echemi logo
Product
  • Product
  • Supplier
  • Inquiry
    Home > Food News > Nutrition News > Artificial intelligence helps detect gait changes and diagnose Parkinson's disease

    Artificial intelligence helps detect gait changes and diagnose Parkinson's disease

    • Last Update: 2023-01-05
    • Source: Internet
    • Author: User
    Search more information of high quality chemicals, good prices and reliable suppliers, visit www.echemi.com
      

    Scientists at the Human Motion Laboratory (motion-lab) at the Department of Physical Education at Paulo State University (UNESP) in Bauru, Brazil, are using artificial intelligence to help diagnose Parkinson's and estimate its progression
    .

    An article published in the journal Gait and Posture reported the findings of a study in which machine learning algorithms identified cases
    of the disease by analyzing spatial and temporal gait parameters.

    The researchers found that four gait features were most important for diagnosing Parkinson's: step size, speed, width, and consistency (or width variability).

    To measure the severity of the disease, the most important factors are the variability of step width and the double support time (during which the feet are in contact with the ground).

    "Compared to the scientific literature, our study employs a larger database than is typically used for diagnostic purposes, which is an innovation
    .
    We chose gait parameters as a key criterion because gait disorders appear in the early stages of Parkinson's disease and worsen over time, and also because they are not related to physiological parameters such as age, height, and weight," Fabio Augusto Barbieri, co-author of the paper, told Agência FAPESP
    .
    Barbieri is a professor
    in the Department of Physical Education at the United Nations Environment Programme Faculty of Science (FC).

    The study was supported
    by FAPESP through 3 projects (14/20549-0, 17/19516-8 and 20/01250-4).

    The study sample included 63 participants and 63 healthy controls, a multidisciplinary program
    of systematic physical activity conducted by FC-UNESP for Parkinson's patients, and 63 healthy controls.
    All volunteers were over
    the age of 50.
    The data was collected and fed into the repository used in the machine learning process for 7 years
    .

    A baseline assessment
    was obtained by analyzing the gait parameters of a healthy control group and comparing them to the expected levels of this age group.
    This involves using a special motion capture camera to measure the length, width, duration, speed, cadence, single- and double-step support time of each person's stride, as well as the variability and asymmetry of stride length
    .

    The researchers used the data to create two different machine learning models — one for disease diagnosis and one for assessing patient severity
    .
    Scientists from the Faculty of Engineering of the University of Porto, Portugal, participated in this part of the study
    .

    They operated on the data using 6 algorithms: Na?ve Bayesian (NB), Support Vector Machine (SVM), Decision Trees (DT), Random Forest (RF), Logistic Regression (LR), and Multilayer Perceptron (MLP).

    NB was diagnosed with 84.
    6% accuracy, while NB and RF performed best
    in assessing severity.

    "The typical accuracy rate for clinical assessment is around
    80%.
    By combining clinical assessment with artificial intelligence, we can significantly reduce the probability of
    diagnostic errors.

    Upcoming challenges

    Parkinson's is at least partly due to the degeneration of nerve cells in the brain that control movement, which is the result of
    insufficient dopamine production.
    Dopamine is a neurotransmitter
    that sends signals to the extremities.
    Low dopamine levels can affect movement, producing symptoms such as tremors, slow gait, stiffness and poor balance, as well as changes
    in the ability to speak and write.

    The current diagnosis is based on the patient's clinical history and neurological examination, and there are no specific tests
    .
    There is no exact information yet, but it is estimated that 3%-4% of people over the age of 65 have Parkinson's disease
    .

    Another co-author, PhD candidate Tiago Penedo's study, which is overseen by Barbieri, said the findings will help improve future diagnostic evaluations, but cost may be a disincentive
    .
    "We have made progress on this tool and contributed to expanding the database, but the expensive equipment we use is difficult to find
    in clinics and doctors' offices," he said.

    The equipment used in the study cost about $100,000
    .
    "It is possible to analyze gait with cheaper techniques, such as using timers, force plates, etc.
    , but the results are not accurate
    ," Penedau said.

    The researchers believe that the techniques used in this study contribute to a better understanding of the underlying mechanisms of the disease, particularly gait patterns
    .

    An older study, of which Barbieri was the last author, reported in an article published in 2021, demonstrated that Parkinson's patients had a 53%
    lower step-length synergistic effect when crossing barriers than healthy subjects of the same age and weight.
    Synergy in this case refers to the ability of the body's mobile (or musculoskeletal) system to adapt to movement, combining factors such as speed and foot position, for example, when walking down the curb (for more information visit: agency.
    faaps.
    br/35563).

    Another study, also published in the journal Gait and Posture, showed that people with Parkinson's have a harder time maintaining stability in postural control and walking trembling than their neurologically healthy peers
    .
    The authors say the findings provide new insights
    into explaining the larger, faster, and more variable swings experienced in Parkinson's patients.

    This article is an English version of an article which is originally in the Chinese language on echemi.com and is provided for information purposes only. This website makes no representation or warranty of any kind, either expressed or implied, as to the accuracy, completeness ownership or reliability of the article or any translations thereof. If you have any concerns or complaints relating to the article, please send an email, providing a detailed description of the concern or complaint, to service@echemi.com. A staff member will contact you within 5 working days. Once verified, infringing content will be removed immediately.

    Contact Us

    The source of this page with content of products and services is from Internet, which doesn't represent ECHEMI's opinion. If you have any queries, please write to service@echemi.com. It will be replied within 5 days.

    Moreover, if you find any instances of plagiarism from the page, please send email to service@echemi.com with relevant evidence.