A survey of deep learning techniques based Parkinson’s disease recognition methods employing clinical data
作者：
Highlights：
• A systematic review of deep learning methods for Parkinson’s disease diagnosis.
• The review explored all existing reviews with their advantages and limitations.
• All datasets and evaluation metrics used in state-of-the-art methods are explored.
• Numerical results comparison was also provided for state-of-the-art methods.
• Challenges and future directions in the domain of Parkinson disease are presented.
摘要
•A systematic review of deep learning methods for Parkinson’s disease diagnosis.•The review explored all existing reviews with their advantages and limitations.•All datasets and evaluation metrics used in state-of-the-art methods are explored.•Numerical results comparison was also provided for state-of-the-art methods.•Challenges and future directions in the domain of Parkinson disease are presented.
论文关键词：Parkinson’s disease,Clinical data,Performance evaluation,Deep learning,Machine learning,Analysis
论文评审过程：Received 3 January 2022, Revised 4 June 2022, Accepted 30 June 2022, Available online 8 July 2022, Version of Record 14 July 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.118045
