Is the Random Forest Algorithm Suitable for Predicting Parkinson's Disease with Mild Cognitive Impairment out of Parkinson's Disease with Normal Cognition?

An Artificial Neural Network Predicts Gender Differences of Motor and Non-Motor Symptoms of Patients with Advanced Parkinson's Disease under Levodopa-Carbidopa Intestinal Gel

Background and Objectives: Currently, no tool exists to predict clinical outcomes in patients with advanced Parkinson's disease (PD) under levodopa-carbidopa intestinal gel (LCIG) treatment. The aim of this study was to develop a novel deep neural network model to predict the clinical outcomes of patients with advanced PD after two years of LCIG therapy. Materials and Methods: This was a longitudinal, 24-month observational study of 59 patients with advanced PD in a multicenter registry under LCIG treatment from September 2019 to September 2021, including 43 movement disorder centers. The data set includes 649 measurements of patients, which make an irregular time series, and they are turned into regular time series during the preprocessing phase. Motor status was assessed with the Unified Parkinson's Disease Rating Scale (UPDRS) Parts III (off) and IV. The NMS was assessed by the NMS Questionnaire (NMSQ) and the Geriatric Depression Scale (GDS), the quality of life by PDQ-39, and severity by Hoehn and Yahr (HY). Multivariate linear regression, ARIMA, SARIMA, and Long Short-Term Memory-Recurrent NeuralNetwork (LSTM-RNN) models were used. Results: LCIG significantly improved dyskinesia duration and quality of life, with men experiencing a 19% and women a 10% greater improvement, respectively. Multivariate linear regression models showed that UPDRS-III decreased by 1.5 and 4.39 units per one-unit increase in the PDQ-39 and UPDRS-IV indexes, respectively. Although the ARIMA-(2,0,2) model is the best one with AIC criterion 101.8 and validation criteria MAE = 0.25, RMSE = 0.59, and RS = 0.49, it failed to predict PD patients' features over a long period of time. Among all the time series models, the LSTM-RNN model predicts these clinical characteristics with the highest accuracy (MAE = 0.057, RMSE = 0.079, RS = 0.0053, mean square error = 0.0069). Conclusions: The LSTM-RNN model predicts, with the highest accuracy, gender-dependent clinical outcomes in patients with advanced PD after two years of LCIG therapy.

CERAD-NAB and flexible battery based neuropsychological differentiation of Alzheimer's dementia and depression using machine learning approaches

Depression (DEP) and dementia of the Alzheimer's type (DAT) represent the most common neuropsychiatric disorders in elderly patients. Accurate differential diagnosis is indispensable to ensure appropriate treatment. However, DEP can yet mimic cognitive symptoms of DAT and patients with DAT often also present with depressive symptoms, impeding correct diagnosis. Machine learning (ML) approaches could eventually improve this discrimination using neuropsychological test data, but evidence is still missing. We therefore employed Support Vector Machine (SVM), Naïve Bayes (NB), Random Forest (RF) and conventional Logistic Regression (LR) to retrospectively predict the diagnoses of 189 elderly patients (68 DEP and 121 DAT) based on either the well-established Consortium to Establish a Registry for Alzheimer's Disease neuropsychological assessment battery (CERAD-NAB) or a flexible battery approach (FLEXBAT). The best performing combination consisted of FLEXBAT and NB, correctly classifying 87.0% of patients as either DAT or DEP. However, all accuracies were similar across algorithms and test batteries (83.0% - 87.0%). Accordingly, our study is the first to show that common ML algorithms with their default parameters can accurately differentiate between patients clinically diagnosed with DAT or DEP using neuropsychological test data, but do not necessarily outperform conventional LR.

Leveraging Computational Intelligence Techniques for Diagnosing Degenerative Nerve Diseases: A Comprehensive Review, Open Challenges, and Future Research Directions

Degenerative nerve diseases such as Alzheimer's and Parkinson's diseases have always been a global issue of concern. Approximately 1/6th of the world's population suffers from these disorders, yet there are no definitive solutions to cure these diseases after the symptoms set in. The best way to treat these disorders is to detect them at an earlier stage. Many of these diseases are genetic; this enables machine learning algorithms to give inferences based on the patient's medical records and history. Machine learning algorithms such as deep neural networks are also critical for the early identification of degenerative nerve diseases. The significant applications of machine learning and deep learning in early diagnosis and establishing potential therapies for degenerative nerve diseases have motivated us to work on this review paper. Through this review, we covered various machine learning and deep learning algorithms and their application in the diagnosis of degenerative nerve diseases, such as Alzheimer's disease and Parkinson's disease. Furthermore, we also included the recent advancements in each of these models, which improved their capabilities for classifying degenerative nerve diseases. The limitations of each of these methods are also discussed. In the conclusion, we mention open research challenges and various alternative technologies, such as virtual reality and Big data analytics, which can be useful for the diagnosis of degenerative nerve diseases.

Determination of the motor status of patients with advanced Parkinson’s disease under levodopa–carbidopa intestinal gel using a machine learning model

BACKGROUND

Despite the careful selection of candidate patients, the levodopa-carbidopa intestinal gel (LCIG) treatment of advanced Parkinson's disease (PD) remains challenging due to a complex interplay between motor and non-motor symptoms. We developed a random forest (RF) model to determine the postoperative motor outcome of patients with advanced PD at 2 years under the LCIG therapy by using motor and non-motor data from a Greek multicenter, observational registry (ForHealth S.A.).

METHODS

This was a prospective 24-month, observational study of 59 patients with advanced PD under LCIG treatment from September 2019 to September 2021. Motor status was assessed with the Unified Parkinson's Disease Rating Scale (UPDRS) parts III and IV. Non-motor symptoms (NMS) were assessed by the Non-Motor Symptoms Questionnaire (NMSQ) and the Geriatric Depression Scale (GDS).

RESULTS

We demonstrated that the proper combination of motor and non-motor measures significantly determines the motor outcome (UPDRS-III year 2: 23.57 ± 14.22 p < 0.001), reducing the RMSE (root-mean-square-error) from 3.487279 to 3.066292, suggesting that the optimized model performed well. Based on the "IncNodePurity," the major determinant factors of UPDRS-III (year 2) were, in descending order: UPDRS-III (year 0), disease duration, NMSQ (year 2), age, NMSQ (year 0), time off (hours) (year 2), time dyskinesia (year 0), quality of life (year 2) after the LCIG implementation.

CONCLUSIONS

The novelty of this model is the possibility to determine the motor outcome after two years of LCIG. This model could be also useful for not specialized Parkinson's neurologists, to improve patient counseling, expectation management, and patient satisfaction with LCIG therapy.

Altered Prefrontal Blood Flow Related With Mild Cognitive Impairment in Parkinson's Disease: A Longitudinal Study

Cognitive impairment is a common non-motor symptom in Parkinson's disease (PD), with executive dysfunction being an initial manifestation. We aimed to investigate whether and how longitudinal changes in the prefrontal perfusion correlate with mild cognitive impairment (MCI) in patients with PD. We recruited 49 patients with PD with normal cognition and 37 matched healthy control subjects (HCs). Patients with PD completed arterial spin labeling MRI (ASL–MRI) scans and a comprehensive battery of neuropsychological assessments at baseline (V0) and 2-year follow-up (V1). HCs completed similar ASL–MRI scans and neuropsychological assessments at baseline. At V1, 10 patients with PD progressed to MCI (converters) and 39 patients remained cognitively normal (non-converters). We examined differences in the cerebral blood flow (CBF) derived from ASL–MRI and neuropsychological measures (a) between patients with PD and HCs at V0 (effect of the disease), (b) between V1 and V0 in patients with PD (effect of the disease progression), and (c) between converters and non-converters (effect of the MCI progression) using t-tests or ANOVAs with false discovery rate correction. We further analyzed the relationship between longitudinal CBF and neuropsychological changes using multivariate regression models with false discovery rate correction, focusing on executive functions. At V0, no group difference was found in prefrontal CBF between patients with PD and HCs, although patients with PD showed worse performances on executive function. At V1, patients with PD showed significantly reduced CBF in multiple prefrontal regions, including the bilateral lateral orbitofrontal, medial orbitofrontal, middle frontal, inferior frontal, superior frontal, caudal anterior cingulate, and rostral anterior cingulate. More importantly, converters showed a more significant CBF reduction in the left lateral orbitofrontal cortex than non-converters. From V0 to V1, the prolonged completion time of Trail Making Test-B (TMT-B) negatively correlated with longitudinal CBF reduction in the right caudal anterior cingulate cortex. The decreased accuracy of the Stroop Color-Word Test positively correlated with longitudinal CBF reduction in the left medial orbitofrontal cortex. In addition, at V1, the completion time of TMT-B negatively correlated with CBF in the left caudal anterior cingulate cortex. Our findings suggest that longitudinal CBF reduction in the prefrontal cortex might impact cognitive functions (especially executive functions) at the early stages of PD.

Predictors of rapid eye movement sleep behavior disorder in patients with Parkinson’s disease based on random forest and decision tree

Background and objectives

Sleep disorders related to Parkinson’s disease (PD) have recently attracted increasing attention, but there are few clinical reports on the correlation of Parkinson’s disease patients with rapid eye movement (REM) sleep behavior disorder (RBD). Therefore, this study conducted a cognitive function examination for Parkinson’s disease patients and discussed the application effect of three algorithms in the screening of influencing factors and risk prediction effects.

Methods

Three algorithms (logistic regression, machine learning-based regression trees and random forest) were used to establish a prediction model for PD-RBD patients, and the application effects of the three algorithms in the screening of influencing factors and the risk prediction of PD-RBD were discussed.

Results

The subjects included 169 patients with Parkinson’s disease (Parkinson’s disease with RBD [PD-RBD] = 69 subjects; Parkinson’s disease without RBD [PD-nRBD] = 100 subjects). This study compared the predictive performance of RF, decision tree and logistic regression, selected a final model with the best model performance and proposed the importance of variables in the final model. After the analysis, the accuracy of RF (83.05%) was better than that of the other models (decision tree = 75.10%, logistic regression = 71.62%). PQSI, Scopa-AUT score, MoCA score, MMSE score, AGE, LEDD, PD-course, UPDRS total score, ESS score, NMSQ, disease type, RLSRS, HAMD, UPDRS III and PDOnsetage are the main variables for predicting RBD, along with increased weight. Among them, PQSI is the most important factor. The prediction model of Parkinson’s disease RBD that was established in this study will help in screening out predictive factors and in providing a reference for the prognosis and preventive treatment of PD-RBD patients.

Conclusions

The random forest model had good performance in the prediction and evaluation of PD-RBD influencing factors and was superior to decision tree and traditional logistic regression models in many aspects, which can provide a reference for the prognosis and preventive treatment of PD-RBD patients.

Detection of child depression using machine learning methods

Background

Mental health problems, such as depression in children have far-reaching negative effects on child, family and society as whole. It is necessary to identify the reasons that contribute to this mental illness. Detecting the appropriate signs to anticipate mental illness as depression in children and adolescents is vital in making an early and accurate diagnosis to avoid severe consequences in the future. There has been no research employing machine learning (ML) approaches for depression detection among children and adolescents aged 4–17 years in a precisely constructed high prediction dataset, such as Young Minds Matter (YMM). As a result, our objective is to 1) create a model that can predict depression in children and adolescents aged 4–17 years old, 2) evaluate the results of ML algorithms to determine which one outperforms the others and 3) associate with the related issues of family activities and socioeconomic difficulties that contribute to depression.

Methods

The YMM, the second Australian Child and Adolescent Survey of Mental Health and Wellbeing 2013–14 has been used as data source in this research. The variables of yes/no value of low correlation with the target variable (depression status) have been eliminated. The Boruta algorithm has been utilized in association with a Random Forest (RF) classifier to extract the most important features for depression detection among the high correlated variables with target variable. The Tree-based Pipeline Optimization Tool (TPOTclassifier) has been used to choose suitable supervised learning models. In the depression detection step, RF, XGBoost (XGB), Decision Tree (DT), and Gaussian Naive Bayes (GaussianNB) have been used.

Results

Unhappy, nothing fun, irritable mood, diminished interest, weight loss/gain, insomnia or hypersomnia, psychomotor agitation or retardation, fatigue, thinking or concentration problems or indecisiveness, suicide attempt or plan, presence of any of these five symptoms have been identified as 11 important features to detect depression among children and adolescents. Although model performance varied somewhat, RF outperformed all other algorithms in predicting depressed classes by 99% with 95% accuracy rate and 99% precision rate in 315 milliseconds (ms).

Conclusion

This RF-based prediction model is more accurate and informative in predicting child and adolescent depression that outperforms in all four confusion matrix performance measures as well as execution duration.

Data-Driven Prediction of Fatigue in Parkinson's Disease Patients

Introduction: Numerous non-motor symptoms are associated with Parkinson's disease (PD) including fatigue. The challenge in the clinic is to detect relevant non-motor symptoms while keeping patient-burden of questionnaires low and to take potential subgroups such as sex differences into account. The Fatigue Severity Scale (FSS) effectively detects clinically significant fatigue in PD patients. Machine learning techniques can determine which FSS items best predict clinically significant fatigue yet the choice of technique is crucial as it determines the stability of results. Methods: 182 records of PD patients were analyzed with two machine learning algorithms: random forest (RF) and Boruta. RF and Boruta calculated feature importance scores, which measured how much impact an FSS item had in predicting clinically significant fatigue. Items with the highest feature importance scores were the best predictors. Principal components analysis (PCA) grouped highly related FSS items together. Results: RF, Boruta and PCA demonstrated that items 8 ("Fatigue is among my three most disabling symptoms") and 9 ("Fatigue interferes with my work, family or social life") were the most important predictors. Item 5 ("Fatigue causes frequent problems for me") was an important predictor for females, and item 6 ("My fatigue prevents sustained physical functioning") was important for males. Feature importance scores' standard deviations were large for RF (14-66%) but small for Boruta (0-5%). Conclusion: The clinically most informative questions may be how disabling fatigue is compared to other symptoms and interference with work, family and friends. There may be some sex-related differences with frequency of fatigue-related complaints in females and endurance-related complaints in males yielding significant information. Boruta but not RF yielded stable results and might be a better tool to determine the most relevant components of abbreviated questionnaires. Further research in this area would be beneficial in order to replicate these findings with other machine learning algorithms, and using a more representative sample of PD patients.

Comparing Ensemble-Based Machine Learning Classifiers Developed for Distinguishing Hypokinetic Dysarthria from Presbyphonia

It is essential to understand the voice characteristics in the normal aging process to accurately distinguish presbyphonia from neurological voice disorders. This study developed the best ensemble-based machine learning classifier that could distinguish hypokinetic dysarthria from presbyphonia using classification and regression tree (CART), random forest, gradient boosting algorithm (GBM), and XGBoost and compared the prediction performance of models. The subjects of this study were 76 elderly patients diagnosed with hypokinetic dysarthria and 174 patients with presbyopia. This study developed prediction models for distinguishing hypokinetic dysarthria from presbyphonia by using CART, GBM, XGBoost, and random forest and compared the accuracy, sensitivity, and specificity of the development models to identify the prediction performance of them. The results of this study showed that random forest had the best prediction performance when it was tested with the test dataset (accuracy = 0.83, sensitivity = 0.90, and specificity = 0.80, and area under the curve (AUC) = 0.85). The main predictors for detecting hypokinetic dysarthria were Cepstral peak prominence (CPP), jitter, shimmer, L/H ratio, L/H ratio_SD, CPP max (dB), CPP min (dB), and CPPF0 in the order of magnitude. Among them, CPP was the most important predictor for identifying hypokinetic dysarthria.

Patient-specific IMRT QA verification using machine learning and gamma radiomics

Gamma function is the standard methodology for comparing dose distributions. It is calculated in dedicated software, and its results verification is not performed. Thus we developed an automatic tool for patient-specific QA results verification through high accuracy machine learning (ML) models based on the radiomics characteristics extraction from gamma images. We used 158 patient-specific QA tests and extracted 105 radiomics features from each gamma image. Three random forest models were developed (ML I, ML II, and ML III). ML I and ML II verified the gamma image approval using criteria of 2%/2mm/15% threshold and 3%/3mm/15% threshold, respectively. ML III verified if the gamma analyzes software recommended protocol was followed to detect if the TPS grid modification step was done. The models were based on the most important features selected using the mean decreased impurity, and their performances were evaluated. ML I included 25 features. Its accuracy was 0.85 using the test set and 0.84 using dataset B. ML II included 10 features, and its accuracy with the test set was 0.98; the same value was achieved using the never seen data (dataset B). The First-order 10th percentile feature was identified as a feature strongly related to the approved classification. ML III selected 23 features with an accuracy of 0.99 for test set and 0.98 for dataset B. An automatic workflow example for gamma analyses QA results verification could be proposed combining the models to detect grid inconsistencies on software evaluation, followed by the test approval classification.

Best early-onset Parkinson dementia predictor using ensemble learning among Parkinson's symptoms, rapid eye movement sleep disorder, and neuropsychological profile

BACKGROUND

Despite the frequent progression from Parkinson’s disease (PD) to Parkinson’s disease dementia (PDD), the basis to diagnose early-onset Parkinson dementia (EOPD) in the early stage is still insufficient.

AIM

To explore the prediction accuracy of sociodemographic factors, Parkinson's motor symptoms, Parkinson’s non-motor symptoms, and rapid eye movement sleep disorder for diagnosing EOPD using PD multicenter registry data.

METHODS

This study analyzed 342 Parkinson patients (66 EOPD patients and 276 PD patients with normal cognition), younger than 65 years. An EOPD prediction model was developed using a random forest algorithm and the accuracy of the developed model was compared with the naive Bayesian model and discriminant analysis.

RESULTS

The overall accuracy of the random forest was 89.5%, and was higher than that of discriminant analysis (78.3%) and that of the naive Bayesian model (85.8%). In the random forest model, the Korean Mini Mental State Examination (K-MMSE) score, Korean Montreal Cognitive Assessment (K-MoCA), sum of boxes in Clinical Dementia Rating (CDR), global score of CDR, motor score of Untitled Parkinson’s Disease Rating (UPDRS), and Korean Instrumental Activities of Daily Living (K-IADL) score were confirmed as the major variables with high weight for EOPD prediction. Among them, the K-MMSE score was the most important factor in the final model.

CONCLUSION

It was found that Parkinson-related motor symptoms (e.g., motor score of UPDRS) and instrumental daily performance (e.g., K-IADL score) in addition to cognitive screening indicators (e.g., K-MMSE score and K-MoCA score) were predictors with high accuracy in EOPD prediction.

Exploring the Predictors of Rapid Eye Movement Sleep Behavior Disorder for Parkinson's Disease Patients Using Classifier Ensemble

The rapid eye movement sleep behavior disorder (RBD) of Parkinson's disease (PD) patients can be improved with medications such as donepezil as long as it is diagnosed with a thorough medical examination, since identifying a high-risk group of RBD is a critical issue to treat PD. This study develops a model for predicting the high-risk groups of RBD using random forest (RF) and provides baseline information for selecting subjects for polysomnography. Subjects consisted of 350 PD patients (Parkinson's disease with normal cognition (PD-NC) = 48; Parkinson's disease with mild cognitive impairment (PD-MCI) = 199; Parkinson's disease dementia (PDD) = 103) aged 60 years and older. This study compares the prediction performance of RF, discriminant analysis, classification and regression tree (CART), radial basis function (RBF) neural network, and logistic regression model to select a final model with the best model performance and presents the variable importance of the final model's variable. As a result of analysis, the sensitivity of RF (79%) was superior to other models (discriminant analysis = 14%, CART = 32%, RBF neural network = 25%, and logistic regression = 51%). It was confirmed that age, the motor score of Untitled Parkinson's Disease Rating (UPDRS), the total score of UPDRS, the age when a subject was diagnosed with PD first time, the Korean Mini Mental State Examination, and Korean Instrumental Activities of Daily Living, were major variables with high weight for predicting RBD. Among them, age was the most important factor. The model for predicting Parkinson's disease RBD developed in this study will contribute to the screening of patients who should receive a video-polysomnography.

Application of Machine Learning Technique to Distinguish Parkinson's Disease Dementia and Alzheimer's Dementia: Predictive Power of Parkinson's Disease-Related Non-Motor Symptoms and Neuropsychological Profile

In order to develop a predictive model that can distinguish Parkinson’s disease dementia (PDD) from other dementia types, such as Alzheimer’s dementia (AD), it is necessary to evaluate and identify the predictive accuracy of the cognitive profile while considering the non-motor symptoms, such as depression and rapid eye movement (REM) sleep behavior disorders. This study compared Parkinson’s disease (PD)’s non-motor symptoms and the diagnostic predictive power of cognitive profiles that distinguish AD and PD using machine learning. This study analyzed 118 patients with AD and 110 patients with PDD, and all subjects were 60 years or older. In order to develop the PDD prediction model, the dataset was divided into training data (70%) and test data (30%). The prediction accuracy of the model was calculated by the recognition rate. The results of this study show that Parkinson-related non-motor symptoms, such as REM sleep behavior disorders, and cognitive screening tests, such as Korean version of Montreal Cognitive Assessment, were highly accurate factors for predicting PDD. It is required to develop customized screening tests that can detect PDD in the early stage based on these results. Furthermore, it is believed that including biomarkers such as brain images or cerebrospinal fluid as input variables will be more useful for developing PDD prediction models in the future.