Enhanced crow search algorithm for early detection of Parkinson's disease in physically challenged patients. (15th March 2023)

• Record Type: Journal Article
• Authors: Abubakar, Raliya; Hamada, Mohamed; Hassan, Mohammed; Ilu, Saratu Yusuf; Waziri, Jamilu Usman
• Is Part Of: International journal of entertainment technology and management. Volume 1:Number 4(2022)
• Page Start: 273
• Page End: 289
• Publication Date: 2023-03-15
• Subjects: Parkinson's disease -- evolutionary algorithms -- crow search -- machine learning -- neurodegenerative disorder -- disease detection -- decision tree -- random forest -- KNN -- logistic regression
• Languages: English
• ISSNs: 1475-8954

Abstract

Diagnosing Parkinson's disease at its early stage is the central issue in the treatment of patients so they can live productive lives for as long as possible. The research to date have tended to concentrate only on predicting the disease rather than predicting it in the early stage. Furthermore, there is an increasing concern to extend the efficiency of the existing models to include physically challenged patients. In this paper, we proposed an enhanced version of the crow search algorithm (ECSA) to improve the diagnosis of Parkinson's disease. The proposed ECSA was used as an optimiser in predicting Parkinson's disease in physically challenged individuals like the blinds, lepers, and disabled. The search is centered towards helping the physically challenged individual to have proper treatment at an early stage. The experimental results gave as high prediction accuracy as 95%. The performance of the proposed enhanced algorithm was compared with that of the original CSA. The result of the experiment reveals that the proposed enhanced algorithm outperforms the original CSA.