The client is one of the leaders in the healthcare industry and wanted to do something significant for those suffering from Parkinson's disease. The inconvenience the patients and their family members face in regularly visiting the clinics to detect the disease gave birth to an innovative idea - a wearable device that will prevent these visits and collect data in a simple way. This revolutionary idea is bound to increase the early detection of this disease and aid patients and doctors in battling it.

  • Industry

    Healthcare

Project Summary

Our client is a top company that makes wearable devices. It wanted to make software to help identify people who are at risk of Parkinson's disease (PD) by collecting medical data. Generally, diagnosing PD is difficult and requires regular visits to the clinician. We wanted to make the process easier for the user. We created a model that would collect the voice recordings of the user and analyze them with machine learning algorithms. We developed various models using different techniques to increase the accuracy. In the end, this device was able to improve research on PD, and 13% of people were treated at the right time with its help.

  • Since diagnosing Parkinson’s Disease (PD) is often difficult, it requires regular visits to the clinic, especially during the early stages. Keeping this in mind, our client wanted to create a non-invasive and convenient tool to diagnose PD
  • PD patients exhibit characteristic vocal features. Therefore, their voice recordings could be used to diagnose the disease.
  • Our client wanted to create a device and a model that will record the patient's voice and apply it to a dataset to accurately diagnose PD.
  • The dataset received was very technical in terms of its attributes.
  • It required much time to understand how the parameters impact the results.
  • The accuracy between the production environment and test environment was very different.
  • Proposed using classification algorithms and Ensemble techniques to diagnose Parkinson’s Disease (PD) using the patient voice recording data.
  • Using various models including Naive Bayes, Logistic Regression, SVM, Decision Tree, Random Forest, etc.
  • Comparing accuracy across these models to finalize the model for prediction before deploying.
  • There was an increase in the use of technology for PD research due to the availability of the device
  • There were 13% of people who were able to take advantage of the device and get treated at the right time.
Discuss your project

Make your vision into Reality with Narola's Expert Team

Our experts team are here to understand your project idea, discuss & provide analytical insight, cost estimates and duration to complete the project.

Book a free consultation

Frequently asked questions (FAQ)

See the answers to some of our most commonly asked questions below.

View All

Connect with us!

We will revert back to you in 24 hours.

    Awards

    As the world's leading web & mobile app development company, we have been privileged to win 13+ awards for our working process. We're honored to be a recipient of each of these awards for our hard work & customer loyalty.

    SGCCI

    SGCCI

    Best outsourcing company in SGCCI

    Know More
    Clutch

    Clutch

    Certified Top 1000 Companies Global 2021

    Know More
    Silicon

    Siliconindia

    Certified as a Mobile app Developers

    Know More
    SGCCI

    SGCCI

    Best outsourcing company in SGCCI

    Get more info
    Clutch

    Clutch

    Certified Top 1000 Companies Global 2021

    Get more info
    Silicon

    Siliconindia

    Certified as a Mobile app Developers

    Get more info