ICT for Health - ICT4SS @politecnicoditorino - 2019/2020
Parkinson’s disease is a neurodegenerative disorder that affects predominately dopamine-producing (“dopaminergic”) neurons in a specific area of the brain called substantia nigra. The cause of Parkinson’s disease is still unknown.
Symptoms generally develop slowly over years ad their progression is often a bit different from one person to another due to the diversity of the disease. People with PD may experience tremor, slowed movement (bradykinesia), rigid muscles, loss of automatics movements and speech changes.
In order to classify the various symptoms of PD in an easy and comprehensive way, a Unified Parkinson’s Disease Rating Scale (UPDRS) has been created in 1987 and widely used since then.
Levodopa, the most effective Parkinson’s disease medication, is a natural chemical that passes into the brain and is converted to dopamine. Levodopa’s effects last for some time, and then a new dose should be taken. Levodopa is prescribed by a neurologist that doses the quantity that a patient should take. Since the progression of PD is continuous, it’s difficult for the neurologist to optimize the treatment. It would be useful to find a faster and less costly way to measure the UPDRS score so that the neurologist could always be up to date on the patient status.
The idea of this project is to perform regression techniques to predict UPDRS on features extracted by voice recordings of patients affected by PD.