Can AI provide a more accurate cancer prognosis?

simple countdown hangover helpers 1800x1200
Alcohol warning labels need updating, researchers say
September 10, 2022
1800x1200 visiting the er for chronic pain features
Deadly “Rainbow Fentanyl” looks like candy and may attract children
September 10, 2022


Sept. 1, 2022 – It’s hard to predict what the future holds for a cancer patient. Many pieces of evidence are considered, such as the patient’s health and family history, grade and stage of the tumor, and characteristics of the cancer cells. But ultimately, the outlook depends on health professionals analyzing the facts.

That can lead to “large-scale variability,” says Faisal Mahmood, PhD, an assistant professor in the department of computational pathology at Brigham and Women’s Hospital. Patients with similar types of cancer can end up with very different prognoses, with some being more (or less) accurate than others, he says.

For this reason, he and his team have developed an artificial intelligence (AI) program that can provide a more objective — and potentially more accurate — assessment. The goal of the research was to determine if AI is a viable idea, and the team’s findings were published in cancer cell.

And since prognosis is key to deciding on treatments, more accuracy could mean more treatment success, Mahmood says.

“[This technology] has the potential to generate more objective risk assessments and consequently more objective treatment decisions,” he says.

Structure of the AI

Researchers developed the AI ​​using data from the Cancer Genome Atlas, a public catalog of profiles of different types of cancer.

Their algorithm predicts cancer outcomes based on histology (a description of the tumor and how fast the cancer cells are likely to grow) and genomics (using DNA sequencing to evaluate a tumor at the molecular level). Histology has been the diagnostic standard for more than 100 years, while genomics is gaining ground, Mahmood notes.

“Both are now commonly used for diagnosis in large cancer centers,” he says.

To test the algorithm, the researchers selected the 14 cancer types with the most available data. When histology and genomics were combined, the algorithm provided more accurate predictions than either information source alone.

Not only that, the AI ​​used other markers — like the patient’s immune response to the treatment — without being prompted, the researchers found. This could mean the AI ​​can discover new markers that we don’t even know about, Mahmood says.

What’s next

Although more research is needed — including large-scale testing and clinical trials — Mahmood is confident that someday, probably within the next 10 years, this technology will be used in real patients.

“In the future, we will see large-scale AI models that can ingest data from multiple modalities,” he says, such as radiology, pathology, genomics, medical records, and family history.

The more information the AI ​​can factor in, the more accurate its assessment will be, says Mahmood.

“Then we can continuously evaluate the patient risk mathematically and objectively.”



Source link

Leave a Reply

gdpr-image
This website uses cookies to improve your experience. By using this website you agree to our Data Protection Policy.
Read more