Researchers are working on a way to use artificial intelligence to predict a patient’s response to two common chemotherapy drugs used to treat breast cancer: paclitaxel and gemcitabine. Their study was published in Molecular Oncology (2015; doi:10.1016/j.molonc.2015.07.006).

The research team, led by Peter Rogan, PhD, at the University of Western Ontario in London, Ontario, Canada, is hoping this technique will remove the guesswork in determining optimal breast cancer treatment.

Patients with the same type of cancer can have different responses to the same drug. Some patients respond well and go into remission, whereas others develop resistance to the drug. Identifying the genetic factors that lead to remission or resistance can lead to better individualized, targeted treatment regimens with better patient outcomes.

Continue Reading

The researchers began their work in 2012 by defining a stable set of genes in 90% of breast cancer tumors. They began their study with 40 genes, including several stable genes.

Next, the team combined artificial intelligence with data from cell lines and tumor tissue. Those cells and tissues came from cancer patients who received one or both of the drugs (paclitaxel and/or gemcitabine). The team worked to narrow down and then identify the genetic signatures most important for determining resistance and remission for each medication.

Using the data, the researchers were able to identify the 84% of women with breast cancer who would go into remission in response to paclitaxel. The genetic signature identified for gemcitabine was able to predict remission using preserved tumor tissue with 62% to 71% accuracy.

Now, with this data in hand, the researchers are working to further refine the genetic signatures and improve the predictions further.

“Artificial intelligence is a powerful tool for predicting drug outcomes because it looks at the sum of all the interacting genes,” said Rogan. “If we can use this technology to improve our knowledge of which medications to use, it could improve patient outcomes. The earlier we treat a patient with the most effective medication, the more likely we can effectively treat or possibly even cure that patient.”