Machine learning enables the early detection of colorectal cancer
A team of researchers in China has combined a machine learning algorithm with cancer methylation signatures to identify colorectal cancer. The diagnostic tool involved identifying colorectal cancer-specific methylation signatures followed by a machine-learning algorithm to spot cancer in people who were at risk for developing colorectal cancer. The researchers report that the system was 87.5 percent and 89.9 percent accurate when testing for sensitivity and specificity respectively. The researchers describe their new approach to the diagnosis of colorectal cancer was found to be useful for predicting the risk of death for patients for up to 26.6 months.