The big "C" is something no one wants to have to face. I have watched its devastation personally on family members close to me. Early detection can literally make the difference between life and death. It has been announced that scientists have developed a cancer detection program with the use of technology and computers in early detection... Take a moment to read this research article by dennismichaellynch.com and comment on what you think!
by Scarlett Fakhar March 24, 2017 HEALTH
Scientists in California have developed a new computer program that can use blood samples to detect cancer. The program can detect tumor DNA and even locate where it is coming from in the body.
CancerLocator works by observing different molecular patterns in DNA and comparing the patterns to genetic modifications known to be caused by different types of cancer.
It was developed by a team from the University of California at Los Angeles.
“Non-invasive diagnosis of cancer is important, as it allows the early diagnosis of cancer, and the earlier the cancer is caught, the higher chance a patient has of beating the disease,” said Professor Jasmine Zhou, co-lead author of the study.
“We have developed a computer-driven test that can detect cancer, and also identify the type of cancer, from a single blood sample. The technology is in its infancy and requires further validation, but the potential benefits to patients are huge.”
The team tested the program with 29 liver cancer patients, 12 lung cancer patients, and five breast cancer patients. When it came to the test results and accuracy of cancer detection, the new program had an error rate of 0.265, which is twice as accurate as any program created in the past.
“Owing to the limited number of blood samples, the results of this study are evaluated only on three cancer types (breast, liver, and lung),” Zhou told The Independent.
“In general, the higher the fraction of tumor DNAs in blood, the more accurate the program was at producing a diagnostic result. I hope [a diagnostic test] will be available within a year. It depends on training data, testing, and machine learning. With enlarged training and testing data, we are confident to achieve much higher performance."