AI Model Could Help Personalize Treatment of Pediatric Brain Tumors

When treating children with brain tumors, clinicians have to carefully balance administering the needed treatment to prevent recurrence while limiting the possible side effects on the patient’s cognitive growth, quality of life and overall development. Attaining this delicate balance isn’t always easy, but a new AI tool could change that. 

A study published early this month in the journal Nature Genetics details how an AI model dubbed MANTIS could help in predicting how long a patient may survive and how aggressive their treatment needs to be to get the best possible clinical outcomes. 

The study, conducted by researchers at Harvard Medical School, involved training the AI model on existing data on nearly 3,000 patients diagnosed with medulloblastoma, a common brain cancer among children. The data also included kids with ependymoma, also a pediatric brain cancer. 

The model was trained to track how the survival chances of patients evolved over a decade after diagnosis. The data it relied on included DNA methylation profiles. These tests are currently done as patients are treated, so no new tests were required for this AI model to work. 

The model’s performance was much better than existing methods of predicting patient survival. The scientists also found that more than half of children with average-risk medulloblastoma might be candidates for lower-dose radiation without compromising survival while sparing the patients from many treatment side effects. 

In the research, patients who received lower doses of radiation to the craniospinal region tended to have better cognitive functioning and development, and the model identified a subgroup whose survival outcomes appeared comparable with lower-dose treatment. 

The study’s first author, Sabina Stefan, says they were excited to find that the tests already being undertaken during pediatric cancer care are sufficient to feed into this AI model in order to get a more accurate predictor of patient survival and get recommendations on treatment dosage during the different stages of the treatment journey. 

The study shows that while patients may be diagnosed with the same malignancy, disease outcomes can vary significantly from one individual to the next, and so treatment approaches can’t be uniform across the group. 

The possible benefits of using this AI model to support clinicians are immense, ranging from potentially cutting treatment costs for some patients, ensuring minimal disruptions to patients’ quality of life, and confidently tweaking treatment dosage to maximize survival. 

If the model is validated in large clinical trials and gets approved for use in clinical settings, the treatments being developed by entities like CNS Pharmaceuticals Inc. (NASDAQ: CNSP) could pack a bigger punch for a lot more patients with pediatric brain cancers. 

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
Austin, Texas
www.BioMedWire.com
512.354.7000 Office
Editor@BioMedWire.com

BioMedWire is powered by IBN

Archives

Select A Month

Official NewsWire Relationships

BIO Informa DGE Dynamic Global Events DTC Healthcare Conference Kiasco Reasearch Nexus Conferences Octane

BioMedWire Currently Accepts

Bitcoin

Bitcoin

Bitcoin Cash

Bitcoin Cash

Ethereum

Ethereum

Litecoin

Litecoin

USD Coin

USD Coin

Contact us: 512.354.7000