Researchers have come a long way in identifying cancer and its sources since there is still a small chance that you’ll get cancer but have no idea where it came from. But now, researchers at DTU Systems Biology created a diagnostic program called TumorTracer, which combines genetics and computer science to accurately identify the source of CUP (cancer of unknown primary). In other words, this program can accurately diagnose cancer the quickest way possible.The program’s advanced self-learning computer algorithms were able to identify the source of cancer with 85 percent accuracy by analyzing DNA mutations in tissue samples from patients with metastasized cancer. This allowed doctors to determine the target area for treatment and also improved patients’ overall prognosis.
According to associate professor Aron Eklund of DTU Systems Biology in a press release,
We are very pleased that we can now use the same sequencing data together with our new algorithms to provide a much faster diagnosis for cancer cases that are difficult to diagnose, and to provide a useful diagnosis in cases which are currently impossible to diagnose. At the moment, it takes researchers two days to obtain a biopsy result, but we expect this time to be reduced as it becomes possible to do the sequencing increasingly faster. And it will be straightforward to integrate the method with the methods already being used by doctors.”
The DNA mutations are registered in a computer program that was developed to keep an eye out for places where primary tumors might be found. According to the researchers, the method had been tested thousands of times in areas where the primary tumor location was already known — the program was able to accurately find the tumor as well. The next step in the process is to get the computer program to accurately identify unknown tumor locations.
The researchers hope that one day the method will be able to identify the source of free cancer cells in a blood sample, creating a faster way of identifying cancer and beginning treatment.