Comparison of random forest and support vector machine for prediction of cognitive impairment in Parkinson's disease

Helmanita Kibtia, Sarini Abdullah, Alhadi Bustamam

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Cognitive impairments are typical in PD and are indicated by mild cognitive impairment (PD-MCI) in the early stages or dementia (PDD) in higher stages. The Montreal Cognitive Assessment (MoCA) is an instrument commonly used for ascertaining cognitive impairments in P D. This research uses the clinical, neuroimaging, and CSF data as a predictor variable and the MoCA score as the target variable representing cognitive impairments. Machine learning approaches through support vector machine (SVM) and random forest (R F) methods were applied for modeling. The mean absolute error (MAE) and the root mean square error (RMSE) are used to compare the predicted performance values of the method's application. The experimental results showed that both S V M and RF performed well in predicting cognitive impairments in PD patients, indicated by the relatively small M A E value at 0.076 and R M S E at 0.542. This research also discovers that S V M is better than RF in predicting cognitive impairments. Meanwhile, RF presents an apparent and explicable outcome, which is beneficial for determining important variables that correspond to cognitive impairments. The five measurements with the highest mean decrease accuracy (% I n c M S E) are age of onset, phosphorylated tau, a-synuclein (aSyn), mean putamen, and total tau.

Original languageEnglish
Title of host publicationInternational Conference on Science and Applied Science, ICSAS 2020
EditorsBudi Purnama, Dewanta Arya Nugraha, Fuad Anwar
PublisherAmerican Institute of Physics Inc.
ISBN (Electronic)9780735440302
DOIs
Publication statusPublished - 16 Nov 2020
Event2020 International Conference on Science and Applied Science, ICSAS 2020 - Surakarta, Indonesia
Duration: 7 Jul 2020 → …

Publication series

NameAIP Conference Proceedings
Volume2296
ISSN (Print)0094-243X
ISSN (Electronic)1551-7616

Conference

Conference2020 International Conference on Science and Applied Science, ICSAS 2020
CountryIndonesia
CitySurakarta
Period7/07/20 → …

Fingerprint Dive into the research topics of 'Comparison of random forest and support vector machine for prediction of cognitive impairment in Parkinson's disease'. Together they form a unique fingerprint.

Cite this