Parkinson's Disease Progression Prediction Using Longitudinal Imaging Data and Grey Wolf Optimizer-Based Feature Selection
- Title
- Parkinson's Disease Progression Prediction Using Longitudinal Imaging Data and Grey Wolf Optimizer-Based Feature Selection
- Creator
- Patil S.C.; Mane D.A.; Singh M.; Garg P.; Desai A.B.; Rawat D.
- Description
- This work uses longitudinal imaging data and a feature selection method based on the Grey Wolf Optimizer (GWO) to create a novel method for forecasting the course of Parkinson's disease.Magnetic resonance imaging (MRI) and positron emission tomography (PET) longitudinal imaging data offer important insights into the structural and functional changes in the brain over time. However, because of its great dimensionality, analysing this complicated data might be difficult. We suggest using the GWO-based feature selection method to identify the most informative imaging features related to illness development in order to solve this problem.The Grey Wolf Optimizer is an algorithm that draws inspiration from nature and imitates the way that grey wolves hunt. By effectively locating an ideal subset of features that maximise classification or regression performance, it has demonstrated promising results in feature selection challenges. GWO will be used in our investigation to choose the most pertinent imaging features from the longitudinal data, lowering dimensionality and improving the model's ability to predict outcomes.Using machine learning strategies, we will build a predictive model that includes the chosen features and longitudinal imaging data. We hope to equip clinicians with a tool to forecast the course of each patient's Parkinson's disease by utilising this model. By assisting in early diagnosis, treatment planning, and disease progression monitoring, this predictive skill can ultimately improve the overall management of Parkinson's disease and the quality of life for those who are affected. Our method has great promise for expanding the fields of neurodegenerative disease prediction and personalised therapy because it integrates longitudinal imaging data and the Grey Wolf Optimizer-based feature selection method in a novel way. 2024, Ismail Saritas. All rights reserved.
- Source
- International Journal of Intelligent Systems and Applications in Engineering, Vol-12, No. 3s, pp. 441-451.
- Date
- 2024-01-01
- Publisher
- Ismail Saritas
- Subject
- Feature selection; Grey Wolf Optimizer; Imaging data; Parkinson Disease; Progression Prediction
- Coverage
- Patil S.C., Department of General Medicine, Krishna Vishwa Vidyapeeth, Maharashtra, Karad, India; Mane D.A., Statistician Krishna Vishwa Vidyapeeth, Maharashtra, Karad, India; Singh M., School of Sciences, Christ University, Delhi NCR campus, India; Garg P., St. Andrews Institute of Technology and Management, Gurugram, Haryana, Farrukh Nagar, India; Desai A.B., Department of Computer Science and Engineering, Graphic Era Hill University, Uttarakhand, Dehradun, India; Rawat D., Department of Computer Science & Engineering, Graphic Era Deemed to be University, Uttarakhand, Dehradun, 248002, India
- Rights
- Restricted Access
- Relation
- ISSN: 21476799
- Format
- Online
- Language
- English
- Type
- Article
Collection
Citation
Patil S.C.; Mane D.A.; Singh M.; Garg P.; Desai A.B.; Rawat D., “Parkinson's Disease Progression Prediction Using Longitudinal Imaging Data and Grey Wolf Optimizer-Based Feature Selection,” CHRIST (Deemed To Be University) Institutional Repository, accessed February 24, 2025, https://archives.christuniversity.in/items/show/13790.