Applications of Machine Learning in Parkinson's Disease Diagnosis
1Universiti Teknologi Malaysia, Johor Bahru, Malaysia
2Universiti Kebangsaan Malaysia, Bandar Baru Bangi, Malaysia
3Imam Abdulrahman Bin Faisal University, Skudai, Saudi Arabia
Applications of Machine Learning in Parkinson's Disease Diagnosis
Description
Parkinson's disease (PD) is a progressive degenerative disease of the nervous system that affects movement control. This disease affects approximately 1% of the population over 60 years old, with a prevalence of approximately 250 per 100,000 persons, and an average age at onset of between 55 and 65. PD is a very complex disorder in which individual motor features vary in their presence and severity over time. Early diagnosis of PD is essential, and so early diagnosis of PD is a subject of increasing research.
Previous studies have emphasized that the main challenge in the diagnosis of PD is the correct recognition of PD affected subjects in the early stages of the disease. Early diagnosis of PD can greatly affect the progression of the disease and the quality of life of the patient. Data mining has long been suggested as a potential tool for improving problems in early diagnosis and prediction, along with knowledge detection from medical repositories. Machine learning techniques have been effective in discovering hidden patterns in these data, and so expert systems developed by machine learning techniques can be used to assist physicians in the diagnosis and prediction of disease.
This Special Issue aims to collect recent developments in methods for Parkinson's disease diagnosis using machine learning. We seek both original research and review articles related to applications of machine learning for PD diagnosis and the considerable enhancements in the accuracy and cost-effectiveness of medical and health care services for PD such applications bring.
Potential topics include but are not limited to the following:
- Deep learning methods for Parkinson's disease diagnosis
- Clustering and classification methods for Parkinson's disease diagnosis
- Hybrid machine learning methods for Parkinson's disease diagnosis
- New algorithms using fuzzy logic approaches
- Online learning methods for Parkinson's disease diagnosis
- Efficient methods for processing and analysis of big datasets for Parkinson's disease diagnosis
- Neuro-fuzzy approaches for Parkinson's disease diagnosis
- Image processing for Parkinson's disease diagnosis
- Signal processing for Parkinson's disease diagnosis
- Scalability and accuracy issues of methods for Parkinson's disease diagnosis