A data-centric branch of artificial intelligence may take the guesswork
out of selecting the appropriate chemotherapy treatment for breast
cancer patients
Patients with the same type of breast cancer can have different
responses to the same medication, which leaves doctors on a tough spot; how
will they know which treatment will have the best response? If they get it
right, their patients may enter remission, but if they are wrong their patient’s
health will deteriorate.
Researchers have been
trying to find the answer of this problem; and now researchers at western
University might have the answer. They developed a machine learning algorithms,
a branch of artificial intelligence, that crunch genetic data to determine the
most likely treatment response and allow personalized treatment regimens.
“Artificial intelligence is a powerful tool for predicting
drug outcomes because it looks at the sum of all interacting genes,” said lead
researcher peter Rogan. “The earlier we treat a patient with the most effective
medication, the more likely we can effectively treat or possibly even cure that
patient.”
The researchers used a set of 40 genes that are found in 90
percent of breast cancer tumors for their analysis of data from cell lines and
tumor tissue samples from around 350 cancer patients who were treated with at
least one of the two chemotherapy drugs paclitaxel and gemcitabine.
They then set their computers to work crunching the data and
identifying associations between the drug and patient genes. Their machine
learning tool managed to predict gemcitabine resistance and paclitaxel sensitivity
with 84 percent accuracy and gemcitabine response with 62 to 71 percent
accuracy.
The researchers now plan to refine their algorithms and feed
the system more data to improve their predictions.
This is not the first case of machine learning being used to
help cancer treatment. A new company called Deep Genomics founded earlier this
year to identify never seen gene variants and mutation in various disease
including cancer, by pitting computers against large data sets.
Source: Gizmag
Source: Gizmag
Content maybe edited for content and length.
No comments:
Post a Comment