Harnessing the Power of Artificial Intelligence to Diagnose Ovarian Cancer
BWH and Dana-Farber Cancer Institute (DFCI) researchers are using artificial intelligence to detect ovarian cancer early and accurately with a simple blood test.
The team looked at a set of molecules called microRNAs, which help control where and when genes are activated. With the aid of an advanced computer algorithm, researchers identified a network of microRNAs that are associated with risk of ovarian cancer and can be detected from a blood sample.
Artificial intelligence, also known as AI, is a branch of computer science in which machines are trained to identify patterns and make predictions after analyzing large amounts of data.
“When we train a computer to find the best microRNA model, it’s a bit like identifying constellations in the night sky. At first, there are just lots of bright dots, but once you find a pattern, wherever you are in the world, you can pick it out,” said Kevin Elias, MD, of BWH’s Department of Obstetrics and Gynecology, and lead author of the study, published in eLife.
Unlike other parts of the genetic code, microRNAs circulate in the blood, making it possible to measure their levels from a sample.
“MicroRNAs are the copyeditors of the genome: Before a gene gets transcribed into a protein, they modify the message, adding proofreading notes to the genome,” said Elias, who collaborated with Dipanjan Chowdhury, PhD, chief of the Division of Radiation and Genomic Stability at DFCI.
Need for Early Detection
Most women are diagnosed with ovarian cancer when the disease is at an advanced stage, at which point only about a quarter of patients will survive for at least five years. But for women whose cancer is unexpectedly found at an early stage, survival rates are much higher.
Existing early-detection blood tests frequently report false positives and have shown no meaningful effect on survival rates. With this in mind, BWH and DFCI researchers sought to develop a tool that would be more sensitive and specific in detecting cases of early-stage ovarian cancer.
To do this, the team investigated the microRNAs in blood samples from 135 women before they underwent surgery or chemotherapy. These samples were used to train a computer program to look for differences in microRNA that indicated the presence of ovarian cancer and to accurately distinguish samples from harmless non-cancerous masses.
When the computer program predicted cancer, it was right more than 90 percent of the time. Similarly, a negative test reflected absence of cancer about 80 percent of the time, which is comparable to the accuracy of a Pap smear test.
“The key is that this test is very unlikely to misdiagnose ovarian cancer and give a positive signal when there is no malignant tumor. This is the hallmark of an effective diagnostic test,” said Chowdhury.
To move the diagnostic tool out of the lab and into the clinic, the research team will need to monitor patient samples further. They are particularly interested in determining if the tool will be useful for women at high risk of ovarian cancer as well as the general population.