detect the disease by the way you walk

THE ESSENTIAL

  • After Alzheimer’s, Parkinson’s disease is the second most common degenerative disease in France.
  • It is characterized by three main motor symptoms: tremors, akinesia (slowness of movement), and hypertonicity, an abnormal stiffness of the muscles.

Each year, 25,000 people in France are diagnosed with Parkinson’s disease, according to theNational Institute of Health and Medical Research (To insert). This neurodegenerative disease is difficult to diagnose because no imaging test or biological test can be sure that a patient has it. The neurologist must then rely on clinical tests when the symptoms are non-specific and are not systematically present.

Parkinsons: 4 gait characteristics to detect the disease

But researchers may have found a solution to improve the diagnosis of this disease. In a study published in the journal gait and posture, explain that they have developed artificial intelligence tools that can determine if a patient will suffer from this pathology by analyzing the way they walk.

Specifically, the researchers found that four gait characteristics allowed the diagnosis to be made: the speed, length and amplitude of the stride as well as its regularity (or consistency). To evaluate the severity of the disease, the most significant factors were the regularity of the steps and the time during which both feet are in contact with the ground.

Parkinson: “diagnostic accuracy is around 80%”

To achieve this result, the authors studied data from 63 participants who were over the age of 50. “We chose gait parameters as important criteria because gait disturbances appear early in Parkinson’s disease and worsen over time, explained Fabio Augusto Barbieri, one of the authors, in a communicated. And also because they have no link with physiological parameters such as age, height and weight”.

The path of these participants was then studied to develop two artificial intelligences, one that deals with the diagnosis and the other with the evolution and severity of the disease, and six different algorithms. “Diagnostic accuracy is about 80%, assures Fabio Augusto Barbieri. We could significantly reduce this margin of diagnostic error by combining AI that diagnoses and AI that assesses evolution”. The scientists believe their work will allow for a better understanding of this disease and in particular some less visible symptoms such as walking.


Leave a Reply

Your email address will not be published. Required fields are marked *