Machine learning predicts individual cancer patient responses to therapeutic drugs with high accuracy
'Precision or personalized cancer medicine is a clinical approach that strives to customize therapies based upon the genomic profiles of individual patient tumors.
The search for significant correlations in cancer-relevant datasets is a task ideally suited to computers and specifically to a branch of artificial intelligence called machine learning.*
A series of studies was designed to evaluate the accuracy of our model and to predict the responses of cancer patients, to chemotherapeutic drugs, from genomic profiles.
In addition to accurately predicting the response of cancer cell lines to 7 chemotherapeutic drugs, the model predicts the sensitivities of ovarian cancer patients to the same drugs. The accuracy of the model to predict responses to treatment, across 175 patients ranged from 81.5% to 82.6%".
* (“Machine learning can figure out how to perform important tasks by generalizing from examples”.) – University of Washington
No comments:
Post a Comment