Model predicts patients at risk for Alzheimer's 2 years in advance

MIT researchers have developed a machine learning model that forecasts the cognitive decline of patients at risk for Alzheimer's disease by predicting their cognition test scores as much as two years in advance. Researchers, who will present a paper later this week at the Machine Learning for Health Care conference at the University of Michigan, contend that experiments indicate that accurate Alzheimer's predictions can be made looking six, 12, 18 and 24 months in advance. Also See: Machine learning helps to identify early signs of Alzheimer's At the Machine Learning for Health Care conference, researchers will discuss how their model could be used for clinical trials to improve the selection of candidate drugs and participating patients who are in the disease's early stages--before symptoms are evident and when treatment has the best chance of being effective. "Accurate prediction of cognitive decline from six to 24 months is critical to designing clinical trials," says Oggi Rudovic, a researcher at the MIT Media Lab. "Being able to accurately predict future cognitive changes can reduce the number of visits the participant has to make, which can be expensive and time-consuming. Apart from helping develop a useful drug, the goal is to help reduce the costs of clinical trials to make them more affordable and done on larger scales."