influencers, consumers, journalists and the general public. By cutting through the overload of information in today’s market, BMW brings its clients unparalleled recognition and brand awareness.

BMW is where breaking news, insightful content and actionable information converge.

To receive SMS alerts from BioMedWire, “Biotech” to 888-902-4192 (U.S. Mobile Phones Only)

For more information, please visit https://www.BioMedWire.com

Please see full terms of use and disclaimers on the BioMedWire website applicable to all content provided by BMW, wherever published or re-published: https://www.BioMedWire.com/Disclaimer

BioMedWire
San Francisco, CA
www.BioMedWire.com
415.949.5050 Office
Editor@BioMedWire.com

BioMedWire is powered by IBN