Machine Learning Methods Predict Individual Upper-Limb Motor Impairment Following Therapy in Chronic Stroke.

Background. Accurate prediction of clinical impairment in upper-extremity motor function following therapy in chronic stroke patients is a difficult task for clinicians but is key in prescribing appropriate therapeutic strategies. Machine learning is a highly promising avenue with which to improve prediction accuracy in clinical practice. Objectives. The objective was to evaluate the performance of 5 machine learning methods in predicting postintervention upper-extremity motor impairment in chronic stroke patients using demographic, clinical, neurophysiological, and imaging input variables. Methods. A total of 102 patients (female: 31%, age 61 ± 11 years) were included. The upper-extremity Fugl-Meyer Assessment (UE-FMA) was used to assess motor impairment of the upper limb before and after intervention. Elastic net (EN), support vector machines, artificial neural networks, classification and regression trees, and random forest were used to predict postintervention UE-FMA. The performances of methods were compared using cross-validated R2. Results. EN performed significantly better than other methods in predicting postintervention UE-FMA using demographic and baseline clinical data (median REN2=0.91,RRF2=0.88,RANN2=0.83,RSVM2=0.79,RCART2=0.70;P < .05). Preintervention UE-FMA and the difference in motor threshold (MT) between the affected and unaffected hemispheres were the strongest predictors. The difference in MT had greater importance than the absence or presence of a motor-evoked potential (MEP) in the affected hemisphere. Conclusion. Machine learning methods may enable clinicians to accurately predict a chronic stroke patient's postintervention UE-FMA. Interhemispheric difference in the MT is an important predictor of chronic stroke patients' response to therapy and, therefore, could be included in prospective studies.

NeuroMeasure: A Software Package for Quantification of Cortical Motor Maps Using Frameless Stereotaxic Transcranial Magnetic Stimulation.

The recent enhanced sophistication of non-invasive mapping of the human motor cortex using MRI-guided Transcranial Magnetic Stimulation (TMS) techniques, has not been matched by refinement of methods for generating maps from motor evoked potential (MEP) data, or in quantifying map features. This is despite continued interest in understanding cortical reorganization for natural adaptive processes such as skill learning, or in the case of motor recovery, such as after lesion affecting the corticospinal system. With the observation that TMS-MEP map calculation and quantification methods vary, and that no readily available commercial or free software exists, we sought to establish and make freely available a comprehensive software package that advances existing methods, and could be helpful to scientists and clinician-researchers. Therefore, we developed NeuroMeasure, an open source interactive software application for the analysis of TMS motor cortex mapping data collected from Nexstim® and BrainSight®, two commonly used neuronavigation platforms. NeuroMeasure features four key innovations designed to improve motor mapping analysis: de-dimensionalization of the mapping data, fitting a predictive model, reporting measurements to characterize the motor map, and comparing those measurements between datasets. This software provides a powerful and easy to use workflow for characterizing and comparing motor maps generated with neuronavigated TMS. The software can be downloaded on our github page: https://github.com/EdwardsLabNeuroSci/NeuroMeasure. AIM: This paper aims to describe a software platform for quantifying and comparing maps of the human primary motor cortex, using neuronavigated transcranial magnetic stimulation, for the purpose of studying brain plasticity in health and disease.

Using Data From the Microsoft Kinect 2 to Quantify Upper Limb Behavior: A Feasibility Study.

The objective of this study was to assess whether the novel application of a machine learning approach to data collected from the Microsoft Kinect 2 (MK2) could be used to classify differing levels of upper limb impairment. Twenty-four healthy subjects completed items of the Wolf Motor Function Test (WMFT), which is a clinically validated metric of upper limb function for stroke survivors. Subjects completed the WMFT three times: 1) as a healthy individual; 2) emulating mild impairment; and 3) emulating moderate impairment. A MK2 was positioned in front of participants, and collected kinematic data as they completed the WMFT. A classification framework, based on Riemannian geometry and the use of covariance matrices as feature representation of the MK2 data, was developed for these data, and its ability to successfully classify subjects as either "healthy," "mildly impaired," or "moderately impaired" was assessed. Mean accuracy for our classifier was 91.7%, with a specific accuracy breakdown of 100%, 83.3%, and 91.7% for the "healthy," "mildly impaired," and "moderately impaired" conditions, respectively. We conclude that data from the MK2 is of sufficient quality to perform objective motor behavior classification in individuals with upper limb impairment. The data collection and analysis framework that we have developed has the potential to disrupt the field of clinical assessment. Future studies will focus on validating this protocol on large populations of individuals with actual upper limb impairments in order to create a toolkit that is clinically validated and available to the clinical community.

A Framework for Combining rTMS with Behavioral Therapy.

Upon its inception, repetitive transcranial magnetic stimulation (rTMS) was delivered at rest, without regard to the potential impact of activity occurring during or around the time of stimulation. rTMS was considered an experimental intervention imposed on the brain; therefore, the myriad features that might suppress or enhance its desired effects had not yet been explored. The field of rTMS has since grown substantially and therapeutic benefits have been reported, albeit with modest and inconsistent improvements. Work in this field accelerated following approval of a psychiatric application (depression), and it is now expanding to other applications and disciplines. In the last decade, experimental enquiry has sought new ways to improve the therapeutic benefits of rTMS, intended to enhance underlying brain reorganization and functional recovery by combining it with behavioral therapy. This concept is appealing, but poorly defined and requires clarity. We provide an overview of how combined rTMS and behavioral therapy has been delineated in the literature, highlighting the diversity of approaches. We outline a framework for study design and reporting such that the effects of this emerging method can be better understood.