An artificial neural network approach to detect presence and severity of Parkinson's disease via gait parameters

Optimizing Rare Disease Gait Classification through Data Balancing and Generative AI: Insights from Hereditary Cerebellar Ataxia

The interpretability of gait analysis studies in people with rare diseases, such as those with primary hereditary cerebellar ataxia (pwCA), is frequently limited by the small sample sizes and unbalanced datasets. The purpose of this study was to assess the effectiveness of data balancing and generative artificial intelligence (AI) algorithms in generating synthetic data reflecting the actual gait abnormalities of pwCA. Gait data of 30 pwCA (age: 51.6 ± 12.2 years; 13 females, 17 males) and 100 healthy subjects (age: 57.1 ± 10.4; 60 females, 40 males) were collected at the lumbar level with an inertial measurement unit. Subsampling, oversampling, synthetic minority oversampling, generative adversarial networks, and conditional tabular generative adversarial networks (ctGAN) were applied to generate datasets to be input to a random forest classifier. Consistency and explainability metrics were also calculated to assess the coherence of the generated dataset with known gait abnormalities of pwCA. ctGAN significantly improved the classification performance compared with the original dataset and traditional data augmentation methods. ctGAN are effective methods for balancing tabular datasets from populations with rare diseases, owing to their ability to improve diagnostic models with consistent explainability.

New era of artificial intelligence and machine learning-based detection, diagnosis, and therapeutics in Parkinson's disease

Parkinson's disease (PD) is characterized by the loss of neuronal cells, which leads to synaptic dysfunction and cognitive defects. Despite the advancements in treatment strategies, the management of PD is still a challenging event. Early prediction and diagnosis of PD are of utmost importance for effective management of PD. In addition, the classification of patients with PD as compared to normal healthy individuals also imposes drawbacks in the early diagnosis of PD. To address these challenges, artificial intelligence (AI) and machine learning (ML) models have been implicated in the diagnosis, prediction, and treatment of PD. Recent times have also demonstrated the implication of AI and ML models in the classification of PD based on neuroimaging methods, speech recording, gait abnormalities, and others. Herein, we have briefly discussed the role of AI and ML in the diagnosis, treatment, and identification of novel biomarkers in the progression of PD. We have also highlighted the role of AI and ML in PD management through altered lipidomics and gut-brain axis. We briefly explain the role of early PD detection through AI and ML algorithms based on speech recordings, handwriting patterns, gait abnormalities, and neuroimaging techniques. Further, the review discuss the potential role of the metaverse, the Internet of Things, and electronic health records in the effective management of PD to improve the quality of life. Lastly, we also focused on the implementation of AI and ML-algorithms in neurosurgical process and drug discovery.

Neurophysiology of cerebellar ataxias and gait disorders

There are numerous forms of cerebellar disorders from sporadic to genetic diseases. The aim of this chapter is to provide an overview of the advances and emerging techniques during these last 2 decades in the neurophysiological tests useful in cerebellar patients for clinical and research purposes. Clinically, patients exhibit various combinations of a vestibulocerebellar syndrome, a cerebellar cognitive affective syndrome and a cerebellar motor syndrome which will be discussed throughout this chapter. Cerebellar patients show abnormal Bereitschaftpotentials (BPs) and mismatch negativity. Cerebellar EEG is now being applied in cerebellar disorders to unravel impaired electrophysiological patterns associated within disorders of the cerebellar cortex. Eyeblink conditioning is significantly impaired in cerebellar disorders: the ability to acquire conditioned eyeblink responses is reduced in hereditary ataxias, in cerebellar stroke and after tumor surgery of the cerebellum. Furthermore, impaired eyeblink conditioning is an early marker of cerebellar degenerative disease. General rules of motor control suggest that optimal strategies are needed to execute voluntary movements in the complex environment of daily life. A high degree of adaptability is required for learning procedures underlying motor control as sensorimotor adaptation is essential to perform accurate goal-directed movements. Cerebellar patients show impairments during online visuomotor adaptation tasks. Cerebellum-motor cortex inhibition (CBI) is a neurophysiological biomarker showing an inverse association between cerebellothalamocortical tract integrity and ataxia severity. Ataxic gait is characterized by increased step width, reduced ankle joint range of motion, increased gait variability, lack of intra-limb inter-joint and inter-segmental coordination, impaired foot ground placement and loss of trunk control. Taken together, these techniques provide a neurophysiological framework for a better appraisal of cerebellar disorders.

Predicting vertical ground reaction force in rearfoot running: A wavelet neural network model and factor loading

This study proposed a simple method for selecting input variables by factor loading and inputting these variables into a wavelet neural network (WNN) model to predict vertical ground reaction force (vGRF). The kinematic data and vGRF of 9 rearfoot strikers at 12, 14, and 16 km/h were collected using a motion capture system and an instrumented treadmill. The input variables were screened by factor loading and utilized to predict vGRF with the WNN. Nine kinematic variables were selected, corresponding to nine principal components, mainly focusing on the knee and ankle joints. The prediction results of vGRF were effective and accurate at different speeds, namely, the coefficient of multiple correlation (CMC) > 0.98 (0.984-0.988), the normalized root means square error (NRMSE) < 15% (9.34-11.51%). The NRMSEs of impact force (8.18-10.01%), active force (4.92-7.42%), and peak time (7.16-12.52%) were less than 15%. There was a small number (peak, 4.12-6.18%; time, 4.71-6.76%) exceeding the 95% confidence interval (CI) using the Bland-Altman method. The knee joint was the optimal location for estimating vGRF, followed by the ankle. There were high accuracy and agreement for predicting vGRF with the peak and peak time at 12, 14, and 16 km/h. Therefore, factor loading could be a valid method to screen kinematic variables in artificial neural networks.

Multiscale Entropy Algorithms to Analyze Complexity and Variability of Trunk Accelerations Time Series in Subjects with Parkinson's Disease

The aim of this study was to assess the ability of multiscale sample entropy (MSE), refined composite multiscale entropy (RCMSE), and complexity index (CI) to characterize gait complexity through trunk acceleration patterns in subjects with Parkinson's disease (swPD) and healthy subjects, regardless of age or gait speed. The trunk acceleration patterns of 51 swPD and 50 healthy subjects (HS) were acquired using a lumbar-mounted magneto-inertial measurement unit during their walking. MSE, RCMSE, and CI were calculated on 2000 data points, using scale factors (τ) 1-6. Differences between swPD and HS were calculated at each τ, and the area under the receiver operating characteristics, optimal cutoff points, post-test probabilities, and diagnostic odds ratios were calculated. MSE, RCMSE, and CIs showed to differentiate swPD from HS. MSE in the anteroposterior direction at τ4 and τ5, and MSE in the ML direction at τ4 showed to characterize the gait disorders of swPD with the best trade-off between positive and negative posttest probabilities and correlated with the motor disability, pelvic kinematics, and stance phase. Using a time series of 2000 data points, a scale factor of 4 or 5 in the MSE procedure can yield the best trade-off in terms of post-test probabilities when compared to other scale factors for detecting gait variability and complexity in swPD.

Identification of a Gait Pattern for Detecting Mild Cognitive Impairment in Parkinson's Disease

The aim of this study was to determine a gait pattern, i.e., a subset of spatial and temporal parameters, through a supervised machine learning (ML) approach, which could be used to reliably distinguish Parkinson's Disease (PD) patients with and without mild cognitive impairment (MCI). Thus, 80 PD patients underwent gait analysis and spatial-temporal parameters were acquired in three different conditions (normal gait, motor dual task and cognitive dual task). Statistical analysis was performed to investigate the data and, then, five ML algorithms and the wrapper method were implemented: Decision Tree (DT), Random Forest (RF), Naïve Bayes (NB), Support Vector Machine (SVM) and K-Nearest Neighbour (KNN). First, the algorithms for classifying PD patients with MCI were trained and validated on an internal dataset (sixty patients) and, then, the performance was tested by using an external dataset (twenty patients). Specificity, sensitivity, precision, accuracy and area under the receiver operating characteristic curve were calculated. SVM and RF showed the best performance and detected MCI with an accuracy of over 80.0%. The key features emerging from this study are stance phase, mean velocity, step length and cycle length; moreover, the major number of features selected by the wrapper belonged to the cognitive dual task, thus, supporting the close relationship between gait dysfunction and MCI in PD.

Application of Artificial Intelligence in Image Processing of Neurodegenerative Disorders: A Review Study

: Neurodegenerative diseases can make life difficult and lead to death in many cases. They also can be difficult, time-consuming, and costly to diagnose with enough accuracy/certainty. Artificial intelligence (AI) has shown promise in tackling some of the challenges present in medical imaging and is anticipated to become a crucial tool in health care applications in the near future. In particular, deep learning methods have displayed great performance in various subfields of image processing, including but not limited to image segmentation, image synthesis, and image reconstruction. In this paper, many state-of-the-art applications of deep learning models in image processing were reviewed.

Harmonic ratio is the most responsive trunk-acceleration derived gait index to rehabilitation in people with Parkinson's disease at moderate disease stages

BACKGROUND

Harmonic ratios (HRs), recurrence quantification analysis in the antero-posterior direction (RQA_detAP), and stride length coefficient of variation (CV) have recently been shown to characterize gait abnormalities and fall risk in people with Parkinson's disease (pwPD) at moderate disease stages.

RESEARCH QUESTION

This study aimed to i) assess the internal and external responsiveness to rehabilitation of HR, RQA_detAP, and CV, ii) identify the baseline predictors of normalization of the gait stability indexes, and iii) investigate the correlations between the gait indexes modifications (∆) and clinical and kinematic ∆s in pwPD at Hoehn and Yahr disease staging classification 3.

METHODS

The trunk acceleration patterns of 21 pwPD and 21 age- and speed-matched healthy subjects (HSmatched) were acquired during gait using an inertial measurement unit at baseline (T0). pwPD were also assessed after a 4-week rehabilitation period (T1). Each participant's HR in the antero-posterior (HR_AP), medio-lateral (HR_ML), and vertical directions, RQA_detAP, CV, spatio-temporal, and kinematic variables were calculated.

RESULTS

At T1, HR_AP and HR_ML improved to normative values and showed high internal and external responsiveness. Lower HRs and higher pelvic rotation values at baseline were predictors of ∆HRs. A minimal clinically important difference (MCID) ≥ 21.5 % is required to normalize HR_AP with 95 % probability. MCID ≥ 36.9 % is required to normalize HR_ML with 92 % probability. ∆HR_AP correlated with ∆HR_ML and both correlated with ∆stride length and ∆pelvic rotation, regardless of ∆gait speed. RQAdetAP and step length CV were not responsive to rehabilitation.

SIGNIFICANCE

When using inertial measurement units, HR_AP and HR_ML can be considered as responsive outcome measures for assessing the effectiveness of rehabilitation on trunk smoothness during walking in pwPD at moderate disease stages.

Impact of Parkinson’s Disease on Functional Mobility at Different Stages

Introduction

Specific functional assessments to determine the progression of Parkinson’s Disease (PD) are important to slow down such progression and better plan rehabilitation. This study aimed to explore possible differences in the performance of different functional tasks included in a mobility test using sensors embedded in an Android device, in people at different PD stages.

Materials and Methods

Eighty-seven participants with PD agreed to participate in this cross-sectional study. They were assessed once using an inertial sensor and variables related to functional status were recorded (i.e., MLDisp, APDisp, DispA, Vrange, MLRange, PTurnSit, PStand, TTime, and RTime).

Results

There was significant impairment of the vertical range during gait between stages I and II. Further, when stages II and III were compared, the sit-to-stand power was significantly impaired, and the total time required to complete the test increased significantly (p < 0.05). Even more significant differences were obtained when stages I and III were compared, in particular, dysfunction in postural control, vertical range, sit to stand power and total time. Finally, there were no significant differences between stages in the medial-lateral displacements and reaction time (p > 0.05).

Conclusion

Functional mobility becomes more significantly impaired in the PD population as the PD stages progress. This implies impaired postural control, decreased ability to sit down or stand up from a chair, increased metabolic cost during walking, and overall slowing-down of motor function.

Machine Learning Classifiers to Evaluate Data From Gait Analysis With Depth Cameras in Patients With Parkinson's Disease

Introduction

The assessments of the motor symptoms in Parkinson's disease (PD) are usually limited to clinical rating scales (MDS UPDRS III), and it depends on the clinician's experience. This study aims to propose a machine learning technique algorithm using the variables from upper and lower limbs, to classify people with PD from healthy people, using data from a portable low-cost device (RGB-D camera). And can be used to support the diagnosis and follow-up of patients in developing countries and remote areas.

Methods

We used Kinect®eMotion system to capture the spatiotemporal gait data from 30 patients with PD and 30 healthy age-matched controls in three walking trials. First, a correlation matrix was made using the variables of upper and lower limbs. After this, we applied a backward feature selection model using R and Python to determine the most relevant variables. Three further analyses were done using variables selected from backward feature selection model (Dataset A), movement disorders specialist (Dataset B), and all the variables from the dataset (Dataset C). We ran seven machine learning models for each model. Dataset was divided 80% for algorithm training and 20% for evaluation. Finally, a causal inference model (CIM) using the DoWhy library was performed on Dataset B due to its accuracy and simplicity.

Results

The Random Forest model is the most accurate for all three variable Datasets (Dataset A: 81.8%; Dataset B: 83.6%; Dataset C: 84.5%) followed by the support vector machine. The CIM shows a relation between leg variables and the arms swing asymmetry (ASA) and a proportional relationship between ASA and the diagnosis of PD with a robust estimator (1,537).

Conclusions

Machine learning techniques based on objective measures using portable low-cost devices (Kinect®eMotion) are useful and accurate to classify patients with Parkinson's disease. This method can be used to evaluate patients remotely and help clinicians make decisions regarding follow-up and treatment.

Machine Learning Approach to Support the Detection of Parkinson's Disease in IMU-Based Gait Analysis

The aim of this study was to determine which supervised machine learning (ML) algorithm can most accurately classify people with Parkinson’s disease (pwPD) from speed-matched healthy subjects (HS) based on a selected minimum set of IMU-derived gait features. Twenty-two gait features were extrapolated from the trunk acceleration patterns of 81 pwPD and 80 HS, including spatiotemporal, pelvic kinematics, and acceleration-derived gait stability indexes. After a three-level feature selection procedure, seven gait features were considered for implementing five ML algorithms: support vector machine (SVM), artificial neural network, decision trees (DT), random forest (RF), and K-nearest neighbors. Accuracy, precision, recall, and F1 score were calculated. SVM, DT, and RF showed the best classification performances, with prediction accuracy higher than 80% on the test set. The conceptual model of approaching ML that we proposed could reduce the risk of overrepresenting multicollinear gait features in the model, reducing the risk of overfitting in the test performances while fostering the explainability of the results.

Comparison of machine learning algorithms applied to symptoms to determine infectious causes of death in children: national survey of 18,000 verbal autopsies in the Million Death Study in India

BACKGROUND

Machine learning (ML) algorithms have been successfully employed for prediction of outcomes in clinical research. In this study, we have explored the application of ML-based algorithms to predict cause of death (CoD) from verbal autopsy records available through the Million Death Study (MDS).

METHODS

From MDS, 18826 unique childhood deaths at ages 1-59 months during the time period 2004-13 were selected for generating the prediction models of which over 70% of deaths were caused by six infectious diseases (pneumonia, diarrhoeal diseases, malaria, fever of unknown origin, meningitis/encephalitis, and measles). Six popular ML-based algorithms such as support vector machine, gradient boosting modeling, C5.0, artificial neural network, k-nearest neighbor, classification and regression tree were used for building the CoD prediction models.

RESULTS

SVM algorithm was the best performer with a prediction accuracy of over 0.8. The highest accuracy was found for diarrhoeal diseases (accuracy = 0.97) and the lowest was for meningitis/encephalitis (accuracy = 0.80). The top signs/symptoms for classification of these CoDs were also extracted for each of the diseases. A combination of signs/symptoms presented by the deceased individual can effectively lead to the CoD diagnosis.

CONCLUSIONS

Overall, this study affirms that verbal autopsy tools are efficient in CoD diagnosis and that automated classification parameters captured through ML could be added to verbal autopsies to improve classification of causes of death.

The Role of Neural Network for the Detection of Parkinson's Disease: A Scoping Review

Background: Parkinson’s Disease (PD) is a chronic neurodegenerative disorder that has been ranked second after Alzheimer’s disease worldwide. Early diagnosis of PD is crucial to combat against PD to allow patients to deal with it properly. However, there is no medical test(s) available to diagnose PD conclusively. Therefore, computer-aided diagnosis (CAD) systems offered a better solution to make the necessary data-driven decisions and assist the physician. Numerous studies were conducted to propose CAD to diagnose PD in the early stages. No comprehensive reviews have been conducted to summarize the role of AI tools to combat PD. Objective: The study aimed to explore and summarize the applications of neural networks to diagnose PD. Methods: PRISMA Extension for Scoping Reviews (PRISMA-ScR) was followed to conduct this scoping review. To identify the relevant studies, both medical databases (e.g., PubMed) and technical databases (IEEE) were searched. Three reviewers carried out the study selection and extracted the data from the included studies independently. Then, the narrative approach was adopted to synthesis the extracted data. Results: Out of 1061 studies, 91 studies satisfied the eligibility criteria in this review. About half of the included studies have implemented artificial neural networks to diagnose PD. Numerous studies included focused on the freezing of gait (FoG). Biomedical voice and signal datasets were the most commonly used data types to develop and validate these models. However, MRI- and CT-scan images were also utilized in the included studies. Conclusion: Neural networks play an integral and substantial role in combating PD. Many possible applications of neural networks were identified in this review, however, most of them are limited up to research purposes.

Ability of a Set of Trunk Inertial Indexes of Gait to Identify Gait Instability and Recurrent Fallers in Parkinson's Disease

The aims of this study were to assess the ability of 16 gait indices to identify gait instability and recurrent fallers in persons with Parkinson’s disease (pwPD), regardless of age and gait speed, and to investigate their correlation with clinical and kinematic variables. The trunk acceleration patterns were acquired during the gait of 55 pwPD and 55 age-and-speed matched healthy subjects using an inertial measurement unit. We calculated the harmonic ratios (HR), percent recurrence, and percent determinism (RQAdet), coefficient of variation, normalized jerk score, and the largest Lyapunov exponent for each participant. A value of ≤1.50 for the HR in the antero-posterior direction discriminated between pwPD at Hoehn and Yahr (HY) stage 3 and healthy subjects with a 67% probability, between pwPD at HY 3 and pwPD at lower HY stages with a 73% probability, and it characterized recurrent fallers with a 77% probability. Additionally, HR in the antero-posterior direction was correlated with pelvic obliquity and rotation. RQAdet in the antero-posterior direction discriminated between pwPD and healthy subjects with 67% probability, regardless of the HY stage, and was correlated with stride duration and cadence. Therefore, HR and RQA_det in the antero-posterior direction can both be used as age- and-speed-independent markers of gait instability.

Current Perspectives on the Assessment and Management of Gait Disorders in Parkinson's Disease

Gait dysfunction is a key defining feature of Parkinson's disease (PD), and is associated with symptoms of freezing and an increased risk of falls. In this narrative review, we cover the putative mechanisms of gait dysfunction in PD, the assessment of gait abnormalities, and the management of symptoms caused by the inherent difficulty in walking. Our understanding of the causes of gait problems in PD has progressed in recent times, moving from neurocognitive theory to correlates of affected neuronal pathways. In particular, this can be shown to correspond with abnormalities in responses to dual-task paradigms and dysfunction in cholinergic signaling. Great progress has been made in the sophistication and precision of gait assessment; however, it has firmly remained in the research domain. There is significant momentum behind wearable technologies that can be used by patients in their own environment, acting as digital biomarkers that can not only reflect progression but also independently discriminate PD from non-PD individuals. The treatment of gait dysfunction has historically relied on physical therapies and training combined with a view to mitigating the impact of such consequences as falls. Pharmacological therapies that are the mainstay of treatment in PD have tended to address symptoms like bradykinesia; however, optimization of dopaminergic therapies likely has a positive effect on quality of gait. Other targets have been assessed with the goal of improving gait, of which medications that improve cholinergic signaling appear most promising. Neuromodulation techniques are increasingly used in the form of deep-brain stimulation; however, standard targets, such as the globus pallidus interna, have a modest effect on gait. Considerable benefit has been seen through targeting the pedunculopontine nucleus, and a dual-target approach may be warranted. Stimulation of the spinal cord and brain through direct or magnetic approaches has been assessed, but requires further evidence.