The clinical manifestations of Parkinson’s disease (PD) are characterized by heterogeneity in age at onset, disease duration, rate of progression, and the constellation of motor versus non-motor features. There is an unmet need for the characterization of distinct disease subtypes as well as improved, individualized predictions of the disease course. We used unsupervised and supervised machine learning methods on comprehensive, longitudinal clinical data from the Parkinson’s Disease Progression Marker Initiative (n = 294 cases) to identify patient subtypes and to predict disease progression. The resulting models were validated in an independent, clinically well-characterized cohort from the Parkinson’s Disease Biomarker Program (n = 263 cases). Our analysis distinguished three distinct disease subtypes with highly predictable progression rates, corresponding to slow, moderate, and fast disease progression. We achieved highly accurate projections of disease progression 5 years after initial diagnosis with an average area under the curve (AUC) of 0.92 (95% CI: 0.95 ± 0.01) for the slower progressing group (PDvec1), 0.87 ± 0.03 for moderate progressors, and 0.95 ± 0.02 for the fast-progressing group (PDvec3). We identified serum neurofilament light as a significant indicator of fast disease progression among other key biomarkers of interest. We replicated these findings in an independent cohort, released the analytical code, and developed models in an open science manner. Our data-driven study provides insights to deconstruct PD heterogeneity. This approach could have immediate implications for clinical trials by improving the detection of significant clinical outcomes. We anticipate that machine learning models will improve patient counseling, clinical trial design, and ultimately individualized patient care.

Objective: Multiple Sclerosis (MS) is one of the most common neurological conditions worldwide whose prevalence is now greatest among people 50-60 years of age. While clinical presentations of MS are highly heterogeneous, mobility limitations is one of the most frequent symptoms. The aims of this study were to examine MS and disability related changes in spatiotemporal and kinetic gait features after normalization; and evaluate the effectiveness of a gait data-based machine learning (ML) framework for MS prediction (GML4MS). Methods: In this study, gait data during self-paced walking on an instrumented treadmill from 20 persons with MS and 20 age, weight, height and gender-matched healthy older adults (HOA) were obtained. We explored two normalization strategies, namely size-N (standard body size-based normalization) and regress-N (regression-based normalization using scaling factors derived by regressing gait features on multiple subject demographics) to minimize the dependency of derived gait features on the subject demographics; and proposed GML4MS, a ML based methodology to classify individual strides of older persons with MS (PwMS) from healthy controls, so as to generalize across different walking tasks and subjects after gait normalization. Results: We observed that regress-N improved the accuracy of identifying pathological gait using ML when compared to size-N. When generalizing from comfortable walking to walking while talking, gradient boosting machine achieved the optimal subject classification accuracy and AUC of 94.3% and 1.0, respectively and for subject generalization, a multilayer perceptron resulted in the best accuracy and AUC of 80% and 0.86, respectively, both with regress-N normalized data. Conclusion:The integration of gait data and ML to predict MS may provide a viable patient-centric approach to aid clinicians in disease monitoring and relapse treatment. This work is the first attempt to employ and demonstrate the potential of ML for this domain. Significance: The results of this study have future implications for the way regression normalized gait features may be clinically used to design ML-based disease prediction strategies and monitor disease progression in PwMS.

No abstract

This study examined the effectiveness of a vision-based framework for multiple sclerosis (MS) and Parkinson's disease (PD) gait dysfunction prediction. We collected gait video data from multi-view digital cameras during self-paced walking from MS, PD patients and age, weight, height and gender-matched healthy older adults (HOA). We then extracted characteristic 3D joint keypoints from the collected videos. In this work, we proposed a data-driven methodology to classify strides in persons with MS (PwMS), persons with PD (PwPD) and HOA that may generalize across different walking tasks and subjects. We presented a comprehensive quantitative comparison of 16 diverse traditional machine and deep learning (DL) algorithms. When generalizing from comfortable walking (W) to walking-while-talking (WT), multi-scale residual neural network achieved perfect accuracy and AUC for classifying individuals with a given gait disorder; for subject generalization in W trials, residual neural network resulted in the highest accuracy and AUC of 78.1% and 0.87 (resp.), and 1D convolutional neural network (CNN) had highest accuracy of 75% in WT trials. Finally, when generalizing over new subjects in different tasks, again 1D CNN had the top classification accuracy and AUC of 79.3% and 0.93 (resp.). This work is the first attempt to apply and demonstrate the potential of DL with a multi-view digital camera-based gait analysis framework for neurological gait dysfunction prediction. This study suggests the viability of inexpensive vision-based systems for diagnosing certain neurological disorders.

America 2 15 4 Data used in preparation of this article were obtained from the Alzheimer's Disease 16 Neuroimaging Initiative (ADNI) database (adni.loni.usc.edu). As such, the investigators within the 17 ADNI contributed to the design and implementation of ADNI and/or provided data but did not 18 participate in analysis or writing of this report. A complete listing of ADNI investigators can be Abstract 33 Background 34 Alzheimer's disease (AD) is a common, age-related, neurodegenerative disease that impairs a 35 person's ability to perform day to day activities. Diagnosing AD is difficult, especially in the early 36 stages, many individuals go undiagnosed partly due to the complex heterogeneity in disease 37 progression. This highlights a need for early prediction of the disease course to assist its treatment 38 and tailor therapy options to the disease progression rate. Recent developments in machine 39 learning techniques provide the potential to not only predict disease progression and trajectory of 40 AD but also to classify the disease into different etiological subtypes. 41Methods and findings 42 The suggested work clusters participants in distinct and multifaceted progression subgroups of AD 43 and discusses an approach to predict the progression stage from baseline diagnosis. We observe 44 that the myriad of clinically reported symptoms summarized in the proposed AD progression space 45 corresponds directly to memory and cognitive measures, classically been used to monitor disease 46 onset and progression. The proposed work concludes notably accurate prediction of disease 47 progression after four years from the first 12 months of post-diagnosis clinical data (Area Under 48 the Curve of 0.92 (95% confidence interval (CI), 0.90-0.94), 0.96 (95% CI, 0.92-1.0), 0.90 (95% 49 CI, 0.86-0.94) and 0.83 (95% CI, 0.77-0.89) for controls, high, moderate and low progression rate 4 50 patients respectively). Further, we explore the long short-term memory (LSTM) neural networks 51 to predict the trajectory of a patient's progression. 52 Conclusion 53The machine learning techniques presented in this study may assist providers with identifying 54 different progression rates and trajectories in the early stages of disease progression, hence 55 allowing for more efficient and unique care deliveries. With additional information about the 56 progression rate of AD at hand, providers may further individualize the treatment plans. The 57 predictive tests discussed in this study not only allow for early AD diagnosis but also facilitate the 58 characterization of distinct AD subtypes relating to trajectories of disease progression. These 59 findings are a crucial step forward to early disease detection. Additionally, models can be used to 60 design improved clinical trials for AD research.61 Introduction 62 Alzheimer's disease (AD) is a progressive and age-associated, chronic neurodegenerative disease 63 affecting a patient's memory, intellectual skills, and other mental functions. It is the most common 64 form of...