Just like a list of personalized TV shows and movies recommendations, the future of cancer treatment could be customized.
Researchers have created a new tool to predict how the disease is likely to behave based on the science behind Netflix’s algorithm.
The streaming service tracks a user’s viewing history, which is then run through artificial intelligence (AI) to find patterns on how often certain shows are watched and if the viewer gave them a thumbs up or down. The AI uses this data to generate personal recommendations.
“Just as Netflix can predict which shows you’ll choose to binge watch next, we believe that we will be able to predict how your cancer is likely to behave, based on the changes its genome has previously experienced,” the study’s co-author Ludmil Alexandrov, from UC San Diego, said.
The medical AI will be looking through genetic data within cells, more specifically on chromosomes and DNA, for “faults” in the tumors—so where, exactly, the cancer starts and stops.
Twenty-one common faults have been identified, which can help doctors better determine a cancer treatment plan to properly reflect the tumor’s characteristics by finding out how aggressive the cancer is and where its weak spots are. Tumors with shattered and reformed chromosomes were found to have the worst chances of survival.
The AI was tested on almost 10,000 patients with over 33 types of cancer. The results were published in the scientific journal Nature.
The technology, among software SigProfilerExtractor, was made available for free to other researchers with the hopes of widening their “fault” list and getting closer to creating a personalized “cancer blueprint.”
Co-author Nischalan Pillay said: “To stay one step ahead of cancer, we need to anticipate how it adapts and changes. Mutations are the key drivers of cancer, but a lot of our understanding is focused on changes to individual genes in cancer.”
He added that the medical community has been missing a bigger picture of “how vast swathes of genes can be copied, moved around or deleted without catastrophic consequences for the tumor.
“Understanding how these events arise will help us regain an advantage over cancer.”