Smartwatch Versus Routine Tremor Documentation: Descriptive Comparison.

We addressed the limitations of subjective clinical tremor assessment by comparing routine neurological evaluation with a Tremor Occurrence Score derived from smartwatch sensor data, among 142 participants with Parkinson disease and 77 healthy controls. Our findings highlight the potential of smartwatches for automated tremor detection as a valuable addition to conventional assessments, applicable in both clinical and home settings.

Machine Learning in the Parkinson's disease smartwatch (PADS) dataset.

The utilisation of smart devices, such as smartwatches and smartphones, in the field of movement disorders research has gained significant attention. However, the absence of a comprehensive dataset with movement data and clinical annotations, encompassing a wide range of movement disorders including Parkinson's disease (PD) and its differential diagnoses (DD), presents a significant gap. The availability of such a dataset is crucial for the development of reliable machine learning (ML) models on smart devices, enabling the detection of diseases and monitoring of treatment efficacy in a home-based setting. We conducted a three-year cross-sectional study at a large tertiary care hospital. A multi-modal smartphone app integrated electronic questionnaires and smartwatch measures during an interactive assessment designed by neurologists to provoke subtle changes in movement pathologies. We captured over 5000 clinical assessment steps from 504 participants, including PD, DD, and healthy controls (HC). After age-matching, an integrative ML approach combining classical signal processing and advanced deep learning techniques was implemented and cross-validated. The models achieved an average balanced accuracy of 91.16% in the classification PD vs. HC, while PD vs. DD scored 72.42%. The numbers suggest promising performance while distinguishing similar disorders remains challenging. The extensive annotations, including details on demographics, medical history, symptoms, and movement steps, provide a comprehensive database to ML techniques and encourage further investigations into phenotypical biomarkers related to movement disorders.

Classification of Parkinson's Disease from Voice - Analysis of Data Selection Bias.

A growing number of studies have been researching biomarkers of Parkinson's disease (PD) using mobile technology. Many have shown high accuracy in PD classification using machine learning (ML) and voice records from the mPower study, a large database of PD patients and healthy controls. Since the dataset has unbalanced class, gender and age distribution, it is important to consider appropriate sampling when assessing classification scores. We analyse biases, such as identity confounding and implicit learning of non-disease-specific characteristics and present a sampling strategy to highlight and prevent these problems.

Consistency of Feature Importance Algorithms for Interpretable EEG Abnormality Detection.

Recent advances in machine learning show great potential for automatic detection of abnormalities in electroencephalography (EEG). While simple and interpretable models combined with expert-comprehensible input features offer full control of the decision making process, these methods commonly lag behind complex deep learning and feature extraction methods in terms of performance. Here we study a feasibility of a bridging solution, where deep learning is combined with interpretable input and an algorithm computing the importance of particular EEG features in the decision process. We built a convolutional neural network with multi-channel EEG frequency bands as input and investigated four different methods for feature importance attribution: Layer-wise Relevance Propagation (LRP), DeepLIFT, Integrated Gradients (IG) and Guided GradCAM. Our analysis showed consistency between the first three methods, and deviating attributions of the fourth method, suggesting the importance of using a package of methods together to ensure the robustness of medical interpretation.

Utilizing a Non-Motor Symptoms Questionnaire and Machine Learning to Differentiate Movement Disorders.

Parkinson's disease (PD) is a common neurodegenerative disorder that severely impacts quality of life as the condition progresses. Early diagnosis and treatment is important to reduce burden and costs. Here, we evaluate the diagnostic potential of the Non-Motor symptoms (NMS) questionnaire by the International Parkinson and Movement Disorder Society based on patient-completed answers from a large single-center prospective study. In this study data from 489 study participants consisting of a PD group, a healthy control (HC) group and patients with differential diagnosis (DD) have been recorded with a smartphone-based system. Evaluation of the study data has shown a significant difference in NMS between the representative groups. Cross-validation of Machine Learning based classification achieves balanced accuracy scores of 88.7% in PD vs. HC, 72.1% in PD vs. DD and 82.6% when discriminating between all movement disorders (PD + DD) and the HC group. The results indicate potentially high feature importance of a simple self-administered questionnaire that could support early diagnosis.

Supporting AI-Explainability by Analyzing Feature Subsets in a Machine Learning Model.

Machine learning algorithms become increasingly prevalent in the field of medicine, as they offer the ability to recognize patterns in complex medical data. Especially in this sensitive area, the active usage of a mostly black box is a controversial topic. We aim to highlight how an aggregated and systematic feature analysis of such models can be beneficial in the medical context. For this reason, we introduce a grouped version of the permutation importance analysis for evaluating the influence of entire feature subsets in a machine learning model. In this way, expert-defined subgroups can be evaluated in the decision-making process. Based on these results, new hypotheses can be formulated and examined.

Prediction of Acute Kidney Injury in the Intensive Care Unit: Preliminary Findings in a European Open Access Database.

Acute kidney injury (AKI) is a common complication in critically ill patients and is associated with long-term complications and an increased mortality. This work presents preliminary findings from the first freely available European intensive care database released by Amsterdam UMC. A machine learning (ML) model was developed to predict AKI in the intensive care unit 12 hours before the actual event. Main features of the model included medications and hemodynamic parameters. Our models perform with an accuracy of 81.8% on moderate to severe AKI and 79.8% on all AKI patients. Those results can compete with models reported in the literature and introduce an ML model for AKI based on European patient data.

Relationships between correlated spikes, oxygen and LFP in the resting-state primate.

Resting-state functional MRI (rsfMRI) provides a view of human brain organization based on correlation patterns of blood oxygen level dependent (BOLD) signals recorded across the whole brain. The neural basis of resting-state BOLD fluctuations and their correlation remains poorly understood. We simultaneously recorded oxygen level, spikes, and local field potential (LFP) at multiple sites in awake, resting monkeys. Following a spike, the average local oxygen and LFP voltage responses each resemble a task-driven BOLD response, with LFP preceding oxygen by 0.5 s. Between sites, features of the long-range correlation patterns of oxygen, LFP, and spikes are similar to features seen in rsfMRI. Most of the variance shared between sites lies in the infraslow frequency band (0.01-0.1 Hz) and in the infraslow envelope of higher-frequency bands (e.g. gamma LFP). While gamma LFP and infraslow LFP are both strong correlates of local oxygen, infraslow LFP explains significantly more of the variance shared between correlated oxygen signals than any other electrophysiological signal. Together these findings are consistent with a causal relationship between infraslow LFP and long-range oxygen correlations in the resting state.

Towards Interpretable Machine Learning in EEG Analysis.

In this paper a machine learning model for automatic detection of abnormalities in electroencephalography (EEG) is dissected into parts, so that the influence of each part on the classification accuracy score can be examined. The most successful setup of several shallow artificial neural networks aggregated via voting results in accuracy of 81%. Stepwise simplification of the model shows the expected decrease in accuracy, but a naive model with thresholding of a single extracted feature (relative wavelet energy) is still able to achieve 75%, which remains strongly above the random guess baseline of 54%. These results suggest the feasibility of building a simple classification model ensuring accuracy scores close to the state-of-the-art research but remaining fully interpretable.

Tracking of Mental Workload with a Mobile EEG Sensor.

The aim of the present investigation was to assess if a mobile electroencephalography (EEG) setup can be used to track mental workload, which is an important aspect of learning performance and motivation and may thus represent a valuable source of information in the evaluation of cognitive training approaches. Twenty five healthy subjects performed a three-level N-back test using a fully mobile setup including tablet-based presentation of the task and EEG data collection with a self-mounted mobile EEG device at two assessment time points. A two-fold analysis approach was chosen including a standard analysis of variance and an artificial neural network to distinguish the levels of cognitive load. Our findings indicate that the setup is feasible for detecting changes in cognitive load, as reflected by alterations across lobes in different frequency bands. In particular, we observed a decrease of occipital alpha and an increase in frontal, parietal and occipital theta with increasing cognitive load. The most distinct levels of cognitive load could be discriminated by the integrated machine learning models with an accuracy of 86%.

Comparison of mobile and clinical EEG sensors through resting state simultaneous data collection.

Development of mobile sensors brings new opportunities to medical research. In particular, mobile electroencephalography (EEG) devices can be potentially used in low cost screening for epilepsy and other neurological and psychiatric disorders. The necessary condition for such applications is thoughtful validation in the specific medical context. As part of validation and quality assurance, we developed a computer-based analysis pipeline, which aims to compare the EEG signal acquired by a mobile EEG device to the one collected by a medically approved clinical-grade EEG device. Both signals are recorded simultaneously during 30 min long sessions in resting state. The data are collected from 22 patients with epileptiform abnormalities in EEG. In order to compare two multichannel EEG signals with differently placed references and electrodes, a novel data processing pipeline is proposed. It allows deriving matching pairs of time series which are suitable for similarity assessment through Pearson correlation. The average correlation of 0.64 is achieved on a test dataset, which can be considered a promising result, taking the positions shift due to the simultaneous electrode placement into account.

Automatic Recognition of Epileptiform EEG Abnormalities.

Long term EEG examinations, for example during epilepsy diagnosis, can be performed more efficiently with support of automated abnormality detection. Currently, these methods are usually developed based on one specific database, which limits the possibilities of generalizations. Here, we present a machine learning solution for detection of interictal abnormal EEG segments optimized on the publically available TUH Abnormal EEG Corpus. The classifier is further re-trained and tested on several combinations of publicly available data sets. The results achieved internally on the datasets are comparable to the known state of the art, while training and testing on different sources produced accuracy in the range of 67.51% to 99.50%. Lower accuracy is achieved when the training data set is highly preprocessed and relatively small.

Improved activation of lumbar multifidus following spinal manipulation: a case report applying rehabilitative ultrasound imaging.

STUDY DESIGN: Case report. BACKGROUND: The use of spinal manipulation as a treatment to facilitate neuromuscular control of the paraspinal musculature is not well described in the literature. The use of rehabilitative ultrasound imaging (RUSI) may offer a convenient way to investigate and document possible changes occurring in the lumbar multifidus associated with manipulation intervention. CASE DESCRIPTION: The patient was a 33-year-old male with a 21-year history of low back pain and left posterior thigh pain who presented with lumbar hypomobility and met a previously published clinical prediction rule for spinal manipulation. During examination, the patient was asked to perform a prone upper extremity lifting task to assess activation in the lumbar multifidus during an automatic task. Through palpation the examiner noted a decreased contraction of the left multifidus between L4-S1 compared to the right. To explore this further, a decision was made to assess the multifidus with RUSI, which confirmed the activation deficit noted during palpation. A lumbar regional manipulation was performed with the intention of reducing spinal hypomobility and of assessing changes in multifidus activation. Imaging of the multifidus muscles at the L4-5 and L5-S1 levels were obtained premanipulation, immediately postmanipulation, and 1 day after manipulation. OUTCOMES: An increased ability to thicken the multifidus during a prone upper extremity lifting task was noted immediately and 1 day after manipulation. Average percent change in thickness at the L4-5 and L5-S1 levels with the prone arm lift was 3.6% premanipulation, 17.2% immediately postmanipulation, and 20.6% approximately 24 hours postmanipulation. Improvements in the thickening of the multifidus muscle during the upper extremity lifting task were greater than 3 standard errors of the measurement. Other changes included immediate palpable improvement in the contraction of the multifidus during the upper extremity lifting task, along with the patient report of increased ease of lifting. DISCUSSION: In this case report we quantified the short-term influence of spinal manipulation on multifidus muscular activation using RUSI. No cause-and-effect claims can be made; however, the results provide preliminary evidence to suggest that spinal manipulation may influence multifidus muscle function. RUSI offers a convenient way to investigate and document these changes.

Use of lumbosacral region manipulation and therapeutic exercises for a patient with a lumbosacral transitional vertebra and low back pain.

STUDY DESIGN: Case report. BACKGROUND: A lumbosacral transitional vertebra (LTV) is a congenital anomaly that occurs in 3% to 21% of people with and without low back pain (LBP). There is lack of agreement in the literature as to whether or not the presence of a LTV may cause LBP. The objective of this case report is to present the use of lumbosacral region manipulation and therapeutic exercises on a patient with a known LTV and LBP. CASE DESCRIPTION: In this case report, an active-duty US Army soldier was referred to physical therapy with right-sided LBP and a lumbar radiograph showing a hemisacralized transitional L5 vertebra on the same side as his pain. The patient was treated with lumbosacral region manipulation and flexion exercises aimed at regaining total spinal motion and reducing pain. The patient responded favorably to spinal manipulation and exercise and was discharged from physical therapy after 4 visits. A modified Oswestry Low Back Pain Disability Questionnaire and inclinometer were used to measure outcome after physical therapy intervention. OUTCOMES: After a 2-week period of treatment in physical therapy, the patient improved from an initial Oswestry score of 32% to a score of 4%. Forward bending and left side bending improved from 74 degrees to 140 degrees and from 21 degrees to 45 degrees, respectively. DISCUSSION: Lumbosacral region manipulation along with therapeutic exercises appears to have been an effective treatment approach for this patient with LBP associated with a type IIA LTV.