Key points:
- A new AI model can better predict cancer survival rates using doctor’s notes.
- When tested, the model demonstrated an 80% accuracy rate.
- The models can be easily scaled and trained using local data, and is applicable to every type of cancer.
Researchers from the University of British Columbia and B.C. Cancer has developed an artificial intelligence (AI) model that predicts cancer patient survival more accurately—based on oncologist notes.
The model uses natural language processing (NLP)—a branch of AI that understands complex human language—to analyze oncologist notes following a patient’s initial consultation visit. According to findings published in JAMA Network Open, identifying characteristics unique to each patient, the model was shown to predict six-month, 36-month and 60-month survival with greater than 80 percent accuracy.
“The A.I. essentially reads the consultation document like a human would read it,” said John-Jose Nunez, a psychiatrist and clinical research fellow with the UBC Mood Disorders Centre and B.C. Cancer. “These documents have many details like the patient's age, the type of cancer, underlying health conditions, past substance use, and family histories. The AI combines all of this to paint a complete picture of patient outcomes.”
Traditionally, cancer survival rates have been calculated retrospectively and categorized by only a few generic factors, such as cancer site and tissue type. The model, however, is able to pick up on unique clues within a patient’s initial consultation document to provide a more nuanced assessment. The AI was trained and tested using data from 47,625 patients across all six B.C. Cancer sites located across British Columbia.
“Because the model is trained on B.C. data, that makes it a potentially powerful tool for predicting cancer survival in the province,” said Nunez. “[But] the great thing about neural NLP models is that they are highly scalable, portable and don’t require structured data sets. We can quickly train these models using local data to improve performance in a new region.”
Additionally, the model is applicable to all cancers, whereas previous models have been limited to certain cancer types.