Motor evoked potentials for multiple sclerosis, a multiyear follow-up dataset.

Multiple sclerosis (MS) is a chronic disease affecting millions of people worldwide. Through the demyelinating and axonal pathology of MS, the signal conduction in the central nervous system is affected. Evoked potential measurements allow clinicians to monitor this process and can be used for decision support. We share a dataset that contains motor evoked potential (MEP) measurements, in which the brain is stimulated and the resulting signal is measured in the hands and feet. This results in time series of 100 milliseconds long. Typically, both hands and feet are measured in one hospital visit. The dataset contains 5586 visits of 963 patients, performed in day-to-day clinical care over a period of 6 years. The dataset consists of approximately 100,000 MEP. Clinical metadata such as the expanded disability status scale, sex, and age is also available. This dataset can be used to explore the role of evoked potentials in MS research and patient care. It may also be used as a benchmark for time series analysis and predictive modelling.

Longitudinal machine learning modeling of MS patient trajectories improves predictions of disability progression.

BACKGROUND AND OBJECTIVES: Research in Multiple Sclerosis (MS) has recently focused on extracting knowledge from real-world clinical data sources. This type of data is more abundant than data produced during clinical trials and potentially more informative about real-world clinical practice. However, this comes at the cost of less curated and controlled data sets. In this work we aim to predict disability progression by optimally extracting information from longitudinal patient data in the real-world setting, with a special focus on the sporadic sampling problem. METHODS: We use machine learning methods suited for patient trajectories modeling, such as recurrent neural networks and tensor factorization. A subset of 6682 patients from the MSBase registry is used. RESULTS: We can predict disability progression of patients in a two-year horizon with an ROC-AUC of 0.85, which represents a 32% decrease in the ranking pair error (1-AUC) compared to reference methods using static clinical features. CONCLUSIONS: Compared to the models available in the literature, this work uses the most complete patient history for MS disease progression prediction and represents a step forward towards AI-assisted precision medicine in MS.

Classification with a Deferral Option and Low-Trust Filtering for Automated Seizure Detection.

Wearable technology will become available and allow prolonged electroencephalography (EEG) monitoring in the home environment of patients with epilepsy. Neurologists analyse the EEG visually and annotate all seizures, which patients often under-report. Visual analysis of a 24-h EEG recording typically takes one to two hours. Reliable automated seizure detection algorithms will be crucial to reduce this analysis. We investigated such algorithms on a dataset of behind-the-ear EEG measurements. Our first aim was to develop a methodology where part of the data is deferred to a human expert, who performs perfectly, with the goal of obtaining an (almost) perfect detection sensitivity (DS). Prediction confidences are determined by temperature scaling of the classification model outputs and trust scores. A DS of approximately 90% (99%) can be achieved when deferring around 10% (40%) of the data. Perfect DS can be achieved when deferring 50% of the data. Our second contribution demonstrates that a common modelling strategy, where predictions from several short EEG segments are combined to obtain a final prediction, can be improved by filtering out untrustworthy segments with low trust scores. The false detection rate shows a relative decrease between 21% and 43%, and the DS shows a small increase or decrease.

Deciphering the Morphology of Motor Evoked Potentials.

Motor Evoked Potentials (MEPs) are used to monitor disability progression in multiple sclerosis (MS). Their morphology plays an important role in this process. Currently, however, there is no clear definition of what constitutes a normal or abnormal morphology. To address this, five experts independently labeled the morphology (normal or abnormal) of the same set of 1,000 MEPs. The intra- and inter-rater agreement between the experts indicates they agree on the concept of morphology, but differ in their choice of threshold between normal and abnormal morphology. We subsequently performed an automated extraction of 5,943 time series features from the MEPs to identify a valid proxy for morphology, based on the provided labels. To do this, we compared the cross-validation performances of one-dimensional logistic regression models fitted to each of the features individually. We find that the approximate entropy (ApEn) feature can accurately reproduce the majority-vote labels. The performance of this feature is evaluated on an independent test set by comparing to the majority vote of the neurologists, obtaining an AUC score of 0.92. The model slightly outperforms the average neurologist at reproducing the neurologists consensus-vote labels. We can conclude that MEP morphology can be consistently defined by pooling the interpretations from multiple neurologists and that ApEn is a valid continuous score for this. Having an objective and reproducible MEP morphological abnormality score will allow researchers to include this feature in their models, without manual annotation becoming a bottleneck. This is crucial for large-scale, multi-center datasets. An exploratory analysis on a large single-center dataset shows that ApEn is potentially clinically useful. Introducing an automated, objective, and reproducible definition of morphology could help overcome some of the barriers that are currently obstructing broad adoption of evoked potentials in daily care and patient follow-up, such as standardization of measurements between different centers, and formulating guidelines for clinical use.

Machine learning analysis of motor evoked potential time series to predict disability progression in multiple sclerosis.

BACKGROUND: Evoked potentials (EPs) are a measure of the conductivity of the central nervous system. They are used to monitor disease progression of multiple sclerosis patients. Previous studies only extracted a few variables from the EPs, which are often further condensed into a single variable: the EP score. We perform a machine learning analysis of motor EP that uses the whole time series, instead of a few variables, to predict disability progression after two years. Obtaining realistic performance estimates of this task has been difficult because of small data set sizes. We recently extracted a dataset of EPs from the Rehabiliation & MS Center in Overpelt, Belgium. Our data set is large enough to obtain, for the first time, a performance estimate on an independent test set containing different patients. METHODS: We extracted a large number of time series features from the motor EPs with the highly comparative time series analysis software package. Mutual information with the target and the Boruta method are used to find features which contain information not included in the features studied in the literature. We use random forests (RF) and logistic regression (LR) classifiers to predict disability progression after two years. Statistical significance of the performance increase when adding extra features is checked. RESULTS: Including extra time series features in motor EPs leads to a statistically significant improvement compared to using only the known features, although the effect is limited in magnitude (ΔAUC = 0.02 for RF and ΔAUC = 0.05 for LR). RF with extra time series features obtains the best performance (AUC = 0.75±0.07 (mean and standard deviation)), which is good considering the limited number of biomarkers in the model. RF (a nonlinear classifier) outperforms LR (a linear classifier). CONCLUSIONS: Using machine learning methods on EPs shows promising predictive performance. Using additional EP time series features beyond those already in use leads to a modest increase in performance. Larger datasets, preferably multi-center, are needed for further research. Given a large enough dataset, these models may be used to support clinicians in their decision making process regarding future treatment.