Detect Hepatitis B early with our machine learning tool for life-saving results

A team of researchers in Australia has developed a machine learning algorithm that can help detect hepatitis B, a potentially life-threatening liver infection caused by the hepatitis B virus (HBV), early. The condition affects more than 296 million people globally. However, most people are unaware that they are infected, which means they don’t receive medical care. Timely detection leads to better patient outcomes and helps prevent transmission. The recommended test for HBV is an enzyme immunoassay, which is expensive and requires specialized facilities. The researchers worked with colleagues at the Nigerian Institute of Medical Research to develop an algorithm that learns from patient data, identifies patterns, and makes intelligent decisions to provide alerts and detect a patient’s HBV infection status. The algorithm relied on the results of normal blood tests for red and white blood cells, salts, enzymes, and other blood chemicals, along with results of tests for hepatitis B. The researchers trained the algorithm to identify pathology markers that predict a patient’s HBV infection status, enabling diagnosis without resorting to immunoassays. The algorithm is highly accurate, with a discrimination threshold of 90%. The researchers now intend to validate the tool using data from other sources in different settings to establish its robustness and applicability.