HOUSTON – A machine-learning algorithm may offer the possibility of early diagnosis of schizophrenia by using a blood test, according to a team led by researchers at Baylor College of Medicine.
The machine, called SPLS-DA, uses the algorithm strategy to “analyze specific regions of the human genome called CoRSIVs, hoping to reveal epigenetic markers for the condition,” according to a release.
The team looks at the DNA from the blood samples and the epigenetic markers, which differ between people diagnosed with the disease and people without the disease. From there, the model will assess the person’s probability of having schizophrenia, according to the release. According to an independent dataset, it revealed that the testing model can identify schizophrenia patients with 80% accuracy, according to the release.
“Schizophrenia is a devastating disease that affects about 1% of the world’s population,” said corresponding author Dr. Robert A. Waterland professor of pediatrics – nutrition at the USDA/ARS Children’s Nutrition Research Center at Baylor and of molecular and human genetics. “Although genetic and environmental components seem to be involved in the condition, current evidence only explains a small portion of cases, suggesting that other factors, such as epigenetic, also could be important.”