Category: Technology
Objective: The model helps neuro physicians/ neurologists to improve the PD symptoms, or therapeutic-treatment planning-procedures.
Background: Artificial intelligence-based machine learning (AI-ML) supervised classification systems have been widely used in Parkinson`s disease (PD) and movement disorders domain-field to detect patient’s data and extract a prognostic model.
Method: Microelectrode recording with STN-DBS for determining the PD. The simulation models based on data mining and AI-ML techniques have been created to identify the Parkinson`s disease early and reduce the motor symptoms by therapeutic method (intraoperative STN and GP DBS). With DBS there is a dramatic improvement in PD patients who received a carefully tuned regimen of oral L-dopa, the metabolic precursor to dopamine.
Results: The Parkinson datasets are often classed by a large number-of-disease measurements and a relatively slight number-of-patient records. Every bit of the data and their features are insignificant (noise). Feature selection is generally applied to enhance model performance. Graph-based feature-selection is one of the best key tasks in database-classification which reduces the computational-complexity and cost by removing irrelevant-features.The methods can support/select the best-differentiating feature-sets for classifying different Parkinson subtypes. So, this makes the identification process precise and lucid.
Conclusion: The classification accuracy shows that the proposed method can produce better results with lesser symptoms than the unique datasets.
References: 1.R.E.Abdel-Aal,GMDH based feature ranking and selection for improved classification of medical data, Journal of Biomed of Informatics. Vol.38,No.6, Pp: 456-468.2005.
2.M. F.Akay,Support vector machines combined with feature selection for breast cancer diagnosis, International. Journal of Expert Systems Appl. Vol.36,No.2, Pp: 3240-3247,2009.
To cite this abstract in AMA style:
V. Rama Raju, G. Ramaraju, V. Ramaraju. Machine learning supervised classification study for Parkinson`s disease progression through graph-based feature selection method [abstract]. Mov Disord. 2022; 37 (suppl 2). https://www.mdsabstracts.org/abstract/machine-learning-supervised-classification-study-for-parkinsons-disease-progression-through-graph-based-feature-selection-method/. Accessed November 21, 2024.« Back to 2022 International Congress
MDS Abstracts - https://www.mdsabstracts.org/abstract/machine-learning-supervised-classification-study-for-parkinsons-disease-progression-through-graph-based-feature-selection-method/