Chemotherapy is one the first and easiest treatment option for many types of cancer, but the question one needs to answer is which drug should be used if in case the first one fails.
Researchers of the Georgia Institute of Technology has come up with an open source decision support tool which can depict the RNA expression tied to information about the patient’s interaction with certain drugs. The tool can individually advise people about chemotherapy drugs.
In a study, the device 80% successfully advised the patients about the chemotherapy drug they should take, the researchers studied RNA expression of 152 patients record. As per the researchers, the efficiency of the device can further be improved if additional information about the patient is provided like family history and demographics.
“By looking at RNA expression in tumors, we believe we can predict with high accuracy which patients are likely to respond to a particular drug,” said John McDonald, a professor in the Georgia Tech School of Biological Sciences and director of its Integrated Cancer Research Center.
“This information could be used, along with other factors, to support the decisions clinicians must make regarding chemotherapy treatment.”
Another research which could further make this tool more precise was reported on 6 November in the Journal Scientific Reports. The study was supported by many institutions like Atlanta-based Ovarian Cancer Institute, the Georgia Research Alliance, and a National Institutes of Health fellowship.
In developing this system the researchers first extracted the RNA data from the 114 records to train the system and used the other 38 records to choose the best chemotherapy drugs which will shrink the tumors on the basis of RNA sequence.
The research started on ovarian cancer but they further expanded it by using other sets of RNA data for lung, breast, liver, and pancreatic cancers. As per McDonald, “Our model is predicting based on the drug and looking across all the patients who were treated with that drug regardless of cancer type.”
The device makes up a chart on the basis of drugs effects on the patients specific cancer. It has the ability to measure the expression levels of genes whether of DNA or RNA. Though both types of data can help the doctor to choose drug therapy but RNA has an upper hand as the cost of RNA analysis is decreasing gradually.
The hospitals and cancer centers can avail the system by an open source software. The accuracy of the result will improved as more patient’s data is analyzed. McDonald and his team members believe the open source is one of the best ways to move the algorithm in use.
“To really get this into clinical practice, we think we’ve got to open it up so that other people can try it, modify if they want to, and demonstrate its value in real-world situations,” McDonald said. “We are trying to create a different paradigm for cancer therapy using the kind of open source strategy used in internet technology.”
“The accuracy of machine learning will improve not only as the amount of training data increases but also as the diversity within that data increases,” said Evan Clayton, a Ph.D. student in the Georgia Tech School of Biological Sciences.
“There’s potential for improvement by including DNA data, demographic information, and patient histories. The model will incorporate any information if it helps predict the success of specific drugs.”