SleepTransformer: Automatic Sleep Staging with Interpretability and Uncertainty Quantification

Black-box skepticism is one of the main hindrances impeding deep-learning-based automatic sleep scoring from being used in clinical environments. Towards interpretability, this work proposes a sequence-to-sequence sleep-staging model, namely SleepTransformer. It is based on the transformer backbone whose self-attention scores offer interpretability of the model's decisions at both the epoch and sequence level. At the epoch level, the attention scores can be encoded as a heat map to highlight sleep-relevant features captured from the input EEG signal. At the sequence level, the attention scores are visualized as the influence of different neighboring epochs in an input sequence (i.e. the context) to recognition of a target epoch, mimicking the way manual scoring is done by human experts. We further propose a simple yet efficient method to quantify uncertainty in the model's decisions. The method, which is based on entropy, can serve as a metric for deferring low-confidence epochs to a human expert for further inspection. Additionally, we demonstrate that the proposed SleepTransformer outperforms existing methods at a lower computational cost and achieves state-of-the-art performance on two experimental databases of different sizes.

Interpretable Deep Learning for the Remote Characterisation of Ambulation in Multiple Sclerosis using Smartphones

The emergence of digital technologies such as smartphones in healthcare applications have demonstrated the possibility of developing rich, continuous, and objective measures of multiple sclerosis (MS) disability that can be administered remotely and out-of-clinic. In this work, deep convolutional neural networks (DCNN) applied to smartphone inertial sensor data were shown to better distinguish healthy from MS participant ambulation, compared to standard Support Vector Machine (SVM) feature-based methodologies. To overcome the typical limitations associated with remotely generated health data, such as low subject numbers, sparsity, and heterogeneous data, a transfer learning (TL) model from similar large open-source datasets was proposed. Our TL framework utilised the ambulatory information learned on Human Activity Recognition (HAR) tasks collected from similar smartphone-based sensor data. A lack of transparency of "black-box" deep networks remains one of the largest stumbling blocks to the wider acceptance of deep learning for clinical applications. Ensuing work therefore aimed to visualise DCNN decisions attributed by relevance heatmaps using Layer-Wise Relevance Propagation (LRP). Through the LRP framework, the patterns captured from smartphone-based inertial sensor data that were reflective of those who are healthy versus persons with MS (PwMS) could begin to be established and understood. Interpretations suggested that cadence-based measures, gait speed, and ambulation-related signal perturbations were distinct characteristics that distinguished MS disability from healthy participants. Robust and interpretable outcomes, generated from high-frequency out-of-clinic assessments, could greatly augment the current in-clinic assessment picture for PwMS, to inform better disease management techniques, and enable the development of better therapeutic interventions.

Estimation of Continuous Blood Pressure from PPG via a Federated Learning Approach

Ischemic heart disease is the highest cause of mortality globally each year. This not only puts a massive strain on the lives of those affected but also on the public healthcare systems. To understand the dynamics of the healthy and unhealthy heart doctors commonly use electrocardiogram (ECG) and blood pressure (BP) readings. These methods are often quite invasive, in particular when continuous arterial blood pressure (ABP) readings are taken and not to mention very costly. Using machine learning methods we seek to develop a framework that is capable of inferring ABP from a single optical photoplethysmogram (PPG) sensor alone. We train our framework across distributed models and data sources to mimic a large-scale distributed collaborative learning experiment that could be implemented across low-cost wearables. Our time series-to-time series generative adversarial network (T2TGAN) is capable of high-quality continuous ABP generation from a PPG signal with a mean error of 2.54 mmHg and a standard deviation of 23.7 mmHg when estimating mean arterial pressure on a previously unseen, noisy, independent dataset. To our knowledge, this framework is the first example of a GAN capable of continuous ABP generation from an input PPG signal that also uses a federated learning methodology.

Change Point Detection in Time Series Data using Autoencoders with a Time-Invariant Representation

Change point detection (CPD) aims to locate abrupt property changes in time series data. Recent CPD methods demonstrated the potential of using deep learning techniques, but often lack the ability to identify more subtle changes in the autocorrelation statistics of the signal and suffer from a high false alarm rate. To address these issues, we employ an autoencoder-based methodology with a novel loss function, through which the used autoencoders learn a partially time-invariant representation that is tailored for CPD. The result is a flexible method that allows the user to indicate whether change points should be sought in the time domain, frequency domain or both. Detectable change points include abrupt changes in the slope, mean, variance, autocorrelation function and frequency spectrum. We demonstrate that our proposed method is consistently highly competitive or superior to baseline methods on diverse simulated and real-life benchmark data sets. Finally, we mitigate the issue of false detection alarms through the use of a postprocessing procedure that combines a matched filter and a newly proposed change point score. We show that this combination drastically improves the performance of our method as well as all baseline methods.

XSleepNet: Multi-View Sequential Model for Automatic Sleep Staging

Automating sleep staging is vital to scale up sleep assessment and diagnosis to millions of people experiencing sleep deprivation and disorders and to enable longitudinal sleep monitoring in home environments. Learning from raw polysomnography signals and their derived time-frequency images has been prevalent. However, learning from multi-view inputs (e.g. both the raw signals and the time-frequency images) for sleep staging is difficult and not well understood. This work proposes a sequence-to-sequence sleep staging model, XSleepNet, that is capable of learning a joint representation from both raw signals and time-frequency images effectively. Since different views often generalize (and overfit) at different rates, the proposed network is trained in such a way that the learning pace on each view is adapted based on their generalization/overfitting behavior. In simple terms, the learning on a particular view is speeded up when it is generalizing well and slowed down when it is overfitting. View-specific generalization/overfitting measures are computed on-the-fly during the training course and used to derive weights to blend the gradients from different views. As a result, the network is able to retain representation power of different views in the joint features which represent the underlying distribution better than those learned by each individual view alone. Furthermore, the XSleepNet architecture is principally designed to gain robustness to the amount of training data and to increase the complementarity between the input views. Experimental results on five databases of different size show that XSleepNet consistently results in better performance than the single-view baselines as well as the multi-view baseline with a simple fusion strategy. Finally, XSleepNet outperforms all prior sleep staging methods and sets new state-of-the-art results on the experimental databases.

Personalized Automatic Sleep Staging with Single-Night Data: a Pilot Study with KL-Divergence Regularization

Brain waves vary between people. An obvious way to improve automatic sleep staging for longitudinal sleep monitoring is personalization of algorithms based on individual characteristics extracted from the first night of data. As a single night is a very small amount of data to train a sleep staging model, we propose a Kullback-Leibler (KL) divergence regularized transfer learning approach to address this problem. We employ the pretrained SeqSleepNet (i.e. the subject independent model) as a starting point and finetune it with the single-night personalization data to derive the personalized model. This is done by adding the KL divergence between the output of the subject independent model and the output of the personalized model to the loss function during finetuning. In effect, KL-divergence regularization prevents the personalized model from overfitting to the single-night data and straying too far away from the subject independent model. Experimental results on the Sleep-EDF Expanded database with 75 subjects show that sleep staging personalization with a single-night data is possible with help of the proposed KL-divergence regularization. On average, we achieve a personalized sleep staging accuracy of 79.6%, a Cohen's kappa of 0.706, a macro F1-score of 73.0%, a sensitivity of 71.8%, and a specificity of 94.2%. We find both that the approach is robust against overfitting and that it improves the accuracy by 4.5 percentage points compared to non-personalization and 2.2 percentage points compared to personalization without regularization.

Improving GANs for Speech Enhancement

Generative adversarial networks (GAN) have recently been shown to be efficient for speech enhancement. Most, if not all, existing speech enhancement GANs (SEGANs) make use of a single generator to perform one-stage enhancement mapping. In this work, we propose two novel SEGAN frameworks, iterated SEGAN (ISEGAN) and deep SEGAN (DSEGAN). In the two proposed frameworks, the GAN architectures are composed of multiple generators that are chained to accomplish multiple-stage enhancement mapping which gradually refines the noisy input signals in stage-wise fashion. On the one hand, ISEGAN's generators share their parameters to learn an iterative enhancement mapping. On the other hand, DSEGAN's generators share a common architecture but their parameters are independent; as a result, different enhancement mappings are learned at different stages of the network. We empirically demonstrate favorable results obtained by the proposed ISEGAN and DSEGAN frameworks over the vanilla SEGAN. The source code is available at http://github.com/pquochuy/idsegan.

Towards More Accurate Automatic Sleep Staging via Deep Transfer Learning

Although large annotated sleep databases are publicly available, and might be used to train automated scoring algorithms, it might still be a challenge to develop an optimal algorithm for your personal sleep study, which might have few subjects or rely on a different recording setup. Both directly applying a learned algorithm or retraining the algorithm on your rather small database is suboptimal. And definitely state-of-the-art sleep staging algorithms based on deep neural networks demand a large amount of data to be trained. This work presents a deep transfer learning approach to overcome the channel mismatch problem and enable transferring knowledge from a large dataset to a small cohort for automatic sleep staging. We start from a generic end-to-end deep learning framework for sequence-to-sequence sleep staging and derive two networks adhering to this framework as a device for transfer learning. The networks are first trained in the source domain (i.e. the large database). The pretrained networks are then finetuned in the target domain, i.e. the small cohort, to complete knowledge transfer. We employ the Montreal Archive of Sleep Studies (MASS) database consisting of 200 subjects as the source domain and study deep transfer learning on four different target domains: the Sleep Cassette subset and the Sleep Telemetry subset of the Sleep-EDF Expanded database, the Surrey-cEEGGrid database, and the Surrey-PSG database. The target domains are purposely adopted to cover different degrees of channel mismatch to the source domain. Our experimental results show significant performance improvement on automatic sleep staging on the target domains achieved with the proposed deep transfer learning approach and we discuss the impact of various fine tuning approaches.