Parkinson’s is a progressive neurodegenerative disease that affects about one million people in the US. It manifests as tremors, difficulty walking, poor posture, slowing of body movements, and more. The explanation is simple: nerve cells in the area of the patient’s brain responsible for movement begin to weaken or die.
MIT News now reveals that a new invention from researchers of the MIT (Massachusetts Institute of Technology) might give classical ways of detecting Parkinson’s a run for their money. Having the appearance of a Wi-Fi router, the new AI-based invention is able to detect neurodegenerative disease as well as its severity in a patient’s brain. Furthermore, the new method can even tell if Parkinson’s is doing its dirty work by analyzing breathing patterns while the patient is sleeping.
A new neural network
The new invention is also a neural network, and it can mimic the way the human brain works through a series of algorithms.
Detecting Parkinson’s disease through the classical ways is indeed difficult, as there is no specific test to tell for sure if a person is suffering from the condition. Furthermore, symptoms can vary from person to person, and other illnesses also have some of those symptoms. Therefore, it’s pretty probable that doctors can give a wrong diagnosis, unfortunately.
Dina Katabi, who is a principal investigator at MIT Jameel Clinic, explained as MIT News quotes:
A relationship between Parkinson’s and breathing was noted as early as 1817, in the work of Dr. James Parkinson. This motivated us to consider the potential of detecting the disease from one’s breathing without looking at movements,
Some medical studies have shown that respiratory symptoms manifest years before motor symptoms, meaning that breathing attributes could be promising for risk assessment prior to Parkinson’s diagnosis.
The University of Rochester, the Mayo Clinic, and also Massachusetts General Hospital collaborated on the new research.
The new work was published in Nature Medicine.