Optimized machine learning methods for prediction of cognitive outcome in Parkinson's disease

Mohammad R Salmanpour; Mojtaba Shamsaei; Abdollah Saberi; Saeed Setayeshi; Ivan S Klyuzhin; Vesna Sossi; Arman Rahmim

doi:10.1016/j.compbiomed.2019.103347

Optimized machine learning methods for prediction of cognitive outcome in Parkinson's disease

Comput Biol Med. 2019 Aug:111:103347. doi: 10.1016/j.compbiomed.2019.103347. Epub 2019 Jun 28.

Authors

Mohammad R Salmanpour¹, Mojtaba Shamsaei¹, Abdollah Saberi², Saeed Setayeshi¹, Ivan S Klyuzhin³, Vesna Sossi⁴, Arman Rahmim⁵

Affiliations

¹ Department of Energy Engineering and Physics, Amirkabir University of Technology, Tehran, Iran.
² Department of Computer Engineering, Islamic Azad University, Tehran, Iran.
³ Department of Medicine, University of British Columbia, Vancouver, BC, Canada.
⁴ Department of Physics & Astronomy, University of British Columbia, Vancouver, BC, Canada.
⁵ Department of Radiology, University of British Columbia, Vancouver, BC, Canada; Department of Physics & Astronomy, University of British Columbia, Vancouver, BC, Canada; Department of Radiology, Johns Hopkins University, Baltimore, MD, USA. Electronic address: arman.rahmim@ubc.ca.

PMID: 31284154
DOI: 10.1016/j.compbiomed.2019.103347

Abstract

Background: Given the increasing recognition of the significance of non-motor symptoms in Parkinson's disease, we investigate the optimal use of machine learning methods for the prediction of the Montreal Cognitive Assessment (MoCA) score at year 4 from longitudinal data obtained at years 0 and 1.

Methods: We selected n = 184 PD subjects from the Parkinson's Progressive Marker Initiative (PPMI) database (93 features). A range of robust predictor algorithms (accompanied with automated machine learning hyperparameter tuning) and feature subset selector algorithms (FSSAs) were selected. We utilized 65%, 5% and 30% of patients in each arrangement for training, training validation and final testing respectively (10 randomized arrangements). For further testing, we enrolled 308 additional patients.

Results: First, we employed 10 predictor algorithms, provided with all 93 features; an error of 1.83 ± 0.13 was obtained by LASSOLAR (Least Absolute Shrinkage and Selection Operator - Least Angle Regression). Subsequently, we used feature subset selection followed by predictor algorithms. GA (Genetic Algorithm) selected 18 features; subsequently LOLIMOT (Local Linear Model Trees) reached an error of 1.70 ± 0.10. DE (Differential evolution) also selected 18 features and coupled with Thiel-Sen regression arrived at a similar performance. NSGAII (Non-dominated sorting genetic algorithm) yielded the best performance: it selected six vital features, which combined with LOLIMOT reached an error of 1.68 ± 0.12. Finally, using this last approach on independent test data, we reached an error of 1.65.

Conclusion: By employing appropriate optimization tools (including automated hyperparameter tuning), it is possible to improve prediction of cognitive outcome. Overall, we conclude that optimal utilization of FSSAs and predictor algorithms can produce very good prediction of cognitive outcome in PD patients.

Keywords: Feature selection; Montreal cognitive assessment (MoCA); Outcome prediction; Parkinson's disease; Predictor algorithms.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Adult
Aged
Aged, 80 and over
Algorithms
Disease Progression
Female
Humans
Longitudinal Studies
Machine Learning*
Male
Mental Status and Dementia Tests / statistics & numerical data*
Middle Aged
Models, Statistical
Parkinson Disease* / diagnosis
Parkinson Disease* / epidemiology
Parkinson Disease* / pathology