Ad Blocker Detected
Our website is made possible by displaying online advertisements to our visitors. Please consider supporting us by disabling your ad blocker.
Sept. 1, 2022 – It’s hard figuring out what the road ahead will look like for a cancer patient. A lot of evidence is considered, like the patient’s health and family history, grade and stage of the tumor, and traits of the cancer cells. But ultimately, the outlook comes down to health professionals who analyze the facts.
That can lead to “large-scale variability,” says Faisal Mahmood, PhD, an assistant professor in the Division of Computational Pathology at Brigham and Women’s Hospital. Patients with similar cancers can end up with very different prognoses, with some being more (or less) accurate than others, he says.
That’s why he and his team developed an artificial intelligence (AI) program that can form a more objective – and potentially more accurate – assessment. The aim of the research was to tell if the AI was a workable idea, and the team’s results have been published in Cancer Cell.
And because prognosis is key in deciding treatments, more accuracy could mean more treatment success, Mahmood says.
“[This technology] has the potential to generate more objective risk assessments and, subsequently, more objective treatment decisions,” he says.
Building the AI
The researchers developed the AI using data from The Cancer Genome Atlas, a public catalog of profiles of different cancers.
Their algorithm predicts cancer outcomes based on histology (a description of the tumor and how quickly 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 used more and more, Mahmood notes.
“Both are now commonly used for diagnosis at major cancer centers,” he says.
To test the algorithm, the researchers chose the 14 cancer types with the most data available. When histology and genomics were combined, the algorithm gave more accurate predictions than it did with either information source alone.
Not only that, but the AI used other markers – like the patient’s immune response to treatment – without being told to do so, the researchers found. This could mean the AI can discover new markers that we don’t even know about yet, Mahmood says.
While more research is needed – including large-scale testing and clinical trials – Mahmood is confident this technology will be used for real-life patients someday, likely in the next 10 years.
“Going forward, we will see large-scale AI models capable of ingesting 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, Mahmood says.
“Then we can continuously assess patient risk in a computational, objective manner.”