A team of researchers from the University of British Columbia and BC Cancer has developed an artificial intelligence tool to better predict a cancer patient’s survival rate by reading their doctor’s notes.
In a Thursday press release, UBC said this new model helps predict survival rates “more accurately” and with “more readily available data” than previous tools.
“Cancer survival prediction is an important factor that can be used to improve cancer treatment,” said lead author Dr. John-Jose Nunez in the press release.
Nunez, a psychiatrist and clinical research associate at the UBC Mood Disorders Center and BC Cancer, said the AI could suggest an earlier referral for support services or a more aggressive treatment plan.
“We hope that a tool like this can be used to instantly personalize and optimize the care a patient receives,” Nunez said, adding that it could help provide patients with the best possible outcome.
The researchers said the model uses natural language processing – a branch of AI that understands complex human language – to analyze an oncologist’s notes after consulting a patient.
The results show that the model was able to predict survival at six months, 36 months and 60 months with more than 80 percent accuracy by identifying characteristics that are unique to each patient, UBC said.
“The AI reads the consultation document in essentially the same way a human would read it,” Nunez said. “These documents contain many details such as the patient’s age, type of cancer, underlying health conditions, past substance use and family histories. The AI brings all of this together to paint a more complete picture of patient outcomes.”
Nunez added that this new tool is applicable to all cancers where previous models were limited to specific cancers.
Researchers tested the model using data from 47,625 patients from six BC cancer sites across BC
“Because the model is trained on BC data, it’s a potentially powerful tool for predicting cancer survival here in the province,” Nunez said.
He said he hopes the technology can one day be used in cancer clinics across the country and around the world.
“The great thing about neural NLP models is that they’re highly scalable and portable, and they don’t require structured datasets,” he said. “We can quickly train these models with local data to improve performance in a new region. I would guess that these models provide a good basis anywhere in the world where patients can see an oncologist.”
Nunez, a recipient of the 2022-23 UBC Institute of Mental Health Marshall Fellowship, is also working on how to use AI techniques to provide cancer patients with the best possible mental health and counseling care.
“I see AI almost like a virtual assistant for doctors,” he said. “As medicine becomes more advanced, AI, which helps to sort and understand all the data, will help guide the doctor’s decisions. Ultimately, this will help improve quality of life and patient outcomes.”
