Novel methods for elucidating modality importance in multimodal electrophysiology classifiers.

Introduction: Multimodal classification is increasingly common in electrophysiology studies. Many studies use deep learning classifiers with raw time-series data, which makes explainability difficult, and has resulted in relatively few studies applying explainability methods. This is concerning because explainability is vital to the development and implementation of clinical classifiers. As such, new multimodal explainability methods are needed. Methods: In this study, we train a convolutional neural network for automated sleep stage classification with electroencephalogram (EEG), electrooculogram, and electromyogram data. We then present a global explainability approach that is uniquely adapted for electrophysiology analysis and compare it to an existing approach. We present the first two local multimodal explainability approaches. We look for subject-level differences in the local explanations that are obscured by global methods and look for relationships between the explanations and clinical and demographic variables in a novel analysis. Results: We find a high level of agreement between methods. We find that EEG is globally the most important modality for most sleep stages and that subject-level differences in importance arise in local explanations that are not captured in global explanations. We further show that sex, followed by medication and age, had significant effects upon the patterns learned by the classifier. Discussion: Our novel methods enhance explainability for the growing field of multimodal electrophysiology classification, provide avenues for the advancement of personalized medicine, yield unique insights into the effects of demographic and clinical variables upon classifiers, and help pave the way for the implementation of multimodal electrophysiology clinical classifiers.

Explainable Sleep Stage Classification with Multimodal Electrophysiology Time-series.

Many automated sleep staging studies have used deep learning approaches, and a growing number of them have used multimodal data to improve their classification performance. However, few studies using multimodal data have provided model explainability. Some have used traditional ablation approaches that "zero out" a modality. However, the samples that result from this ablation are unlikely to be found in real electroencephalography (EEG) data, which could adversely affect the importance estimates that result. Here, we train a convolutional neural network for sleep stage classification with EEG, electrooculograms (EOG), and electromyograms (EMG) and propose an ablation approach that replaces each modality with values that approximate the line-related noise commonly found in electrophysiology data. The relative importance that we identify for each modality is consistent with sleep staging guidelines, with EEG being important for most sleep stages and EOG being important for Rapid Eye Movement (REM) and non-REM stages. EMG showed low relative importance across classes. A comparison of our approach with a "zero out" ablation approach indicates that while the importance results are consistent for the most part, our method accentuates the importance of modalities to the model for the classification of some stages like REM (p < 0.05). These results suggest that a careful, domain-specific selection of an ablation approach may provide a clearer indicator of modality importance. Further, this study provides guidance for future research on using explainability methods with multimodal electrophysiology data.Clinical Relevance- While explainability is helpful for clinical machine learning classifiers, it is important to consider how explainability methods interact with clinical data, a domain for which they were not originally designed.

Benefits of Blockchain Initiatives for Value-Based Care: Proposed Framework.

BACKGROUND: The potential of blockchain technology to achieve strategic goals, such as value-based care, is increasingly being recognized by both researchers and practitioners. However, current research and practices lack comprehensive approaches for evaluating the benefits of blockchain applications. OBJECTIVE: The goal of this study was to develop a framework for holistically assessing the performance of blockchain initiatives in providing value-based care by extending the existing balanced scorecard (BSC) evaluation framework. METHODS: Based on a review of the literature on value-based health care, blockchain technology, and methods for evaluating initiatives in disruptive technologies, we propose an extended BSC method for holistically evaluating blockchain applications in the provision of value-based health care. The proposed method extends the BSC framework, which has been extensively used to measure both financial and nonfinancial performance of organizations. The usefulness of our proposed framework is further demonstrated via a case study. RESULTS: We describe the extended BSC framework, which includes five perspectives (both financial and nonfinancial) from which to assess the appropriateness and performance of blockchain initiatives in the health care domain. CONCLUSIONS: The proposed framework moves us toward a holistic evaluation of both the financial and nonfinancial benefits of blockchain initiatives in the context of value-based care and its provision.