early diagnosis of parkinsons disease using speech recognition4360

Parkinson?s disease (PD) is the second most common neurodegenerative disorder in the world. However, there is no diagnostic tool for PD and this can make it difficult to diagnose, especially in the early stages. But strong evidences suggest that speech is affected very early and continues to deterio

Project Title

Project Area of Specialization

Artificial Intelligence

Project Summary

Parkinson’s disease (PD) is the second most common neurodegenerative disorder in the world. However, there is no diagnostic tool for PD and this can make it difficult to diagnose, especially in the early stages. But strong evidences suggest that speech is affected very early and continues to deteriorate as the disease progresses. This makes speech signal a natural candidate for early diagnosis and quantification of PD. Hence in this project we will develop a machine learning algorithm for the automatic discrimination of speech of people with PD and healthy speakers. Early diagnosis of PD will make the treatments more effective. Also non-pharmacologic treatments, such as increased exercise, are also easier to perform in the early stages of PD and may help slow down disease progression.

Project Objectives

To design and develop a machine learning algorithm for the automatic classification of Parkinson’s vs. non-Parkinson’s speech signals. The speech signals will be recorded from native Pakistani speakers. And the speech recordings will be modelled for four speech dimensions (i.e. phonation, prosody, articulation and intelligibility).

Project Implementation Method

• A comprehensive literature review.
• Protocol development for speech recordings.
• Selection of microphone for speech recordings.
• Recruitment of normal and clinically diagnosed patients.
• Data collection 
• Pre-processing of speech signals.
• Feature extraction from preprocessed signals
• Implementation of different classifiers for the comparative analysis of normal and PD patients.
• Verification of the developed machine learning algorithm.

Benefits of the Project

• Automatic detection of Parkinson’s disease from speech signals.
• Treatment of Parkinson’s disease will be more effective in early stages hence it will help to slow down disease progression.
• The methods and techniques used in this project can be easily adapted to perform analyses of other speech disorders as well (e.g. Alzheimer's disease).
• Provides a database of speech recordings of Pakistani Parkinson’s patients and healthy speakers.

Technical Details of Final Deliverable

The final form of the project will consist of two parts. The first part will be a headset for recording speech signals. The second part will be a software system for the automatic diagnosis of Parkinson’s disease.

Final Deliverable of the Project

Software System

Core Industry

Medical

Other Industries

Core Technology

Artificial Intelligence(AI)

Other Technologies

Sustainable Development Goals

Good Health and Well-Being for People, Decent Work and Economic Growth

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com