Predicting Multiple Sclerosis From Gait Dynamics Using an Instrumented Treadmill: A Machine Learning Approach

An analytical review on the use of artificial intelligence and machine learning in diagnosis, prediction, and risk factor analysis of multiple sclerosis

Medical research offers potential for disease prediction, like Multiple Sclerosis (MS). This neurological disorder damages nerve cell sheaths, with treatments focusing on symptom relief. Manual MS detection is time-consuming and error prone. Though MS lesion detection has been studied, limited attention has been paid to clinical analysis and computational risk factor prediction. Artificial intelligence (AI) techniques and Machine Learning (ML) methods offer accurate and effective alternatives to mapping MS progression. However, there are challenges in accessing clinical data and interdisciplinary collaboration. By analyzing 103 papers, we recognize the trends, strengths and weaknesses of AI, ML, and statistical methods applied to MS diagnosis. AI/ML-based approaches are suggested to identify MS risk factors, select significant MS features, and improve the diagnostic accuracy, such as Rule-based Fuzzy Logic (RBFL), Adaptive Fuzzy Inference System (ANFIS), Artificial Neural Network methods (ANN), Support Vector Machine (SVM), and Bayesian Networks (BNs). Meanwhile, applications of the Expanded Disability Status Scale (EDSS) and Magnetic Resonance Imaging (MRI) can enhance MS diagnostic accuracy. By examining established risk factors like obesity, smoking, and education, some research tackled the issue of disease progression. The performance metrics varied across different aspects of MS studies: Diagnosis: Sensitivity ranged from 60 % to 98 %, specificity from 60 % to 98 %, and accuracy from 61 % to 97 %. Prediction: Sensitivity ranged from 76 % to 98 %, specificity from 65 % to 98 %, and accuracy from 62 % to 99 %. Segmentation: Accuracy ranged up to 96.7 %. Classification: Sensitivity ranged from 78 % to 97.34 %, specificity from 65 % to 99.32 %, and accuracy from 71 % to 97.94 %. Furthermore, the literature shows that combining techniques can improve efficiency, exploiting their strengths for better overall performance.

Perturbation walking effects on prefrontal cortical activation and walking performance in older women with and without osteoarthritis: a FNIRS study

Introduction

Perturbation walking (PW) has been shown to improve gait, however its effect on the cortical control of gait might provide insights on neural mechanisms underlying falls in adults with osteoarthritis. The objective of this study is to investigate the effect of PW on prefrontal cortical (PFC) activation in older women with (OA) and without osteoarthritis (HOA). We hypothesized that there would be an increase in PFC activation during PW relative to comfortable walking (CW) and higher increase in PFC activation during PW in HOA compared to OA.

Methods

Twenty community-dwelling older women (66.7 ± 5.41 years old) walked on an instrumented treadmill that provided perturbations at pseudo-random intervals between 5-25 s using a counterbalanced design. Functional Near Infrared Spectroscopy was used to quantify PFC oxygenated hemoglobin (HbO2) and deoxyhemoglobin (Hb) levels, while standing prior to the task as a baseline. A linear mixed effects model was conducted to investigate the effects of cohort (HOA vs OA), task (PW vs CW), and their interaction on HbO2 (μM) and Hb (μM) levels.

Results

HbO2 and Hb levels differed significantly between CW and PW tasks for both cohorts (P < 0.001) and demonstrated significant task by cohort interaction (P < 0.05). In addition, we found changes in walking performance (stride time, stride length, stride width and stance time) during and after PW. Spearman correlation demonstrated a strong association between increased stance time, increased body mass index and decreased PFC activation during PW. No other significant results were found.

Discussion

This study found increase in PFC activation during PW and gait adaptation after a short bout of PW in HOA and OA. This increase in PFC activation was higher in HOA compared to OA, particularly during PW tasks, and was consistent with theory of limitations in mobility affecting neural activation in older adults. Further work remains to examine how pain, obesity, and mobility impacts cortical control in older adults with and without osteoarthritis.

Remyelinating Drugs at a Crossroad: How to Improve Clinical Efficacy and Drug Screenings

Axons wrapped around the myelin sheath enable fast transmission of neuronal signals in the Central Nervous System (CNS). Unfortunately, myelin can be damaged by injury, viral infection, and inflammatory and neurodegenerative diseases. Remyelination is a spontaneous process that can restore nerve conductivity and thus movement and cognition after a demyelination event. Cumulative evidence indicates that remyelination can be pharmacologically stimulated, either by targeting natural inhibitors of Oligodendrocyte Precursor Cells (OPCs) differentiation or by reactivating quiescent Neural Stem Cells (qNSCs) proliferation and differentiation in myelinating Oligodendrocytes (OLs). Although promising results were obtained in animal models for demyelination diseases, none of the compounds identified have passed all the clinical stages. The significant number of patients who could benefit from remyelination therapies reinforces the urgent need to reassess drug selection approaches and develop strategies that effectively promote remyelination. Integrating Artificial Intelligence (AI)-driven technologies with patient-derived cell-based assays and organoid models is expected to lead to novel strategies and drug screening pipelines to achieve this goal. In this review, we explore the current literature on these technologies and their potential to enhance the identification of more effective drugs for clinical use in CNS remyelination therapies.

Explainable machine learning for predicting conversion to neurological disease: Results from 52,939 medical records

Objective

This study assesses the application of interpretable machine learning modeling using electronic medical record data for the prediction of conversion to neurological disease.

Methods

A retrospective dataset of Cleveland Clinic patients diagnosed with Alzheimer's disease, amyotrophic lateral sclerosis, multiple sclerosis, or Parkinson's disease, and matched controls based on age, sex, race, and ethnicity was compiled. Individualized risk prediction models were created using eXtreme Gradient Boosting for each neurological disease at four timepoints in patient history. The prediction models were assessed for transparency and fairness.

Results

At timepoints 0-months, 12-months, 24-months, and 60-months prior to diagnosis, Alzheimer's disease models achieved the area under the receiver operating characteristic curve on a holdout test dataset of 0.794, 0.742, 0.709, and 0.645; amyotrophic lateral sclerosis of 0.883, 0.710, 0.658, and 0.620; multiple sclerosis of 0.922, 0.877, 0.849, and 0.781; and Parkinson's disease of 0.809, 0.738, 0.700, and 0.651, respectively.

Conclusions

The results demonstrate that electronic medical records contain latent information that can be used for risk stratification for neurological disorders. In particular, patient-reported outcomes, sleep assessments, falls data, additional disease diagnoses, and longitudinal changes in patient health, such as weight change, are important predictors.

MR myelin imaging in multiple sclerosis: A scoping review

The inability of disease-modifying therapies to stop the progression of multiple sclerosis (MS), has led to the development of a new therapeutic strategy focussing on myelin repair. While conventional MRI lacks sensitivity for quantifying myelin damage, advanced MRI techniques are proving effective. The development of targeted therapeutics requires histological validation of myelin imaging results, alongside the crucial task of establishing correlations between myelin imaging results and clinical assessments, so that the effectiveness of therapeutic interventions can be evaluated. The aims of this scoping review were to identify myelin imaging methods - some of which have been histologically validated, and to determine how these approaches correlate with clinical assessments of people with MS (pwMS), thus allowing for effective therapeutic evaluation. A search of two databases was undertaken for publications relating to studies on adults MS using either MRI/MR-histology of the MS brain in the range 1990-to-2022. The myelin imaging methods specified were relaxometry, magnetization transfer, and quantitative susceptibility. Relaxometry was used most frequently, with myelin water fraction (MWF) being the primary metric. Studies conducted on tissue from various regions of the brain showed that MWF was significantly lower in pwMS than in healthy controls. Magnetization transfer ratio indicated that the macromolecular content of lesions was lower than that of normal-appearing tissue. Higher magnetic susceptibility of lesions were indicative of myelin breakdown and iron accumulation. Several myelin imaging metrics were correlated with disability, disease severity and duration. Many studies showed a good correlation between myelin measured histologically and by MR myelin imaging techniques.

A global bibliometric and visualized analysis of gait analysis and artificial intelligence research from 1992 to 2022

Gait is an important basic function of human beings and an integral part of life. Many mental and physical abnormalities can cause noticeable differences in a person's gait. Abnormal gait can lead to serious consequences such as falls, limited mobility and reduced life satisfaction. Gait analysis, which includes joint kinematics, kinetics, and dynamic Electromyography (EMG) data, is now recognized as a clinically useful tool that can provide both quantifiable and qualitative information on performance to aid in treatment planning and evaluate its outcome. With the assistance of new artificial intelligence (AI) technology, the traditional medical environment has undergone great changes. AI has the potential to reshape medicine, making gait analysis more accurate, efficient and accessible. In this study, we analyzed basic information about gait analysis and AI articles that met inclusion criteria in the WoS Core Collection database from 1992-2022, and the VosViewer software was used for web visualization and keyword analysis. Through bibliometric and visual analysis, this article systematically introduces the research status of gait analysis and AI. We introduce the application of artificial intelligence in clinical gait analysis, which affects the identification and management of gait abnormalities found in various diseases. Machine learning (ML) and artificial neural networks (ANNs) are the most often utilized AI methods in gait analysis. By comparing the predictive capability of different AI algorithms in published studies, we evaluate their potential for gait analysis in different situations. Furthermore, the current challenges and future directions of gait analysis and AI research are discussed, which will also provide valuable reference information for investors in this field.

A Deep Learning Approach for Automatic and Objective Grading of the Motor Impairment Severity in Parkinson's Disease for Use in Tele-Assessments

Wearable sensors provide a tool for at-home monitoring of motor impairment progression in neurological conditions such as Parkinson's disease (PD). This study examined the ability of deep learning approaches to grade the motor impairment severity in a modified version of the Movement Disorders Society-sponsored revision of the Unified Parkinson's Disease Rating Scale (MDS-UPDRS) using low-cost wearable sensors. We hypothesized that expanding training datasets with motion data from healthy older adults (HOAs) and initializing classifiers with weights learned from unsupervised pre-training would lead to an improvement in performance when classifying lower vs. higher motor impairment relative to a baseline deep learning model (XceptionTime). This study evaluated the change in classification performance after using expanded training datasets with HOAs and transferring weights from unsupervised pre-training compared to a baseline deep learning model (XceptionTime) using both upper extremity (finger tapping, hand movements, and pronation-supination movements of the hands) and lower extremity (toe tapping and leg agility) tasks consistent with the MDS-UPDRS. Overall, we found a 12.2% improvement in accuracy after expanding the training dataset and pre-training using max-vote inference on hand movement tasks. Moreover, we found that the classification performance improves for every task except toe tapping after the addition of HOA training data. These findings suggest that learning from HOA motion data can implicitly improve the representations of PD motion data for the purposes of motor impairment classification. Further, our results suggest that unsupervised pre-training can improve the performance of motor impairment classifiers without any additional annotated PD data, which may provide a viable solution for a widely deployable telemedicine solution.

Artificial Intelligence and Multiple Sclerosis: Up-to-Date Review

Multiple sclerosis (MS) remains a challenging neurological disorder for the clinician in terms of diagnosis and management. The growing integration of AI-based algorithms in healthcare offers a golden opportunity for clinicians and patients with MS. AI models are based on statistical analyses of large quantities of data from patients including "demographics, genetics, clinical and radiological presentation." These approaches are promising in the quest for greater diagnostic accuracy, tailored management plans, and better prognostication of disease. The use of AI in multiple sclerosis represents a paradigm shift in disease management. With ongoing advancements in AI technologies and the increasing availability of large-scale datasets, the potential for further innovation is immense. As AI continues to evolve, its integration into clinical practice will play a vital role in improving diagnostics, optimizing treatment strategies, and enhancing patient outcomes for MS. This review is about conducting a literature review to identify relevant studies on AI applications in MS. Only peer-reviewed studies published in the last four years have been selected. Data related to AI techniques, advancements, and implications are extracted. Through data analysis, key themes and tendencies are identified. The review presents a cohesive synthesis of the current state of AI and MS, highlighting potential implications and new advancements.

A Deep Learning Approach for Grading of Motor Impairment Severity in Parkinson's Disease

Objective and quantitative monitoring of movement impairments is crucial for detecting progression in neurological conditions such as Parkinson's disease (PD). This study examined the ability of deep learning approaches to grade motor impairment severity in a modified version of the Movement Disorders Society-sponsored revision of the Unified Parkinson's Disease Rating Scale (MDS-UPDRS) using low-cost wearable sensors. A convolutional neural network architecture, XceptionTime, was used to classify lower and higher levels of motor impairment in persons with PD, across five distinct rhythmic tasks: finger tapping, hand movements, pronation-supination movements of the hands, toe tapping, and leg agility. In addition, an aggregate model was trained on data from all tasks together for evaluating bradykinesia symptom severity in PD. The model performance was highest in the hand movement tasks with an accuracy of 82.6% in the hold-out test dataset; the accuracy for the aggregate model was 79.7%, however, it demonstrated the lowest variability. Overall, these findings suggest the feasibility of integrating low-cost wearable technology and deep learning approaches to automatically and objectively quantify motor impairment in persons with PD. This approach may provide a viable solution for a widely deployable telemedicine solution.

Deep Learning for Multiple Sclerosis Differentiation Using Multi-Stride Dynamics in Gait

OBJECTIVE

Multiple sclerosis (MS) is a chronic neurological condition of the central nervous system leading to various physical, mental and psychiatric complexities. Mobility limitations are amongst the most frequent and early markers of MS. We evaluated the effectiveness of a DeepMS2G (deep learning (DL) for MS differentiation using multistride dynamics in gait) framework, which is a DL-based methodology to classify multi-stride sequences of persons with MS (PwMS) from healthy controls (HC), in order to generalize over newer walking tasks and subjects.

METHODS

We collected single-task Walking and dual-task Walking-while-Talking gait data using an instrumented treadmill from a balanced collection of 20 HC and 20 PwMS. We utilized domain knowledge-based spatiotemporal and kinetic gait features along with two normalization schemes, namely standard size-based and multiple regression normalization strategies. To differentiate between multi-stride sequences of HC and PwMS, we compared 16 traditional machine learning and DL algorithms. Further, we studied the interpretability of our highest-performing models; and discussed the association between the lower extremity function of participants and our model predictions.

RESULTS

We observed that residual neural network (ResNet) based models with regression-based normalization were the top performers across both task and subject generalization classification designs. Considering regression-based normalization, a multi-scale ResNet attained a subject classification accuracy and F 1-score of 1.0 when generalizing from single-task Walking to dual-task Walking-while-Talking; and a ResNet resulted in the top subject-wise accuracy and F 1 of 0.83 and 0.81 (resp.), when generalizing over unseen participants.

CONCLUSION

We used advanced DL and dynamics across domain knowledge-based spatiotemporal and kinetic gait parameters to successfully classify MS gait across distinct walking trials and unseen participants.

SIGNIFICANCE

Our proposed DL algorithms might contribute to efforts to automate MS diagnoses.

Diagnostic performance of artificial intelligence in multiple sclerosis: a systematic review and meta-analysis

BACKGROUND

The expansion of the availability of advanced imaging methods needs more time, expertise, and resources which is in contrast to the primary goal of the imaging techniques. To overcome most of these difficulties, artificial intelligence (AI) can be used. A number of studies used AI models for multiple sclerosis (MS) diagnosis and reported diverse results. Therefore, we aim to perform a comprehensive systematic review and meta-analysis study on the role of AI in the diagnosis of MS.

METHODS

We performed a systematic search using four databases including PubMed, Scopus, Web of Science, and IEEE. Studies that applied deep learning or AI to the diagnosis of MS based on any modalities were considered eligible in our study. The accuracy, sensitivity, specificity, precision, and area under curve (AUC) were pooled with a random-effects model and 95% confidence interval (CI).

RESULTS

After the screening, 41 articles with 5989 individuals met the inclusion criteria and were included in our qualitative and quantitative synthesis. Our analysis showed that the overall accuracy among studies was 94% (95%CI: 93%, 96%). The pooled sensitivity and specificity were 92% (95%CI: 90%, 95%) and 93% (95%CI: 90%, 96%), respectively. Furthermore, our analysis showed 92% precision in MS diagnosis for AI studies (95%CI: 88%, 97%). Also, the overall pooled AUC was 93% (95%CI: 89%, 96%).

CONCLUSION

Overall, AI models can further improve our diagnostic practice in MS patients. Our results indicate that the use of AI can aid the clinicians in accurate diagnosis of MS and improve current diagnostic approaches as most of the parameters including accuracy, sensitivity, specificity, precision, and AUC were considerably high, especially when using MRI data.

Multiple Sclerosis Diagnosis Using Machine Learning and Deep Learning: Challenges and Opportunities

Multiple Sclerosis (MS) is a disease that impacts the central nervous system (CNS), which can lead to brain, spinal cord, and optic nerve problems. A total of 2.8 million are estimated to suffer from MS. Globally, a new case of MS is reported every five minutes. In this review, we discuss the proposed approaches to diagnosing MS using machine learning (ML) published between 2011 and 2022. Numerous models have been developed using different types of data, including magnetic resonance imaging (MRI) and clinical data. We identified the methods that achieved the best results in diagnosing MS. The most implemented approaches are SVM, RF, and CNN. Moreover, we discussed the challenges and opportunities in MS diagnosis to improve AI systems to enable researchers and practitioners to enhance their approaches and improve the automated diagnosis of MS. The challenges faced by automated MS diagnosis include difficulty distinguishing the disease from other diseases showing similar symptoms, protecting the confidentiality of the patients' data, achieving reliable ML models that are also easily understood by non-experts, and the difficulty of collecting a large reliable dataset. Moreover, we discussed several opportunities in the field such as the implementation of secure platforms, employing better AI solutions, developing better disease prognosis systems, combining more than one data type for better MS prediction and using OCT data for diagnosis, utilizing larger, multi-center datasets to improve the reliability of the developed models, and commercialization.

A Survey of Human Gait-Based Artificial Intelligence Applications

We performed an electronic database search of published works from 2012 to mid-2021 that focus on human gait studies and apply machine learning techniques. We identified six key applications of machine learning using gait data: 1) Gait analysis where analyzing techniques and certain biomechanical analysis factors are improved by utilizing artificial intelligence algorithms, 2) Health and Wellness, with applications in gait monitoring for abnormal gait detection, recognition of human activities, fall detection and sports performance, 3) Human Pose Tracking using one-person or multi-person tracking and localization systems such as OpenPose, Simultaneous Localization and Mapping (SLAM), etc., 4) Gait-based biometrics with applications in person identification, authentication, and re-identification as well as gender and age recognition 5) “Smart gait” applications ranging from smart socks, shoes, and other wearables to smart homes and smart retail stores that incorporate continuous monitoring and control systems and 6) Animation that reconstructs human motion utilizing gait data, simulation and machine learning techniques. Our goal is to provide a single broad-based survey of the applications of machine learning technology in gait analysis and identify future areas of potential study and growth. We discuss the machine learning techniques that have been used with a focus on the tasks they perform, the problems they attempt to solve, and the trade-offs they navigate.

Improved cortical activity and reduced gait asymmetry during poststroke self-paced walking rehabilitation

Background

For patients with gait impairment due to neurological disorders, body weight-supported treadmill training (BWSTT) has been widely used for gait rehabilitation. On a conventional (passive) treadmill that runs at a constant speed, however, the level of patient engagement and cortical activity decreased compared with gait training on the ground. To increase the level of cognitive engagement and brain activity during gait rehabilitation, a self-paced (active) treadmill is introduced to allow patients to actively control walking speed, as with overground walking.

Methods

To validate the effects of self-paced treadmill walking on cortical activities, this paper presents a clinical test with stroke survivors. We hypothesized that cortical activities on the affected side of the brain would also increase during active walking because patients have to match the target walking speed with the affected lower limbs. Thus, asymmetric gait patterns such as limping or hobbling might also decrease during active walking.

Results

Although the clinical test was conducted in a short period, the patients showed higher cognitive engagement, improved brain activities assessed by electroencephalography (EEG), and decreased gait asymmetry with the self-paced treadmill. As expected, increases in the spectral power of the low γ and β bands in the prefrontal cortex (PFC), premotor cortex (PMC), and supramarginal gyrus (SG) were found, which are possibly related to processing sensory data and planning voluntary movements. In addition, these changes in cortical activities were also found with the affected lower limbs during the swing phase. Since our treadmill controller tracked the swing speed of the leg to control walking speed, such results imply that subjects made substantial effort to control their affected legs in the swing phase to match the target walking speed.

Conclusions

The patients also showed reduced gait asymmetry patterns. Based on the results, the self-paced gait training system has the potential to train the symmetric gait and to promote the related cortical activities after stroke.

Trial registration Not applicable