Is AI Poised to Increase Cancer Survivability? Research shows that technology can determine where tumors originate, helping doctors choose the best treatment
- In some cases, doctors have a hard time pinpointing where the tumor is coming from
- This makes it difficult to choose a treatment for those patients – reducing survival
- READ MORE: We have AI to give us chances on some VERY awkward questions
Artificial intelligence could help figure out where a patient’s cancer came from, helping doctors choose better treatments, a study suggests.
For a small percentage of patients — especially those whose cancer has spread — doctors can have a hard time pinpointing where the tumor is coming from.
This makes it much more difficult to choose a treatment for those patients, because many cancer drugs are typically developed for specific types of cancer.
Now, a new technique developed by scientists may make it easier to figure out where these puzzling cancers come from.
AI DOCTOR: A previous study found that AI gives higher quality answers and is more empathetic than real doctors
Researchers have created a computer model that can analyze the sequence of about 400 genes and use that information to predict where a given tumor originated in the body.
Using this model, the team showed that they could accurately classify at least 40 percent of tumors of unknown origin with high confidence in a dataset of about 900 patients.
This approach more than doubled the number of patients who could have been eligible for precision treatment based on the origin of their cancer.
Intae Moon, a researcher from the Massachusetts Institute of Technology, said: ‘That was the key finding in our paper – that this model could potentially be used to support treatment decisions and guide physicians towards personalized treatments for patients with cancers of unknown primary origin. . .’
Alexander Gusev, senior author of the study, added: ‘A significant number of individuals develop these cancers of unknown primary each year, and because most therapies are approved in a site-specific manner, where you need to know the primary site to deploy them . , they have very limited treatment options.
“We’re not demanding that a new drug be approved… what we’re saying is that this population may now be eligible for precision treatments that already exist.”
The findings were published in the journal Nature Medicine.
A study shows that AI gives higher quality answers and is more empathetic than real doctors.
Research by the University of California San Diego compared written answers from doctors and ChatGPT to real-world health questions to see which came out on top.
A panel of healthcare professionals preferred ChatGPT’s answers 79 percent of the time, rating them as higher quality in terms of the information provided and greater understanding. The panel didn’t know what was what.