Predicting Parkinson’s Disease Progression: Evaluation of Ensemble Methods in Machine Learning

Table 1

List of acronyms in this paper.

Acronyms	Description
AI	Artificial intelligence
ANFIS	Adaptive neurofuzzy inference system
ANN	Artificial neural network
CART	Tree classification and regression
CDSSs	Clinical decision support systems
CGP	Cartesian genetic programming
CSPA	Cluster-based similarity partitioning algorithm
CNN	Convolutional neural network
DBN	Deep belief network
DT	Decision tree
DSS	Decision support systems
DNN	Deep neural network
ebTL	Empirical Bayes transfer learning
ECG	Electrocardiogram
ELM	Extreme learning machines
EM	Expectation-maximization
EMG	Electromyogram
FDR	Fisher discriminant ratio
FNS	Fuzzy neural system
FOG	Freezing of gait
GA	Genetic algorithm
GRNN	Generalized regression neural networks
HGPA	Hypergraph partitioning algorithm
IMU	Inertial measurement unit
ISVR	Incremental support vector regression
K-NN	K-nearest neighbor
LR	Logistic regression
LSTM	Long short-term memory
LSVM	Lagrangian support vector machine
MAE	Mean absolute error
ML	Machine learning
MLP	Multilayer perceptron
MSA	Multiple system atrophy
MLP-LSVM	Multilayer perceptron-Lagrangian support vector machine
MLR	Multiple linear regression
NB	Naïve Bayes
NN	Neural network
NIPALS	Nonlinear iterative partial least squares
OPF	Optimum-path forest
PCA	Principal component analysis
PCG	Phonocardiogram
PD	Parkinson’s disease
PSP	Progressive supranuclear palsy
RBM	Restricted Boltzmann machine
RF	Random forest
RBF	Radial basis functions
RNN	Recurrent neural network
RSSD	Sparse signal decomposition
RMSE	Root mean squared error
RBF	Radial basis functions
RNN	Recurrent neural network
RSSD	Sparse signal decomposition
RMSE	Root mean squared error
rTL	Regularized transfer learning
SOM	Self-organizing map
SVD	Singular value decomposition
SPECT	Single-photon emission computerized tomography
SVR	Support vector regression
SVM	Support vector machine
T-F	Time-frequency
UPDRS	Unified Parkinson’s disease rating scale
WK	Wavelet kernel