Application of novel hybrid machine learning systems and radiomics features for non-motor outcome prediction in Parkinson’s disease

Abstract

Objectives: Parkinson's disease (PD) is a complex neurodegenerative disorder, affecting 2–3% of the elderly population. Montreal Cognitive Assessment (MoCA), a rapid nonmotor screening test, assesses different cognitive dysfunctionality aspects. Early MoCA prediction may facilitate better temporal therapy and disease control. Radiomics features (RF), in addition to clinical features (CF), are indicated to increase clinical diagnoses, etc., bridging between medical imaging procedures and personalized medicine. We investigate the effect of RFs, CFs, and conventional imaging features (CIF) to enhance prediction performance using hybrid machine learning systems (HMLS). Methods: We selected 210 patients with 981 features (CFs, CIFs, and RFs) from the Parkinson's Progression-Markers-Initiative database. We generated 4 datasets, namely using (i,ii) year-0 (D1) or year-1 (D2) features, iii) longitudinal data (D3, putting datasets in years 0&1 longitudinally next to each other), and iv) timeless data (D4, effectively doubling dataset size by listing both datasets from years 0&1 separately). First, we directly applied 23 predictor algorithms (PA) to the datasets to predict year-4 MoCA, which PD patients this year have a higher dementia risk. Subsequently, HMLSs, including 14 attribute extraction (AEA) and 10 feature selection algorithms (FSA) followed by PAs were employed to enhance prediction performances. 80% of all datapoints were utilized to select the best model based on minimum mean absolute error (MAE) resulting from 5-fold cross-validation. Subsequently, the remaining 20% was used for hold-out testing of the selected models. Results: When applying PAs without ASAs/FEAs to datasets (MoCA outcome range: [11,30]), Adaboost achieved a MAE of 1.74±0.29 on D4 with a hold-out testing performance of 1.71. When employing HMLSs, D4+Minimum_Redundancy_Maximum_Relevance (MRMR)+K_Nearest_Neighbor Regressor achieved the highest performance of 1.05±0.25 with a hold-out testing performance of 0.57. Conclusion: Our study shows the importance of using larger datasets (timeless), and utilizing optimized HMLSs, for significantly improved prediction of MoCA in PD patients.

Prediction of Cognitive Decline in Parkinson’s Disease Using Clinical and DAT SPECT Imaging Features, and Hybrid Machine Learning Systems

“…Most predictor algorithms are not able to work with a large number of input features, and, thus, it is necessary to select the optimal few features to be used as inputs. Based on previous studies [4,32,38,39,42,43,46,47], 8 classifiers (elaborated as elaborated in Supplemental Section B, part 2) such as AdaBoost Classifier (AdaC) [58], Bagging Classifier (BagC) [59], Gradient Boosting Classifier (GBC) [60], Random Forest Classifier (RandF) [61], Extreme Gradient Boosting Classifier (XGBC) [62], Multi-Layer Perceptron (MLP) [63], K-Nearest Neighbors Classifier (KNN) [64] and Extra Trees Classifier (ETC) [65] were experimentally selected among various families of learner algorithms. In addition, we used 5-fold crossvalidation and the Bayesian optimization technique to tune the hyperparameters of the classifiers.…”

“…Another study [38] set to predict cognitive decline using ML algorithms and CFs alone. In addition, other studies [39,40] were designed to predict cognitive decline using CFs as well as RFs and combinations of regression algorithms coupled with dimension reduction algorithms. Moreover, some studies [19,41] utilized simple linear regression to predict cognitive decline in PD.…”