Owkin’s AI model provides proof of concept that machine learning can predict gene expression across cancer types

Share on facebook
Share on twitter
Share on linkedin
Share on email
Share on print

Will an oncologist of the not-so-distant future be able to pull up an image of a tumor biopsy slide on a screen and—without having to order a biomarker test—see the molecular characteristics of the cancer?

To access this subscriber-only content please log in or subscribe.

If your institution has a site license, log in with IP-login or register for a sponsored account.*
*Not all site licenses are enrolled in sponsored accounts.

Login Subscribe
Matthew Bin Han Ong
Matthew Bin Han Ong
Table of Contents

YOU MAY BE INTERESTED IN

The tremendous promise—and potential peril—of the prostate-specific antigen (PSA) screening test have confounded guideline developers for decades. When introduced, PSA was one of the first and the only credible blood biomarkers for cancer screening. That a simple blood test should be used to screen for the most common cancer in men, one that was lethal for 3% of men and 5% of Black men, seemed like a slam dunk. 
With artificial intelligence becoming an increasingly ubiquitous part of the fabric of modern life, Cancer Grand Challenges has committed $10 million to a project aimed at developing AI “co-scientists”—AI agents that could help cancer researchers analyze data, generate hypotheses, and suggest new experiments.
For decades, cancer treatment has largely followed a familiar model: Identify the disease, determine its stage, and select the therapy most likely to benefit patients with similar characteristics. Even as targeted therapies and immunotherapies have transformed oncology, we have generally developed drugs for populations rather than individuals.
Matthew Bin Han Ong
Matthew Bin Han Ong

Never miss an issue!

Get alerts for our award-winning coverage in your inbox.

Login