Clinical Antibody Test to Quickly Detect Even Low Levels of Common Parasitic Infection

Neglected tropical diseases encompass a range of conditions that impact millions of individuals worldwide, primarily in impoverished regions, yet they often lack the scientific focus they require. Schistosomiasis is one such disease—a chronic parasitic infection affecting approximately 250 million people across 78 countries, especially in Africa and Latin America. Due to the limited research on schistosomiasis, advancements in diagnostic tools and treatments frequently take a backseat. Existing diagnostics for schistosomiasis do not consistently identify the infection in its early or mild stages, and blood tests often struggle to differentiate between active and past infections. If left undiagnosed and untreated, schistosomiasis can result in severe complications affecting the bladder or liver. Researchers have now identified methods to detect schistosomiasis when other, less sensitive tests fail, allowing for earlier treatment that can improve long-term outcomes.

The research findings, reported by the team at Emory University’s School of Medicine (Atlanta, GA, USA) in Science Translational Medicine, indicate potential for developing a clinical antibody test that can swiftly and easily identify even low levels of the infection. The traditional gold standard for diagnosis is the microscopic visualization of schistosoma parasite eggs, a process that can be labor-intensive and may miss infections. By integrating their expertise in infectious diseases with biological data analytics, the researchers devised a novel and previously unrecognized method for diagnosing schistosomiasis. They employed interpretable machine learning to distinguish individuals with active infections from those with past infections. Their machine learning platform was able to identify groups of biomarkers for schistosomiasis that provided valuable insights into the disease's progression in specific patients.

When comparing healthy individuals to those with infections across two human cohorts from Brazil and Kenya, the researchers uncovered previously uncharacterized signatures of active disease that can facilitate more accurate diagnosis. According to the team, basing the diagnosis on the characteristics of groups of antibodies rather than the quantity of a single marker will enhance the reliability of early disease detection. Ultimately, the researchers aim to scale the antibody test sufficiently so that it can replace many existing diagnostic techniques and be implemented quickly and easily in rural areas where schistosomiasis is most commonly found. They are optimistic that the collaboration between infectious disease expertise and machine-assisted data analysis can significantly contribute to public health.