Explore the vast range of titles available.

Deep neural networks (DNNs) used for brain–computer interface (BCI) classification are commonly expected to learn general features when trained across a variety of contexts, such that these features could be fine-tuned to specific contexts. While some success is found in such an approach, we suggest that this interpretation is limited and an alternative would better leverage the newly (publicly) available massive electroencephalography (EEG) datasets. We consider how to adapt techniques and architectures used for language modeling (LM) that appear capable of ingesting awesome amounts of data toward the development of encephalography modeling with DNNs in the same vein. We specifically adapt an approach effectively used for automatic speech recognition, which similarly (to LMs) uses a self-supervised training objective to learn compressed representations of raw data signals. After adaptation to EEG, we find that a single pre-trained model is capable of modeling completely novel raw EEG sequences recorded with differing hardware, and different subjects performing different tasks. Furthermore, both the internal representations of this model and the entire architecture can be fine-tuned to a variety of downstream BCI and EEG classification tasks, outperforming prior work in more task-specific (sleep stage classification) self-supervision.

Introduction: Research related to the automatic detection of Alzheimer's disease (AD) is important, given the high prevalence of AD and the high cost of traditional diagnostic methods. Since AD significantly affects the content and acoustics of spontaneous speech, natural language processing, and machine learning provide promising techniques for reliably detecting AD. There has been a recent proliferation of classification models for AD, but these vary in the datasets used, model types and training and testing paradigms. In this study, we compare and contrast the performance of two common approaches for automatic AD detection from speech on the same, well-matched dataset, to determine the advantages of using domain knowledge vs. pre-trained transfer models. Methods: Audio recordings and corresponding manually-transcribed speech transcripts of a picture description task administered to 156 demographically matched older adults, 78 with Alzheimer's Disease (AD) and 78 cognitively intact (healthy) were classified using machine learning and natural language processing as “AD” or “non-AD.” The audio was acoustically-enhanced, and post-processed to improve quality of the speech recording as well control for variation caused by recording conditions. Two approaches were used for classification of these speech samples: (1) using domain knowledge: extracting an extensive set of clinically relevant linguistic and acoustic features derived from speech and transcripts based on prior literature, and (2) using transfer-learning and leveraging large pre-trained machine learning models: using transcript-representations that are automatically derived from state-of-the-art pre-trained language models, by fine-tuning Bidirectional Encoder Representations from Transformer (BERT)-based sequence classification models. Results: We compared the utility of speech transcript representations obtained from recent natural language processing models (i.e., BERT) to more clinically-interpretable language feature-based methods. Both the feature-based approaches and fine-tuned BERT models significantly outperformed the baseline linguistic model using a small set of linguistic features, demonstrating the importance of extensive linguistic information for detecting cognitive impairments relating to AD. We observed that fine-tuned BERT models numerically outperformed feature-based approaches on the AD detection task, but the difference was not statistically significant. Our main contribution is the observation that when tested on the same, demographically balanced dataset and tested on independent, unseen data, both domain knowledge and pretrained linguistic models have good predictive performance for detecting AD based on speech. It is notable that linguistic information alone is capable of achieving comparable, and even numerically better, performance than models including both acoustic and linguistic features here. We also try to shed light on the inner workings of the more black-box natural language processing model by performing an interpretability analysis, and find that attention weights reveal interesting patterns such as higher attribution to more important information content units in the picture description task, as well as pauses and filler words. Conclusion: This approach supports the value of well-performing machine learning and linguistically-focussed processing techniques to detect AD from speech and highlights the need to compare model performance on carefully balanced datasets, using consistent same training parameters and independent test datasets in order to determine the best performing predictive model.

When evaluating surgeons in the operating room, experienced physicians must rely on live or recorded video to assess the surgeon's technical performance, an approach prone to subjectivity and error. Owing to the large number of surgical procedures performed daily, it is infeasible to review every procedure; therefore, there is a tremendous loss of invaluable performance data that would otherwise be useful for improving surgical safety. To evaluate a framework for assessing surgical video clips by categorizing them based on the surgical step being performed and the level of the surgeon's competence. This quality improvement study assessed 103 video clips of 8 surgeons of various levels performing knot tying, suturing, and needle passing from the Johns Hopkins University-Intuitive Surgical Gesture and Skill Assessment Working Set. Data were collected before 2015, and data analysis took place from March to July 2019. Deep learning models were trained to estimate categorical outputs such as performance level (ie, novice, intermediate, and expert) and surgical actions (ie, knot tying, suturing, and needle passing). The efficacy of these models was measured using precision, recall, and model accuracy. The provided architectures achieved accuracy in surgical action and performance calculation tasks using only video input. The embedding representation had a mean (root mean square error [RMSE]) precision of 1.00 (0) for suturing, 0.99 (0.01) for knot tying, and 0.91 (0.11) for needle passing, resulting in a mean (RMSE) precision of 0.97 (0.01). Its mean (RMSE) recall was 0.94 (0.08) for suturing, 1.00 (0) for knot tying, and 0.99 (0.01) for needle passing, resulting in a mean (RMSE) recall of 0.98 (0.01). It also estimated scores on the Objected Structured Assessment of Technical Skill Global Rating Scale categories, with a mean (RMSE) precision of 0.85 (0.09) for novice level, 0.67 (0.07) for intermediate level, and 0.79 (0.12) for expert level, resulting in a mean (RMSE) precision of 0.77 (0.04). Its mean (RMSE) recall was 0.85 (0.05) for novice level, 0.69 (0.14) for intermediate level, and 0.80 (0.13) for expert level, resulting in a mean (RMSE) recall of 0.78 (0.03). The proposed models and the accompanying results illustrate that deep machine learning can identify associations in surgical video clips. These are the first steps to creating a feedback mechanism for surgeons that would allow them to learn from their experiences and refine their skills.

Speech represents a promising novel biomarker by providing a window into brain health, as shown by its disruption in various neurological and psychiatric diseases. As with many novel digital biomarkers, however, rigorous evaluation is currently lacking and is required for these measures to be used effectively and safely. This paper outlines and provides examples from the literature of evaluation steps for speech-based digital biomarkers, based on the recent V3 framework (Goldsack et al., 2020). The V3 framework describes 3 components of evaluation for digital biomarkers: verification, analytical validation, and clinical validation. Verification includes assessing the quality of speech recordings and comparing the effects of hardware and recording conditions on the integrity of the recordings. Analytical validation includes checking the accuracy and reliability of data processing and computed measures, including understanding test-retest reliability, demographic variability, and comparing measures to reference standards. Clinical validity involves verifying the correspondence of a measure to clinical outcomes which can include diagnosis, disease progression, or response to treatment. For each of these sections, we provide recommendations for the types of evaluation necessary for speech-based biomarkers and review published examples. The examples in this paper focus on speech-based biomarkers, but they can be used as a template for digital biomarker development more generally.

We consider whether a deep neural network trained with raw MEG data can be used to predict the age of children performing a verb-generation task, a monosyllable speech-elicitation task, and a multi-syllabic speech-elicitation task. Furthermore, we argue that the network makes predictions on the grounds of differences in speech development. Previous work has explored taking ‘deep’ neural networks (DNNs) designed for, or trained with, images to classify encephalographic recordings with some success, but this does little to acknowledge the structure of these data. Simple neural networks have been used extensively to classify data expressed as features, but require extensive feature engineering and pre-processing. We present novel DNNs trained using raw magnetoencephalography (MEG) and electroencephalography (EEG) recordings that mimic the feature-engineering pipeline. We highlight criteria the networks use, including relative weighting of channels and preferred spectro-temporal characteristics of re-weighted channels. Our data feature 92 subjects aged 4–18, recorded using a 151-channel MEG system. Our proposed model scores over 95% mean cross-validation accuracy distinguishing above and below 10 years of age in single trials of un-seen subjects, and can classify publicly available EEG with state-of-the-art accuracy.

Currently, in Canada, existing health administrative data and hospital-inputted portal systems are used to measure the wait times to receiving a procedure or therapy after a specialist visit. However, due to missing and inconsistent labelling, estimating the wait time prior to seeing a specialist physician requires costly manual coding to label primary care referral notes. In this work, we represent the notes using word-count vectors and develop a logistic regression machine learning model to automatically label the target specialist physician from a primary care referral note. These labels are not available in the administrative system. We also study the effects of note length (measured in number of tokens) and dataset size (measured in number of notes per target specialty) on model performance to help other researchers determine if such an approach may be feasible for them. We then calculate the wait time by linking the specialist type from a primary care referral to a full consultation visit held in Ontario, Canada health administrative data. For many target specialties, we can reliably (F1Score ≥ 0.70) predict the target specialist type. Doing so enables the automated measurement of wait time from family physician referral to specialist physician visit. Of the six specialties with wait times estimated using both 2008 and 2015 data, two had a substantial increase (defined as a change such that the original value lay outside the 95% confidence interval) in both median and 75th percentile wait times, one had a substantial decrease in both median and 75th percentile wait times, and three has non-substantial increases. Automating these wait time measurements, which had previously been too time consuming and costly to evaluate at a population level, can be useful for health policy researchers studying the effects of policy decisions on patient access to care.

BackgroundPatients with essential tremor (ET), Parkinson’s disease (PD) and dystonic tremor (DT) can be difficult to classify and often share similar characteristics.ObjectivesTo use ubiquitous smartphone accelerometers with and without clinical features to automate tremor classification using supervised machine learning, and to use unsupervised learning to evaluate if natural clusterings of patients correspond to assigned clinical diagnoses.MethodsA supervised machine learning classifier was trained to classify 78 tremor patients using leave-one-out cross-validation to estimate performance on unseen accelerometer data. An independent cohort of 27 patients were also studied. Next, we focused on a subset of 48 patients with both smartphone-based tremor measurements and detailed clinical assessment metrics and compared two separate machine learning classifiers trained on these data.ResultsThe classifier yielded a total accuracy of 74.4% and F1-score of 0.74 for a trinary classification with an area under the curve of 0.904, average F1-score of 0.94, specificity of 97% and sensitivity of 84% in classifying PD from ET or DT. The algorithm classified ET from non-ET with 88% accuracy, but only classified DT from non-DT with 29% accuracy. A poorer performance was found in the independent cohort. Classifiers trained on accelerometer and clinical data respectively obtained similar results.ConclusionsMachine learning classifiers achieved a high accuracy of PD, however moderate accuracy of ET, and poor accuracy of DT classification. This underscores the difficulty of using AI to classify some tremors due to lack of specificity in clinical and neuropathological features, reinforcing that they may represent overlapping syndromes.

National governments worldwide have implemented nonpharmaceutical interventions to control the COVID-19 pandemic and mitigate its effects. The aim of this study was to investigate the prediction of future daily national confirmed COVID-19 infection growth-the percentage change in total cumulative cases-across 14 days for 114 countries using nonpharmaceutical intervention metrics and cultural dimension metrics, which are indicative of specific national sociocultural norms. We combined the Oxford COVID-19 Government Response Tracker data set, Hofstede cultural dimensions, and daily reported COVID-19 infection case numbers to train and evaluate five non-time series machine learning models in predicting confirmed infection growth. We used three validation methods-in-distribution, out-of-distribution, and country-based cross-validation-for the evaluation, each of which was applicable to a different use case of the models. Our results demonstrate high R values between the labels and predictions for the in-distribution method (0.959) and moderate R values for the out-of-distribution and country-based cross-validation methods (0.513 and 0.574, respectively) using random forest and adaptive boosting (AdaBoost) regression. Although these models may be used to predict confirmed infection growth, the differing accuracies obtained from the three tasks suggest a strong influence of the use case. This work provides new considerations in using machine learning techniques with nonpharmaceutical interventions and cultural dimensions as metrics to predict the national growth of confirmed COVID-19 infections.

Background A verbal autopsy (VA) is a post-hoc written interview report of the symptoms preceding a person’s death in cases where no official cause of death (CoD) was determined by a physician. Current leading automated VA coding methods primarily use structured data from VAs to assign a CoD category. We present a method to automatically determine CoD categories from VA free-text narratives alone. Methods After preprocessing and spelling correction, our method extracts word frequency counts from the narratives and uses them as input to four different machine learning classifiers: naïve Bayes, random forest, support vector machines, and a neural network. Results For individual CoD classification, our best classifier achieves a sensitivity of.770 for adult deaths for 15 CoD categories (as compared to the current best reported sensitivity of.57), and.662 with 48 WHO categories. When predicting the CoD distribution at the population level, our best classifier achieves.962 cause-specific mortality fraction accuracy for 15 categories and.908 for 48 categories, which is on par with leading CoD distribution estimation methods. Conclusions Our narrative-based machine learning classifier performs as well as classifiers based on structured data at the individual level. Moreover, our method demonstrates that VA narratives provide important information that can be used by a machine learning system for automated CoD classification. Unlike the structured questionnaire-based methods, this method can be applied to any verbal autopsy dataset, regardless of the collection process or country of origin.

Language is one the earliest capacities affected by cognitive change. To monitor that change longitudinally, we have developed a web portal for remote linguistic data acquisition, called Talk2Me, consisting of a variety of tasks. In order to facilitate research in different aspects of language, we provide baselines including the relations between different scoring functions within and across tasks. These data can be used to augment studies that require a normative model; for example, we provide baseline classification results in identifying dementia. These data are released publicly along with a comprehensive open-source package for extracting approximately two thousand lexico-syntactic, acoustic, and semantic features. This package can be applied arbitrarily to studies that include linguistic data. To our knowledge, this is the most comprehensive publicly available software for extracting linguistic features. The software includes scoring functions for different tasks.