Predicting dementia development in Parkinson's disease using Bayesian network classifiers

Machine learning for the detection and diagnosis of cognitive impairment in Parkinson's Disease: A systematic review

BACKGROUND

Parkinson's Disease is the second most common neurological disease in over 60s. Cognitive impairment is a major clinical symptom, with risk of severe dysfunction up to 20 years post-diagnosis. Processes for detection and diagnosis of cognitive impairments are not sufficient to predict decline at an early stage for significant impact. Ageing populations, neurologist shortages and subjective interpretations reduce the effectiveness of decisions and diagnoses. Researchers are now utilising machine learning for detection and diagnosis of cognitive impairment based on symptom presentation and clinical investigation. This work aims to provide an overview of published studies applying machine learning to detecting and diagnosing cognitive impairment, evaluate the feasibility of implemented methods, their impacts, and provide suitable recommendations for methods, modalities and outcomes.

METHODS

To provide an overview of the machine learning techniques, data sources and modalities used for detection and diagnosis of cognitive impairment in Parkinson's Disease, we conducted a review of studies published on the PubMed, IEEE Xplore, Scopus and ScienceDirect databases. 70 studies were included in this review, with the most relevant information extracted from each. From each study, strategy, modalities, sources, methods and outcomes were extracted.

RESULTS

Literatures demonstrate that machine learning techniques have potential to provide considerable insight into investigation of cognitive impairment in Parkinson's Disease. Our review demonstrates the versatility of machine learning in analysing a wide range of different modalities for the detection and diagnosis of cognitive impairment in Parkinson's Disease, including imaging, EEG, speech and more, yielding notable diagnostic accuracy.

CONCLUSIONS

Machine learning based interventions have the potential to glean meaningful insight from data, and may offer non-invasive means of enhancing cognitive impairment assessment, providing clear and formidable potential for implementation of machine learning into clinical practice.

Multi-source multi-modal markers for Bayesian Networks: Application to the extremely preterm born brain

The preterm phenotype results from the interplay of multiple disorders affecting the brain and cognitive outcomes. Accurately characterising these interactions can reveal prematurity markers. Bayesian Networks (BNs) are powerful tools to disentangle these relationships, as they inherently measure associations between variables while mitigating confounding factors. We present Modified PC-HC (MPC-HC), a Bayesian Network (BN) structural learning algorithm. MPC-HC employs statistical testing and search-and-score techniques to explore equivalent classes. We employ MPC-HC to estimate BNs for extremely preterm (EP) young adults and full-term controls. Using MRI measurements and cognitive performance markers, we investigate predictive relationships and mutual influences through predictions and sensitivity analysis. We assess the confidence in the estimated BN structures using bootstrapping. Furthermore, MPC-HC's validation involves assessing its ability to recover benchmark BN structures. MPC-HC achieves an average prediction accuracy of 72.5% compared to 62.5% of PC, 64.5% of MMHC, and 71.5% of HC, while it outperforms PC, MMHC, and HC algorithms in reconstructing the true structure of benchmark BNs. The sensitivity analysis shows that MRI measurements mainly affect EP cognitive scores. Our work has two key contributions: first, the introduction and validation of a new BN structure learning method. Second, demonstrating the potential of BNs in modelling variable relationships, predicting variables of interest, modelling uncertainty, and evaluating how variables impact each other. Finally, we demonstrate this by characterising complex phenotypes, such as preterm birth, and discovering results consistent with literature findings.

Prediction of complications associated with general surgery using a Bayesian network

BACKGROUND

Numerous attempts have been made to identify risk factors for surgery complications, but few studies have identified accurate methods of predicting complex outcomes involving multiple complications.

METHODS

We performed a prospective cohort study of general surgical inpatients who attended 4 regionally representative hospitals in China from January to June 2015 and January to June 2016. The risk factors were identified using logistic regression. A Bayesian network model, consisting of directed arcs and nodes, was used to analyze the relationships between risk factors and complications. Probability ratios for complications for a given node state relative to the baseline probability were calculated to quantify the potential effects of risk factors on complications or of complications on other complications.

RESULTS

We recruited 19,223 participants and identified 21 nodes, representing 9 risk factors and 12 complications, and 55 direct relationships between these. Respiratory failure was at the center of the network, directly affected by 5 risk factors, and directly affected 7 complications. Cardiopulmonary resuscitation and sepsis or septic shock also directly affected death. The area under the receiver operating characteristic curve for the ability of the network to predict complications was >0.7. Notably, the probability of other severe complications or death significantly increased when a severe complication occurred. Most importantly, there was a 141-fold higher risk of death when cardiopulmonary resuscitation was required.

CONCLUSION

We have created a Bayesian network that displays how risk factors affect complications and their interrelationships and permits the accurate prediction of complications and the creation of appropriate preventive guidelines.

A fully automated approach involving neuroimaging and deep learning for Parkinson's disease detection and severity prediction

Three-dimensional magnetic resonance imaging has been proved to detect and predict the severity of progressive neurodegenerative disorders such as Parkinson's disease. The application of pre-processing with neuroimaging methods plays a vital role in post-processing for these problems. The development of technology over the years has enabled the use of deep learning methods such as convolutional neural networks (CNN) on magnetic resonance imaging (MRI) . In this study, the detection of Parkinson's disease and the prediction of disease severity were studied with 2D and 3D CNN using T1-weighted MRIs that were pre-processed with FLIRT image registration and BET non-brain tissue scraper. For 2D CNN, the median slices of the MR images in the sagittal, coronal, and axial planes were used separately and in combination. In addition, the whole brain for 3D CNN has been downsized. Considering the performance of the proposed methods, the highest results achieved for detecting Parkinson's disease were measured as 0.9620, 0.9452, 0.9407, and 0.9536 for Accuracy, F1 score, precision, and Recall, respectively. The highest result achieved for estimating the severity of Parkinson's disease was that 3D CNN was fed three times with a downsized whole MRI, which were measured for R, and R2 as 0.9150 and 0.8372, respectively. When the results obtained with the methods suggested within the scope of the study were examined, it was observed that the applied methods yielded promising performance.

Interpretable machine learning for dementia: A systematic review

INTRODUCTION

Machine learning research into automated dementia diagnosis is becoming increasingly popular but so far has had limited clinical impact. A key challenge is building robust and generalizable models that generate decisions that can be reliably explained. Some models are designed to be inherently "interpretable," whereas post hoc "explainability" methods can be used for other models.

METHODS

Here we sought to summarize the state-of-the-art of interpretable machine learning for dementia.

RESULTS

We identified 92 studies using PubMed, Web of Science, and Scopus. Studies demonstrate promising classification performance but vary in their validation procedures and reporting standards and rely heavily on popular data sets.

DISCUSSION

Future work should incorporate clinicians to validate explanation methods and make conclusive inferences about dementia-related disease pathology. Critically analyzing model explanations also requires an understanding of the interpretability methods itself. Patient-specific explanations are also required to demonstrate the benefit of interpretable machine learning in clinical practice.

Prediction of Cognitive Degeneration in Parkinson's Disease Patients Using a Machine Learning Method

This study developed a predictive model for cognitive degeneration in patients with Parkinson's disease (PD) using a machine learning method. The clinical data, plasma biomarkers, and neuropsychological test results of patients with PD were collected and utilized as model predictors. Machine learning methods comprising support vector machines (SVMs) and principal component analysis (PCA) were applied to obtain a cognitive classification model. Using 32 comprehensive predictive parameters, the PCA-SVM classifier reached 92.3% accuracy and 0.929 area under the receiver operating characteristic curve (AUC). Furthermore, the accuracy could be increased to 100% and the AUC to 1.0 in a PCA-SVM model using only 13 carefully chosen features.

A multivariate Bayesian classification algorithm for cerebral stage prediction by diffusion tensor imaging in amyotrophic lateral sclerosis

•

Novel DTI-based classification of ALS disease stages by a Bayesian approach is applied.

•

Bayesian classification algorithm improves threshold-based staging method.

•

Step forward in MRI-based patient stratification in ALS in vivo.

Background and Objective

Diffusion tensor imaging (DTI) can be used to tract-wise map correlates of the sequential disease progression and, therefore, to assess disease stages of amyotrophic lateral sclerosis (ALS) in vivo. According to a threshold-based sequential scheme, a classification of ALS patients into disease stages is possible, however, several patients cannot be staged for methodological reasons. This study aims to implement a multivariate Bayesian classification algorithm for disease stage prediction at an individual ALS patient level based on DTI metrics of involved tract systems to improve disease stage mapping.

Methods

The analysis of fiber tracts involved in each stage of ALS was performed in 325 ALS patients and 130 age- and gender-matched healthy controls. Based on Bayes’ theorem and in accordance with the sequential disease progression, a multistage classifier was implemented. Patients were categorized into in vivo DTI stages using the threshold-based method and the Bayesian algorithm. By the margin of confidence, the reliability of the Bayesian categorizations was accessible.

Results

Based on the Bayesian multistage classifier, 88% of all ALS patients could be assigned into an ALS stage compared to 77% using the threshold-based staging scheme. Additionally, the confidence of all classifications could be estimated.

Conclusions

By the application of the multi-stage Bayesian classifier, an individualized in vivo cerebral staging of ALS patients was possible based on the sequentially involved tract systems and, furthermore, the reliability of the respective classifications could be determined. The Bayesian classification algorithm is an improvement of the threshold-based staging method and could provide a framework for extending the DTI-based in vivo cerebral staging in ALS.

Machine Learning Models for Diagnosis of Parkinson's Disease Using Multiple Structural Magnetic Resonance Imaging Features

Purpose

This study aimed to develop machine learning models for the diagnosis of Parkinson's disease (PD) using multiple structural magnetic resonance imaging (MRI) features and validate their performance.

Methods

Brain structural MRI scans of 60 patients with PD and 56 normal controls (NCs) were enrolled as development dataset and 69 patients with PD and 71 NCs from Parkinson's Progression Markers Initiative (PPMI) dataset as independent test dataset. First, multiple structural MRI features were extracted from cerebellar, subcortical, and cortical regions of the brain. Then, the Pearson's correlation test and least absolute shrinkage and selection operator (LASSO) regression were used to select the most discriminating features. Finally, using logistic regression (LR) classifier with the 5-fold cross-validation scheme in the development dataset, the cerebellar, subcortical, cortical, and a combined model based on all features were constructed separately. The diagnostic performance and clinical net benefit of each model were evaluated with the receiver operating characteristic (ROC) analysis and the decision curve analysis (DCA) in both datasets.

Results

After feature selection, 5 cerebellar (absolute value of left lobule crus II cortical thickness (CT) and right lobule IV volume, relative value of right lobule VIIIA CT and lobule VI/VIIIA gray matter volume), 3 subcortical (asymmetry index of caudate volume, relative value of left caudate volume, and absolute value of right lateral ventricle), and 4 cortical features (local gyrification index of right anterior circular insular sulcus and anterior agranular insula complex, local fractal dimension of right middle insular area, and CT of left supplementary and cingulate eye field) were selected as the most distinguishing features. The area under the curve (AUC) values of the cerebellar, subcortical, cortical, and combined models were 0.679, 0.555, 0.767, and 0.781, respectively, for the development dataset and 0.646, 0.632, 0.690, and 0.756, respectively, for the independent test dataset, respectively. The combined model showed higher performance than the other models (Delong's test, all p-values < 0.05). All models showed good calibration, and the DCA demonstrated that the combined model has a higher net benefit than other models.

Conclusion

The combined model showed favorable diagnostic performance and clinical net benefit and had the potential to be used as a non-invasive method for the diagnosis of PD.

A Clinical-Radiomic Model for Predicting Indocyanine Green Retention Rate at 15 Min in Patients With Hepatocellular Carcinoma

Purpose:

The indocyanine green retention rate at 15 min (ICG-R15) is of great importance in the accurate assessment of hepatic functional reserve for safe hepatic resection. To assist clinicians to evaluate hepatic functional reserve in medical institutions that lack expensive equipment, we aimed to explore a novel approach to predict ICG-R15 based on CT images and clinical data in patients with hepatocellular carcinoma (HCC).

Methods

In this retrospective study, 350 eligible patients were enrolled and randomly assigned to the training cohort (245 patients) and test cohort (105 patients). Radiomics features and clinical factors were analyzed to pick out the key variables, and based on which, we developed the random forest regression, extreme gradient boosting regression (XGBR), and artificial neural network models for predicting ICG-R15, respectively. Pearson's correlation coefficient (R) was adopted to evaluate the performance of the models.

Results

We extracted 660 CT image features in total from each patient. Fourteen variables significantly associated with ICG-R15 were picked out for model development. Compared to the other two models, the XGBR achieved the best performance in predicting ICG-R15, with a mean difference of 1.59% (median, 1.53%) and an R-value of 0.90. Delong test result showed no significant difference in the area under the receiver operating characteristic (AUROCs) for predicting post hepatectomy liver failure between actual and estimated ICG-R15.

Conclusion

The proposed approach that incorporates the optimal radiomics features and clinical factors can allow for individualized prediction of ICG-R15 value of patients with HCC, regardless of the specific equipment and detection reagent (NO. ChiCTR2100053042; URL, http://www.chictr.org.cn).

Early Prediction of Parkinson’s Disease from Brain MRI Images Using Convolutional Neural Network

The early diagnosis of Parkinson’s Disease (PD) is a challenging practice for doctors. Currently, there are no separate diagnostics and tests to be done to predict onset PD. However, the PD can be predicted through repeated clinical trials and tests. Sometimes, early prediction of PD can become tedious based on trials and tests. The computer-aided prediction will help medical professionals predict PD accurately during one’s onset stages to improve the PD patients’ quality of life. Hence, early prediction of PD is essential. In this article, Convolution Neural Networks (CNN) is proposed to classify PD patients and healthy individuals. The brain MRI images are given as input for the proposed methodology. The CNN deep neural network will first extract the features from the images. Then, it will classify the PD patients and healthy individuals from the extracted features. The automatic feature extraction will improve the accuracy of the classifier and reduce human error. The brain MRI images are taken from the PPMI dataset for experimentation. The sensitivity, specificity, and accuracy are calculated to assess the performance of the proposed methodology. The loss is also calculated to verify the performance of the classifier. It is observed that the CNN classifier has produced a higher accuracy of more than 98% in classifying PD patients and healthy individuals when compared to multi-layer perceptron deep learning.

Imaging Cognitive Impairment and Impulse Control Disorders in Parkinson's Disease

Dementia and mild forms of cognitive impairment as well as neuropsychiatric symptoms (i. e., impulse control disorders) are frequent and disabling non-motor symptoms of Parkinson's disease (PD). The identification of changes in neuroimaging studies for the early diagnosis and monitoring of the cognitive and neuropsychiatric symptoms associated with Parkinson's disease, as well as their pathophysiological understanding, are critical for the development of an optimal therapeutic approach. In the current literature review, we present an update on the latest structural and functional neuroimaging findings, including high magnetic field resonance and radionuclide imaging, assessing cognitive dysfunction and impulse control disorders in PD.

A Deep Neural Network-Based Method for Prediction of Dementia Using Big Data

The rise in dementia among the aging Korean population will quickly create a financial burden on society, but timely recognition of early warning for dementia and proper responses to the occurrence of dementia can enhance medical treatment. Health behavior and medical service usage data are relatively more accessible than clinical data, and a prescreening tool with easily accessible data could be a good solution for dementia-related problems. In this paper, we apply a deep neural network (DNN) to prediction of dementia using health behavior and medical service usage data, using data from 7031 subjects aged over 65 collected from the Korea National Health and Nutrition Examination Survey (KNHANES) in 2001 and 2005. In the proposed model, principal component analysis (PCA) featuring and min/max scaling are used to preprocess and extract relevant background features. We compared our proposed methodology, a DNN/scaled PCA, with five well-known machine learning algorithms. The proposed methodology shows 85.5% of the area under the curve (AUC), a better result than that using other algorithms. The proposed early prescreening method for possible dementia can be used by both patients and doctors.

Identifying Parkinson's disease with mild cognitive impairment by using combined MR imaging and electroencephalogram

OBJECTIVES

To analyse the changes of quantitative electroencephalogram (qEEG) and cortex structural magnetic resonance (MR) imaging in Parkinson's disease with mild cognitive impairment (PD-MCI) and to explore the "composite marker"-based machine learning model in identifying PD-MCI.

METHODS

Retrospective analysis of patients with PD identified 36 PD-MCI and 35 PD with normal cognition (PD-NC). QEEG features of power spectrum and structural MR features of cortex based on surface-based morphometry (SBM) were extracted. Support vector machine (SVM) was established using combined features of structural MR and qEEG to identify PD-MCI. Feature importance evaluation algorithm of mean impact value (MIV) was established to sort the vital characteristics of qEEG and structural MR.

RESULTS

Compared with PD-NC, PD-MCI showed a statistically significant difference in 5 leads and waves of qEEG and 7 cortical region features of structural MR. The SVM model based on these qEEG and structural MR features yielded an accuracy of 0.80 in the training set and had a high prediction accuracy of 0.80 in the test set (sensitivity was 0.78, specificity was 0.83, area under the receiver operating characteristic curve was 0.77), which was higher than the model built by the feature separately. QEEG features of theta wave in C3 had a marked impact on the model for classification according to the MIV algorithm.

CONCLUSIONS

PD-MCI is characterized by widespread structural and EEG abnormality. "Composite markers" could be valuable for the individualized diagnosis of PD-MCI by machine learning.

KEY POINTS

• Explore the brain abnormalities in Parkinson's disease with mild cognitive impairment by using the quantitative electroencephalogram and cortex structural MR simultaneously. • Multimodal features based support vector machine for identifying Parkinson's disease with mild cognitive impairment has an acceptable performance. • Theta wave in C3 is the most influential feature of qEEG and cortex structure MR imaging in identifying Parkinson's disease with mild cognitive impairment using support vector machine.

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.

An SBM-based machine learning model for identifying mild cognitive impairment in patients with Parkinson's disease

OBJECTIVE

To identify Parkinson's disease with mild cognitive impairment (PD-MCI) through surface-based morphometry (SBM) based machine learning model.

METHODS

93 patients with parkinson's disease (35 PD with normal cognition, 58 PD-MCI) were examined, obtaining 276 SBM variables per subject. 20 healthy control subjects were used as the reference. After extracting features with statistically significance, support vector machine (SVM) model with grid search method was applied to identify patients with PD-MCI. Accuracy, matthews correlation coefficient (MCC), receiver operating characteristic curve (ROC), precision-recall curve (PR), AUC-ROC, AUC-PR and leave-one-out cross validation (LOOCV) strategy were employed for model evaluation.

RESULTS

PD-MCI is characterized by widespread structural abnormality. SVM model with SBM features achieved an accuracy of 80.00% and area under the ROC of 0.86 for identifying PD-MCI. MCC, AUC-PR, and LOOCV classification accuracy were 0.56, 0.89, and 78.08%, respectively.

CONCLUSION

Automatic identification of PD-MCI could be realized by SBM-based machine learning model.

Prediction of mild parkinsonism revealed by neural oscillatory changes and machine learning

Neural oscillatory changes within and across different frequency bands are thought to underlie motor dysfunction in Parkinson's disease (PD) and may serve as biomarkers for closed-loop deep brain stimulation (DBS) approaches. Here, we used neural oscillatory signals derived from chronically implanted cortical and subcortical electrode arrays as features to train machine learning algorithms to discriminate between naive and mild PD states in a nonhuman primate model. Local field potential (LFP) data were collected over several months from a 12-channel subdural electrocorticography (ECoG) grid and a 6-channel custom array implanted in the subthalamic nucleus (STN). Relative to the naive state, the PD state showed elevated primary motor cortex (M1) and STN power in the beta, high gamma, and high-frequency oscillation (HFO) bands and decreased power in the delta band. Theta power was found to be decreased in STN but not M1. In the PD state there was elevated beta-HFO phase-amplitude coupling (PAC) in the STN. We applied machine learning with support vector machines with radial basis function (SVM-RBF) kernel and k-nearest neighbors (KNN) classifiers trained by features related to power and PAC changes to discriminate between the naive and mild states. Our results show that the most predictive feature of parkinsonism in the STN was high beta (∼86% accuracy), whereas it was HFO in M1 (∼98% accuracy). A feature fusion approach outperformed every individual feature, particularly in the M1, where ∼98% accuracy was achieved with both classifiers. Overall, our data demonstrate the ability to use various frequency band power to classify the clinical state and are also beneficial in developing closed-loop DBS therapeutic approaches.NEW & NOTEWORTHY Neurophysiological biomarkers that correlate with motor symptoms or disease severity are vital to improve our understanding of the pathophysiology in Parkinson's disease (PD) and for the development of more effective treatments, including deep brain stimulation (DBS). This work provides direct insight into the application of these biomarkers in training classifiers to discriminate between brain states, which is a first step toward developing closed-loop DBS systems.

Classification model based on strain measurements to identify patients with arrhythmogenic cardiomyopathy with left ventricular involvement

BACKGROUND AND OBJECTIVE

A heterogenous expression characterizes arrhythmogenic cardiomyopathy (AC). The evaluation of regional wall movement included in the current Task Force Criteria is only qualitative and restricted to the right ventricle. However, a strain-based approach could precisely quantify myocardial deformation in both ventricles. We aim to define and modelize the strain behavior of the left ventricle in AC patients with left ventricular (LV) involvement by applying algorithms such as Principal Component Analysis (PCA), clustering and naïve Bayes (NB) classifiers.

METHODS

Thirty-six AC patients with LV involvement and twenty-three non-affected family members (controls) were enrolled. Feature-tracking analysis was applied to cine cardiac magnetic resonance imaging to assess strain time series from a 3D approach, to which PCA was applied. A Two-Step clustering algorithm separated the patients' group into clusters according to their level of LV strain impairment. A statistical characterization between controls and the new AC subgroups was done. Finally, a NB classifier was built and new data from a small evolutive dataset was predicted.

RESULTS

60% of AC-LV patients showed mildly affected strain and 40% severely affected strain. Both groups and controls exhibited statistically significant differences, especially when comparing controls and severely affected AC-LV patients. The classification accuracy of the strain NB classifier reached 82.76%. The model performance was as good as to classify the individuals with a 100% sensitivity and specificity for severely impaired strain patients, 85.7% and 81.1% for mildly impaired strain patients, and 69.9% and 91.4% for normal strain, respectively. Even when the severely affected LV-AC group was excluded, LV strain showed a good accuracy to differentiate patients and controls. The prediction of the evolutive dataset revealed a progressive alteration of strain in time.

CONCLUSIONS

Our LV strain classification model may help to identify AC patients with LV involvement, at least in a setting of a high pretest probability, such as family screening.

Neuroimaging in Parkinson's disease dementia: connecting the dots

Dementia is a common and devastating symptom of Parkinson's disease but the anatomical substrate remains unclear. Some evidence points towards hippocampal involvement but neuroimaging abnormalities have been reported throughout the brain and are largely inconsistent across studies. Here, we test whether these disparate neuroimaging findings for Parkinson's disease dementia localize to a common brain network. We used a literature search to identify studies reporting neuroimaging correlates of Parkinson's dementia (11 studies, 385 patients). We restricted our search to studies of brain atrophy and hypometabolism that compared Parkinson's patients with dementia to those without cognitive involvement. We used a standard coordinate-based activation likelihood estimation meta-analysis to assess for consistency in the neuroimaging findings. We then used a new approach, coordinate-based network mapping, to test whether neuroimaging findings localized to a common brain network. This approach uses resting-state functional connectivity from a large cohort of normative subjects (n = 1000) to identify the network of regions connected to a reported neuroimaging coordinate. Activation likelihood estimation meta-analysis failed to identify any brain regions consistently associated with Parkinson's dementia, showing major heterogeneity across studies. In contrast, coordinate-based network mapping found that these heterogeneous neuroimaging findings localized to a specific brain network centred on the hippocampus. Next, we tested whether this network showed symptom specificity and stage specificity by performing two further analyses. We tested symptom specificity by examining studies of Parkinson's hallucinations (9 studies, 402 patients) that are frequently co-morbid with Parkinson's dementia. We tested for stage specificity by using studies of mild cognitive impairment in Parkinson's disease (15 studies, 844 patients). Coordinate-based network mapping revealed that correlates of visual hallucinations fell within a network centred on bilateral lateral geniculate nucleus and correlates of mild cognitive impairment in Parkinson's disease fell within a network centred on posterior default mode network. In both cases, the identified networks were distinct from the hippocampal network of Parkinson's dementia. Our results link heterogeneous neuroimaging findings in Parkinson's dementia to a common network centred on the hippocampus. This finding was symptom and stage-specific, with implications for understanding Parkinson's dementia and heterogeneity of neuroimaging findings in general.

Use of Magnetic Resonance Imaging and Artificial Intelligence in Studies of Diagnosis of Parkinson's Disease

Parkinson's disease (PD) is a common neurodegenerative disorder. It has a delitescent onset and a slow progress. The clinical manifestations of PD in patients are highly heterogeneous. Thus, PD diagnosis process is complex and mainly depends on the professional knowledge and experience of the physician. Magnetic resonance imaging (MRI) could detect the small changes in the brain of PD patients, and quantitative analysis of brain MRI may improve the clinical diagnosis efficiency. However, due to the complexity of clinical courses in PD and the high dimensionality in multimodal MRI data, traditional mathematical analysis could not effectively extract the huge information in them. Up to now, the accuracy of PD diagnosis in large sample size is still unsatisfying. As artificial intelligence (AI) is becoming more mature, varieties of statistical models and machine learning (ML) algorithms have been used for quantitative imaging data analysis to explore a diagnostic result. This review aims to state an overview of existing research recently that used statistical ML/AI methods to perform quantitative analysis of MR image data for the study of PD diagnosis. First we review the recent research in three subareas: diagnosis, differential diagnosis, and subtyping of PD. Then we described the overall workflow from MR image to classification result. Finally, we summarized a critical assessment of the current research and provide some recommendations for likely future research developments and trends.

Biomarkers for Dementia, Fatigue, and Depression in Parkinson's Disease

Parkinson's disease is a common multisystem neurodegenerative disorder characterized by typical motor and non-motor symptoms. There is an urgent need for biomarkers for assessment of disease severity, complications and prognosis. In addition, biomarkers reporting the underlying pathophysiology assist in understanding the disease and developing neuroprotective therapies. Ultimately, biomarkers could be used to develop a more efficient personalized approach for clinical trials and treatment strategies. With the goal to improve quality of life in Parkinson's disease it is essential to understand and objectively monitor non-motor symptoms. This narrative review provides an overview of recent developments of biomarkers (biofluid samples and imaging) for three common neuropsychological syndromes in Parkinson's disease: dementia, fatigue, and depression.

Machine Learning for Predicting Cognitive Diseases: Methods, Data Sources and Risk Factors

Machine learning and data mining approaches are being successfully applied to different fields of life sciences for the past 20 years. Medicine is one of the most suitable application domains for these techniques since they help model diagnostic information based on causal and/or statistical data and therefore reveal hidden dependencies between symptoms and illnesses. In this paper we give a detailed overview of the recent machine learning research and its applications for predicting cognitive diseases, especially the Alzheimer's disease, mild cognitive impairment and the Parkinson's disease. We survey different state-of-the-art methodological approaches, data sources and public data, and provide their comparative analysis. We conclude by identifying the open problems within the field that include an early detection of the cognitive diseases and inclusion of machine learning tools into diagnostic practice and therapy planning.

Can neuroimaging predict dementia in Parkinson's disease?

Dementia in Parkinson's disease affects 50% of patients within 10 years of diagnosis but there is wide variation in severity and timing. Thus, robust neuroimaging prediction of cognitive involvement in Parkinson's disease is important: (i) to identify at-risk individuals for clinical trials of potential new treatments; (ii) to provide reliable prognostic information for individuals and populations; and (iii) to shed light on the pathophysiological processes underpinning Parkinson's disease dementia. To date, neuroimaging has not made major contributions to predicting cognitive involvement in Parkinson's disease. This is perhaps unsurprising considering conventional methods rely on macroscopic measures of topographically distributed neurodegeneration, a relatively late event in Parkinson's dementia. However, new technologies are now emerging that could provide important insights through detection of other potentially relevant processes. For example, novel MRI approaches can quantify magnetic susceptibility as a surrogate for tissue iron content, and increasingly powerful mathematical approaches can characterize the topology of brain networks at the systems level. Here, we present an up-to-date overview of the growing role of neuroimaging in predicting dementia in Parkinson's disease. We discuss the most relevant findings to date, and consider the potential of emerging technologies to detect the earliest signs of cognitive involvement in Parkinson's disease.

Large-scale identification of clinical and genetic predictors of motor progression in patients with newly diagnosed Parkinson's disease: a longitudinal cohort study and validation

Background

Better understanding and prediction of PD progression could improve disease management and clinical trial design. We aimed to use longitudinal clinical, molecular, and genetic data to develop predictive models, compare potential biomarkers, and identify novel predictors for motor progression in PD. We also sought to assess the use of these models in the design of treatment trials in PD.

Methods

A Bayesian multivariate predictive inference platform was applied to data from the Parkinson’s Progression Markers Initiative (PPMI) study (NCT01141023). We used genetic data and baseline molecular and clinical variables from PD patients and healthy controls to construct an ensemble of models to predict the annualised rate of the Movement Disorder Society-Unified Parkinson’s Disease Rating Scale parts II and III combined. We tested our overall explanatory power, as assessed by the coefficient of determination (R²), and replicated novel findings in an independent clinical cohort of PD patients from the Longitudinal and Biomarker Study in PD (LABS-PD; NCT00605163). The potential utility of these models for clinical trial design was quantified by comparing simulated randomized placebo-controlled trials within the out-of sample LABS-PD cohort.

Findings

A total of 117 controls and 312 PD cases were available for analysis. Our model ensemble exhibited strong performance in-cohort (5-fold cross-validated R²=41%, 95% CI: 35% – 47%) and significant, though reduced, performance out-of-cohort (R²=9%, 95% CI: 4% – 16%). Individual predictive features identified from PPMI data were confirmed in the LABS-PD cohort of 317 PD patients. These included significant replication of higher baseline motor score, male sex, and increased age, as well as a novel PD-specific epistatic interaction all indicative of faster motor progression. Genetic variation was the most useful predictive marker of motor progression (2.9%, 95%CI: 1.5–4.3%). CSF biomarkers at baseline showed a more modest (0.3%; 95%CI: 0.1–0.5%), but still significant effect on motor progression prediction. The simulations (n=5000) showed that incorporating the predicted rates of motor progression into the final models of treatment effect reduced the variability in the study outcome allowing significant differences to be detected at sample sizes up to 20% smaller than in naïve trials.

Interpretation

Our model ensemble confirmed established and identified novel predictors of PD motor progression. Improving existing prognostic models through machine learning approaches should benefit trial design and evaluation, as well as clinical disease monitoring and treatment.

Funding

Michael J. Fox Foundation for Parkinson’s Research and National Institute of Neurological Disorders and Stroke (1P20NS092529-01).

Applying Naive Bayesian Networks to Disease Prediction: a Systematic Review

INTRODUCTION

Naive Bayesian networks (NBNs) are one of the most effective and simplest Bayesian networks for prediction.

OBJECTIVE

This paper aims to review published evidence about the application of NBNs in predicting disease and it tries to show NBNs as the fundamental algorithm for the best performance in comparison with other algorithms.

METHODS

PubMed was electronically checked for articles published between 2005 and 2015. For characterizing eligible articles, a comprehensive electronic searching method was conducted. Inclusion criteria were determined based on NBN and its effects on disease prediction. A total of 99 articles were found. After excluding the duplicates (n= 5), the titles and abstracts of 94 articles were skimmed according to the inclusion criteria. Finally, 38 articles remained. They were reviewed in full text and 15 articles were excluded. Eventually, 23 articles were selected which met our eligibility criteria and were included in this study.

RESULT

In this article, the use of NBN in predicting diseases was described. Finally, the results were reported in terms of Accuracy, Sensitivity, Specificity and Area under ROC curve (AUC). The last column in Table 2 shows the differences between NBNs and other algorithms.

DISCUSSION

This systematic review (23 studies, 53,725 patients) indicates that predicting diseases based on a NBN had the best performance in most diseases in comparison with the other algorithms. Finally in most cases NBN works better than other algorithms based on the reported accuracy.

CONCLUSION

The method, termed NBNs is proposed and can efficiently construct a prediction model for disease.

Biomarkers for dementia and mild cognitive impairment in Parkinson's disease

Cognitive decline is one of the most frequent and disabling nonmotor features of Parkinson's disease. Around 30% of patients with Parkinson's disease experience mild cognitive impairment, a well-established risk factor for the development of dementia. However, mild cognitive impairment in patients with Parkinson's disease is a heterogeneous entity that involves different types and extents of cognitive deficits. Because it is not currently known which type of mild cognitive impairment confers a higher risk of progression to dementia, it would be useful to define biomarkers that could identify these patients to better study disease progression and possible interventions. In this sense, the identification among patients with Parkinson's disease and mild cognitive impairment of biomarkers associated with dementia would allow the early detection of this process. This review summarizes studies from the past 25 years that have assessed the potential biomarkers of dementia and mild cognitive impairment in Parkinson's disease patients. Despite the potential importance, no biomarker has as yet been validated. However, features such as low levels of epidermal and insulin-like growth factors or uric acid in plasma/serum and of Aß in CSF, reduction of cerebral cholinergic innervation and metabolism measured by PET mainly in posterior areas, and hippocampal atrophy in MRI might be indicative of distinct deficits with a distinct risk of dementia in subgroups of patients. Longitudinal studies combining the existing techniques and new approaches are needed to identify patients at higher risk of dementia. © 2016 International Parkinson and Movement Disorder Society.

Bayesian network classifiers for categorizing cortical GABAergic interneurons

An accepted classification of GABAergic interneurons of the cerebral cortex is a major goal in neuroscience. A recently proposed taxonomy based on patterns of axonal arborization promises to be a pragmatic method for achieving this goal. It involves characterizing interneurons according to five axonal arborization features, called F1-F5, and classifying them into a set of predefined types, most of which are established in the literature. Unfortunately, there is little consensus among expert neuroscientists regarding the morphological definitions of some of the proposed types. While supervised classifiers were able to categorize the interneurons in accordance with experts' assignments, their accuracy was limited because they were trained with disputed labels. Thus, here we automatically classify interneuron subsets with different label reliability thresholds (i.e., such that every cell's label is backed by at least a certain (threshold) number of experts). We quantify the cells with parameters of axonal and dendritic morphologies and, in order to predict the type, also with axonal features F1-F4 provided by the experts. Using Bayesian network classifiers, we accurately characterize and classify the interneurons and identify useful predictor variables. In particular, we discriminate among reliable examples of common basket, horse-tail, large basket, and Martinotti cells with up to 89.52% accuracy, and single out the number of branches at 180 μm from the soma, the convex hull 2D area, and the axonal features F1-F4 as especially useful predictors for distinguishing among these types. These results open up new possibilities for an objective and pragmatic classification of interneurons.

Neurological Diseases from a Systems Medicine Point of View

The difficulty to understand, diagnose, and treat neurological disorders stems from the great complexity of the central nervous system on different levels of physiological granularity. The individual components, their interactions, and dynamics involved in brain development and function can be represented as molecular, cellular, or functional networks, where diseases are perturbations of networks. These networks can become a useful research tool in investigating neurological disorders if they are properly tailored to reflect corresponding mechanisms. Here, we review approaches to construct networks specific for neurological disorders describing disease-related pathology on different scales: the molecular, cellular, and brain level. We also briefly discuss cross-scale network analysis as a necessary integrator of these scales.

Distinguishing Parkinson's disease from atypical parkinsonian syndromes using PET data and a computer system based on support vector machines and Bayesian networks

Differentiating between Parkinson's disease (PD) and atypical parkinsonian syndromes (APS) is still a challenge, specially at early stages when the patients show similar symptoms. During last years, several computer systems have been proposed in order to improve the diagnosis of PD, but their accuracy is still limited. In this work we demonstrate a full automatic computer system to assist the diagnosis of PD using ¹⁸F-DMFP PET data. First, a few regions of interest are selected by means of a two-sample t-test. The accuracy of the selected regions to separate PD from APS patients is then computed using a support vector machine classifier. The accuracy values are finally used to train a Bayesian network that can be used to predict the class of new unseen data. This methodology was evaluated using a database with 87 neuroimages, achieving accuracy rates over 78%. A fair comparison with other similar approaches is also provided.

Bayesian predictive modeling based on multidimensional connectivity profiling

Dysfunction of brain structural and functional connectivity is increasingly being recognized as playing an important role in many brain disorders. Diffusion tensor imaging (DTI) and functional magnetic resonance (fMR) imaging are widely used to infer structural and functional connectivity, respectively. How to combine structural and functional connectivity patterns for predictive modeling is an important, yet open, problem. We propose a new method, called Bayesian prediction based on multidimensional connectivity profiling (BMCP), to distinguish subjects at the individual level based on structural and functional connectivity patterns. BMCP combines finite mixture modeling and Bayesian network classification. We demonstrate its use in distinguishing young and elderly adults based on DTI and resting-state fMR data.

Predictive structural dynamic network analysis

BACKGROUND

Classifying individuals based on magnetic resonance data is an important task in neuroscience. Existing brain network-based methods to classify subjects analyze data from a cross-sectional study and these methods cannot classify subjects based on longitudinal data. We propose a network-based predictive modeling method to classify subjects based on longitudinal magnetic resonance data.

NEW METHOD

Our method generates a dynamic Bayesian network model for each group which represents complex spatiotemporal interactions among brain regions, and then calculates a score representing that subject's deviation from expected network patterns. This network-derived score, along with other candidate predictors, are used to construct predictive models.

RESULTS

We validated the proposed method based on simulated data and the Alzheimer's Disease Neuroimaging Initiative study. For the Alzheimer's Disease Neuroimaging Initiative study, we built a predictive model based on the baseline biomarker characterizing the baseline state and the network-based score which was constructed based on the state transition probability matrix. We found that this combined model achieved 0.86 accuracy, 0.85 sensitivity, and 0.87 specificity.

COMPARISON WITH EXISTING METHODS

For the Alzheimer's Disease Neuroimaging Initiative study, the model based on the baseline biomarkers achieved 0.77 accuracy. The accuracy of our model is significantly better than the model based on the baseline biomarkers (p-value=0.002).

CONCLUSIONS

We have presented a method to classify subjects based on structural dynamic network model based scores. This method is of great importance to distinguish subjects based on structural network dynamics and the understanding of the network architecture of brain processes and disorders.

Classification of pallidal oscillations with increasing parkinsonian severity

The firing patterns of neurons in the basal ganglia are known to become more oscillatory and synchronized from healthy to parkinsonian conditions. Similar changes have been observed with local field potentials (LFPs). In this study, we used an unbiased machine learning approach to investigate the utility of pallidal LFPs for discriminating the stages of a progressive parkinsonian model. A feature selection algorithm was used to identify subsets of LFP features that provided the most discriminatory information for severity of parkinsonian motor signs. Prediction errors <20% were achievable using 28 of the possible 206 features tested. For all subjects, a spectral feature within the beta band was chosen through the feature selection algorithm, but a combination of features, including alpha-band power and phase-amplitude coupling, was necessary to achieve minimal prediction errors. There was large variability between the discriminatory features for individual subjects, and testing of classifiers between subjects yielded prediction errors >50%. These results suggest that pallidal oscillations can be predictive biomarkers of parkinsonian severity, but the features are more complex than spectral power in individual frequency bands, such as the beta band. Additionally, the best feature set was subject specific, which highlights the pathophysiological heterogeneity of parkinsonism and the importance of subject specificity when designing closed-loop system controllers dependent on such features.

Recent imaging advances in neurology

Over the recent years, the application of neuroimaging techniques such as magnetic resonance imaging (MRI) and positron emission tomography (PET) has considerably advanced the understanding of complex neurological disorders. PET is a powerful molecular imaging tool, which investigates the distribution and binding of radiochemicals attached to biologically relevant molecules; as such, this technique is able to give information on biochemistry and metabolism of the brain in health and disease. MRI uses high intensity magnetic fields and radiofrequency pulses to provide structural and functional information on tissues and organs in intact or diseased individuals, including the evaluation of white matter integrity, grey matter thickness and brain perfusion. The aim of this article is to review the most recent advances in neuroimaging research in common neurological disorders such as movement disorders, dementia, epilepsy, traumatic brain injury and multiple sclerosis, and to evaluate their contribution in the diagnosis and management of patients.

Bayesian networks in neuroscience: a survey

Bayesian networks are a type of probabilistic graphical models lie at the intersection between statistics and machine learning. They have been shown to be powerful tools to encode dependence relationships among the variables of a domain under uncertainty. Thanks to their generality, Bayesian networks can accommodate continuous and discrete variables, as well as temporal processes. In this paper we review Bayesian networks and how they can be learned automatically from data by means of structure learning algorithms. Also, we examine how a user can take advantage of these networks for reasoning by exact or approximate inference algorithms that propagate the given evidence through the graphical structure. Despite their applicability in many fields, they have been little used in neuroscience, where they have focused on specific problems, like functional connectivity analysis from neuroimaging data. Here we survey key research in neuroscience where Bayesian networks have been used with different aims: discover associations between variables, perform probabilistic reasoning over the model, and classify new observations with and without supervision. The networks are learned from data of any kind-morphological, electrophysiological, -omics and neuroimaging-, thereby broadening the scope-molecular, cellular, structural, functional, cognitive and medical- of the brain aspects to be studied.

Predictors of mild cognitive impairment in early-stage Parkinson's disease

Aim

The aim of this study was to identify mild cognitive deficits in Parkinson's disease (PD) prior to extensive neurodegeneration and to evaluate the extent to which dopamine depletion and other disease-related predictors can explain cognitive profiles.

Methods

Neuropsychological performances of 40 nondemented early-stage PD patients and 42 healthy controls were compared across on or off dopaminergic medications. Stepwise regression evaluated cognitive predictors of early-stage PD and disease-related predictors of PD cognition (levodopa dose, disease duration, Unified Parkinson's Disease Rating Scale score, sleep, quality of life, and mood) across on and off states.

Results

Neuropsychological performance was lower in PD patients across cognitive domains with significant memory, naming, visuomotor, and complex attention/executive deficits, but with intact visuospatial, simple attention, and phonemic fluency functions. However, medication effects were absent except for simple attention. Regression analyses revealed age, working memory, and memory recall to be the best cognitive predictors of PD, while age, quality of life, disease duration, and anxiety predicted PD cognition in the off state.

Conclusion

Nondemented early-stage PD patients presented with extensive mild cognitive deficits including prominent memory impairment. The profile was inconsistent with expected isolated frontostriatal dysfunction previously attributed to dopamine depletion and this highlights the need to further characterize extranigral sources of mild cognitive impairment in PD.