The scale of Parkinson’s disease diagnosis poses a major challenge to healthcare systems around the world.
According to the nonprofit Parkinson’s Disease Foundation, nearly 90,000 people are newly diagnosed with Parkinson’s disease each year in the United States.
Parkinson’s disease is a progressive brain disease that damages dopamine-producing neurons, causing symptoms such as tremors, stiffness, slowness of movement, and non-motor disorders such as depression and sleep problems.
The highly individual nature of this condition means that medical teams face great uncertainty when charting a long-term treatment path.
According to Parkinson’s UK, “Around 28,000 people in the UK are expected to be diagnosed with Parkinson’s disease in 2025. This works out to someone being diagnosed with Parkinson’s disease every 20 minutes.”
The NHS writes: “In the early stages, symptoms are often mild, so your doctor may have difficulty determining whether you definitely have the disease.”
This diagnostic ambiguity highlights why health care providers have traditionally relied on a reactive treatment approach.
Although there is no cure, researchers at the University of Adelaide are using machine learning to go beyond reacting to symptoms and start predicting symptoms, fundamentally changing the way health systems allocate resources.
