Mining imaging and clinical data with machine learning approaches for the diagnosis and early detection of Parkinson's disease

Machine Learning Models for Parkinson Disease: Systematic Review

Background

With the increasing availability of data, computing resources, and easier-to-use software libraries, machine learning (ML) is increasingly used in disease detection and prediction, including for Parkinson disease (PD). Despite the large number of studies published every year, very few ML systems have been adopted for real-world use. In particular, a lack of external validity may result in poor performance of these systems in clinical practice. Additional methodological issues in ML design and reporting can also hinder clinical adoption, even for applications that would benefit from such data-driven systems.

Objective

To sample the current ML practices in PD applications, we conducted a systematic review of studies published in 2020 and 2021 that used ML models to diagnose PD or track PD progression.

Methods

We conducted a systematic literature review in accordance with PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines in PubMed between January 2020 and April 2021, using the following exact string: "Parkinson's" AND ("ML" OR "prediction" OR "classification" OR "detection" or "artificial intelligence" OR "AI"). The search resulted in 1085 publications. After a search query and review, we found 113 publications that used ML for the classification or regression-based prediction of PD or PD-related symptoms.

Results

Only 65.5% (74/113) of studies used a holdout test set to avoid potentially inflated accuracies, and approximately half (25/46, 54%) of the studies without a holdout test set did not state this as a potential concern. Surprisingly, 38.9% (44/113) of studies did not report on how or if models were tuned, and an additional 27.4% (31/113) used ad hoc model tuning, which is generally frowned upon in ML model optimization. Only 15% (17/113) of studies performed direct comparisons of results with other models, severely limiting the interpretation of results.

Conclusions

This review highlights the notable limitations of current ML systems and techniques that may contribute to a gap between reported performance in research and the real-life applicability of ML models aiming to detect and predict diseases such as PD.

Detecting Parkinson's disease from shoe-mounted accelerometer sensors using convolutional neural networks optimized with modified metaheuristics

Neurodegenerative conditions significantly impact patient quality of life. Many conditions do not have a cure, but with appropriate and timely treatment the advance of the disease could be diminished. However, many patients only seek a diagnosis once the condition progresses to a point at which the quality of life is significantly impacted. Effective non-invasive and readily accessible methods for early diagnosis can considerably enhance the quality of life of patients affected by neurodegenerative conditions. This work explores the potential of convolutional neural networks (CNNs) for patient gain freezing associated with Parkinson's disease. Sensor data collected from wearable gyroscopes located at the sole of the patient's shoe record walking patterns. These patterns are further analyzed using convolutional networks to accurately detect abnormal walking patterns. The suggested method is assessed on a public real-world dataset collected from parents affected by Parkinson's as well as individuals from a control group. To improve the accuracy of the classification, an altered variant of the recent crayfish optimization algorithm is introduced and compared to contemporary optimization metaheuristics. Our findings reveal that the modified algorithm (MSCHO) significantly outperforms other methods in accuracy, demonstrated by low error rates and high Cohen's Kappa, precision, sensitivity, and F1-measures across three datasets. These results suggest the potential of CNNs, combined with advanced optimization techniques, for early, non-invasive diagnosis of neurodegenerative conditions, offering a path to improve patient quality of life.

Exploiting macro- and micro-structural brain changes for improved Parkinson's disease classification from MRI data

Parkinson's disease (PD) is the second most common neurodegenerative disease. Accurate PD diagnosis is crucial for effective treatment and prognosis but can be challenging, especially at early disease stages. This study aimed to develop and evaluate an explainable deep learning model for PD classification from multimodal neuroimaging data. The model was trained using one of the largest collections of T1-weighted and diffusion-tensor magnetic resonance imaging (MRI) datasets. A total of 1264 datasets from eight different studies were collected, including 611 PD patients and 653 healthy controls (HC). These datasets were pre-processed and non-linearly registered to the MNI PD25 atlas. Six imaging maps describing the macro- and micro-structural integrity of brain tissues complemented with age and sex parameters were used to train a convolutional neural network (CNN) to classify PD/HC subjects. Explainability of the model's decision-making was achieved using SmoothGrad saliency maps, highlighting important brain regions. The CNN was trained using a 75%/10%/15% train/validation/test split stratified by diagnosis, sex, age, and study, achieving a ROC-AUC of 0.89, accuracy of 80.8%, specificity of 82.4%, and sensitivity of 79.1% on the test set. Saliency maps revealed that diffusion tensor imaging data, especially fractional anisotropy, was more important for the classification than T1-weighted data, highlighting subcortical regions such as the brainstem, thalamus, amygdala, hippocampus, and cortical areas. The proposed model, trained on a large multimodal MRI database, can classify PD patients and HC subjects with high accuracy and clinically reasonable explanations, suggesting that micro-structural brain changes play an essential role in the disease course.

Applications of Machine Learning to Diagnosis of Parkinson's Disease

BACKGROUND

Accurate diagnosis of Parkinson's disease (PD) is challenging due to its diverse manifestations. Machine learning (ML) algorithms can improve diagnostic precision, but their generalizability across medical centers in China is underexplored.

OBJECTIVE

To assess the accuracy of an ML algorithm for PD diagnosis, trained and tested on data from different medical centers in China.

METHODS

A total of 1656 participants were included, with 1028 from Beijing (training set) and 628 from Fuzhou (external validation set). Models were trained using the least absolute shrinkage and selection operator-logistic regression (LASSO-LR), decision tree (DT), random forest (RF), eXtreme gradient boosting (XGboost), support vector machine (SVM), and k-nearest neighbor (KNN) techniques. Hyperparameters were optimized using five-fold cross-validation and grid search techniques. Model performance was evaluated using the area under the curve (AUC) of the receiver operating characteristic (ROC) curve, accuracy, sensitivity (recall), specificity, precision, and F1 score. Variable importance was assessed for all models.

RESULTS

SVM demonstrated the best differentiation between healthy controls (HCs) and PD patients (AUC: 0.928, 95% CI: 0.908-0.947; accuracy: 0.844, 95% CI: 0.814-0.871; sensitivity: 0.826, 95% CI: 0.786-0.866; specificity: 0.861, 95% CI: 0.820-0.898; precision: 0.849, 95% CI: 0.807-0.891; F1 score: 0.837, 95% CI: 0.803-0.868) in the validation set. Constipation, olfactory decline, and daytime somnolence significantly influenced predictability.

CONCLUSION

We identified multiple pivotal variables and SVM as a precise and clinician-friendly ML algorithm for prediction of PD in Chinese patients.

The differential diagnosis value of radiomics-based machine learning in Parkinson's disease: a systematic review and meta-analysis

Background

In recent years, radiomics has been increasingly utilized for the differential diagnosis of Parkinson's disease (PD). However, the application of radiomics in PD diagnosis still lacks sufficient evidence-based support. To address this gap, we carried out a systematic review and meta-analysis to evaluate the diagnostic value of radiomics-based machine learning (ML) for PD.

Methods

We systematically searched Embase, Cochrane, PubMed, and Web of Science databases as of November 14, 2022. The radiomics quality assessment scale (RQS) was used to evaluate the quality of the included studies. The outcome measures were the c-index, which reflects the overall accuracy of the model, as well as sensitivity and specificity. During this meta-analysis, we discussed the differential diagnostic value of radiomics-based ML for Parkinson's disease and various atypical parkinsonism syndromes (APS).

Results

Twenty-eight articles with a total of 6,057 participants were included. The mean RQS score for all included articles was 10.64, with a relative score of 29.56%. The pooled c-index, sensitivity, and specificity of radiomics for predicting PD were 0.862 (95% CI: 0.833-0.891), 0.91 (95% CI: 0.86-0.94), and 0.93 (95% CI: 0.87-0.96) in the training set, and 0.871 (95% CI: 0.853-0.890), 0.86 (95% CI: 0.81-0.89), and 0.87 (95% CI: 0.83-0.91) in the validation set, respectively. Additionally, the pooled c-index, sensitivity, and specificity of radiomics for differentiating PD from APS were 0.866 (95% CI: 0.843-0.889), 0.86 (95% CI: 0.84-0.88), and 0.80 (95% CI: 0.75-0.84) in the training set, and 0.879 (95% CI: 0.854-0.903), 0.87 (95% CI: 0.85-0.89), and 0.82 (95% CI: 0.77-0.86) in the validation set, respectively.

Conclusion

Radiomics-based ML can serve as a potential tool for PD diagnosis. Moreover, it has an excellent performance in distinguishing Parkinson's disease from APS. The support vector machine (SVM) model exhibits excellent robustness when the number of samples is relatively abundant. However, due to the diverse implementation process of radiomics, it is expected that more large-scale, multi-class image data can be included to develop radiomics intelligent tools with broader applicability, promoting the application and development of radiomics in the diagnosis and prediction of Parkinson's disease and related fields.

Systematic review registration

https://www.crd.york.ac.uk/PROSPERO/display_record.php?RecordID=383197, identifier ID: CRD42022383197.

Diagnosis and classification of Parkinson's disease using ensemble learning and 1D-PDCovNN

In this paper, we proposed a novel approach to diagnose and classify Parkinson's Disease (PD) using ensemble learning and 1D-PDCovNN, a novel deep learning technique. PD is a neurodegenerative disorder; early detection and correct classification are essential for better disease management. The primary aim of this study is to develop a robust approach to diagnosing and classifying PD using EEG signals. As the dataset, we have used the San Diego Resting State EEG dataset to evaluate our proposed method. The proposed method mainly consists of three stages. In the first stage, the Independent Component Analysis (ICA) method has been used as the pre-processing method to filter out the blink noises from the EEG signals. Also, the effect of the band showing motor cortex activity in the 7-30 Hz frequency band of EEG signals in diagnosing and classifying Parkinson's disease from EEG signals has been investigated. In the second stage, the Common Spatial Pattern (CSP) method has been used as the feature extraction to extract useful information from EEG signals. Finally, an ensemble learning approach, Dynamic Classifier Selection (DCS) in Modified Local Accuracy (MLA), has been employed in the third stage, consisting of seven different classifiers. As the classifier method, DCS in MLA, XGBoost, and 1D-PDCovNN classifier has been used to classify the EEG signals as the PD and healthy control (HC). We first used dynamic classifier selection to diagnose and classify Parkinson's disease (PD) from EEG signals, and promising results have been obtained. The performance of the proposed approach has been evaluated using the classification accuracy, F-1 score, kappa score, Jaccard score, ROC curve, recall, and precision values in the classification of PD with the proposed models. In the classification of PD, the combination of DCS in MLA achieved an accuracy of 99,31%. The results of this study demonstrate that the proposed approach can be used as a reliable tool for early diagnosis and classification of PD.

The application of risk models based on machine learning to predict endometriosis-associated ovarian cancer in patients with endometriosis

INTRODUCTION

There is currently no satisfactory model for predicting malignant transformation of endometriosis. The aim of this study was to construct and evaluate a risk model incorporating noninvasive clinical parameters to predict endometriosis-associated ovarian cancer (EAOC) in patients with endometriosis.

MATERIAL AND METHODS

We enrolled 6809 patients with endometriosis confirmed by pathology, and randomly allocated them to training (n = 4766) and testing cohorts (n = 2043). The proportion of patients with EAOC in each cohort was similar. We extracted a total of 94 demographic and clinicopathologic features from the medical records using natural language processing. We used a machine learning method - gradient-boosting decision tree - to construct a predictive model for EAOC and to evaluate the accuracy of the model. We also constructed a multivariate logistic regression model inclusive of the EAOC-associated risk factors using a back stepwise procedure. Then we compared the performance of the two risk-predicting models using DeLong's test.

RESULTS

The occurrence of EAOC was 1.84% in this study. The logistic regression model comprised 10 selected features and demonstrated good discrimination in the testing cohort, with an area under the curve (AUC) of 0.891 (95% confidence interval [CI] 0.821-0.960), sensitivity of 88.9%, and specificity of 76.7%. The risk model based on machine learning had an AUC of 0.942 (95% CI 0.914-0.969), sensitivity of 86.8%, and specificity of 86.7%. The machine learning-based risk model performed better than the logistic regression model in DeLong's test (p = 0.036). Furthermore, in a prospective dataset, the machine learning-based risk model had an AUC of 0.8758, a sensitivity of 94.4%, and a specificity of 73.8%.

CONCLUSIONS

The machine learning-based risk model was constructed to predict EAOC and had high sensitivity and specificity. This model could be of considerable use in helping reduce medical costs and designing follow-up schedules.

The emerging role of furin in neurodegenerative and neuropsychiatric diseases

Furin is an important mammalian proprotein convertase that catalyzes the proteolytic maturation of a variety of prohormones and proproteins in the secretory pathway. In the brain, the substrates of furin include the proproteins of growth factors, receptors and enzymes. Emerging evidence, such as reduced FURIN mRNA expression in the brains of Alzheimer's disease patients or schizophrenia patients, has implicated a crucial role of furin in the pathophysiology of neurodegenerative and neuropsychiatric diseases. Currently, compared to cancer and infectious diseases, the aberrant expression of furin and its pharmaceutical potentials in neurological diseases remain poorly understood. In this article, we provide an overview on the physiological roles of furin and its substrates in the brain, summarize the deregulation of furin expression and its effects in neurodegenerative and neuropsychiatric disorders, and discuss the implications and current approaches that target furin for therapeutic interventions. This review may expedite future studies to clarify the molecular mechanisms of furin deregulation and involvement in the pathogenesis of neurodegenerative and neuropsychiatric diseases, and to develop new diagnosis and treatment strategies for these diseases.

Characterization of Early Stage Parkinson's Disease From Resting-State fMRI Data Using a Long Short-Term Memory Network

Parkinson's disease (PD) is a common and complex neurodegenerative disorder with five stages on the Hoehn and Yahr scaling. Characterizing brain function alterations with progression of early stage disease would support accurate disease staging, development of new therapies, and objective monitoring of disease progression or treatment response. Functional magnetic resonance imaging (fMRI) is a promising tool in revealing functional connectivity (FC) differences and developing biomarkers in PD. While fMRI and FC data have been utilized for diagnosis of PD through application of machine learning approaches such as support vector machine and logistic regression, the characterization of FC changes in early-stage PD has not been investigated. Given the complexity and non-linearity of fMRI data, we propose the use of a long short-term memory (LSTM) network to distinguish the early stages of PD and understand related functional brain changes. The study included 84 subjects (56 in stage 2 and 28 in stage 1) from the Parkinson's Progression Markers Initiative (PPMI), the largest-available public PD dataset. Under a repeated 10-fold stratified cross-validation, the LSTM model reached an accuracy of 71.63%, 13.52% higher than the best traditional machine learning method and 11.56% higher than a CNN model, indicating significantly better robustness and accuracy compared with other machine learning classifiers. Finally, we used the learned LSTM model weights to select the top brain regions that contributed to model prediction and performed FC analyses to characterize functional changes with disease stage and motor impairment to gain better insight into the brain mechanisms of PD.

Can Dopamine Responsiveness Be Predicted in Parkinson's Disease Without an Acute Administration Test?

BACKGROUND

Dopamine responsiveness (dopa-sensitivity) is an important parameter in the management of patients with Parkinson's disease (PD). For quantification of this parameter, patients undergo a challenge test with acute Levodopa administration after drug withdrawal, which may lead to patient discomfort and use of significant resources.

OBJECTIVE

Our objective was to develop a predictive model combining clinical scores and imaging.

METHODS

350 patients, recruited by 13 specialist French centers and considered for deep brain stimulation, underwent an acute L-dopa challenge (dopa-sensitivity > 30%), full assessment, and MRI investigations, including T1w and R2* images. Data were randomly divided into a learning base from 10 centers and data from the remaining centers for testing. A machine selection approach was applied to choose the optimal variables and these were then used in regression modeling. Complexity of the modelling was incremental, while the first model considered only clinical variables, the subsequent included imaging features. The performances were evaluated by comparing the estimated values and actual valuesResults:Whatever the model, the variables age, sex, disease duration, and motor scores were selected as contributors. The first model used them and the coefficients of determination (R2) was 0.60 for the testing set and 0.69 in the learning set (p < 0.001). The models that added imaging features enhanced the performances: with T1w (R2 = 0.65 and 0.76, p < 0.001) and with R2* (R2 = 0.60 and 0.72, p < 0.001).

CONCLUSION

These results suggest that modeling is potentially a simple way to estimate dopa-sensitivity, but requires confirmation in a larger population, including patients with dopa-sensitivity < 30.