Study Objectives: Consumer wearable devices may be a helpful method of assessing sleep, but validation is required for their use in clinical practice. Our aim was to validate two models of Fitbit sleep trackers that rely on both accelerometer and heart rate sensors against polysomnography in participants with obstructive sleep apnea (OSA). Methods: Participants were adults presenting with symptoms of OSA and attending our outpatient sleep clinic. A polysomnography (PSG) was applied to all participants at the same time they were wearing a Fitbit sleep tracker. Using paired t tests and Bland-Altman plots, we compared the sleep measures provided by the wearable devices with those obtained by PSG. Since Fitbit devices' automatic detection of sleep start time can cause bias, we performed a correction using Huber loss function-based linear regression and a leave-one-out strategy. Results: Our sample consisted of 65 patients. Diagnosis of OSA was confirmed on 55 (84.6%). There were statistically significant differences between PSG and Fitbit measures for all sleep outcomes but rapid eye movement sleep. Fitbit devices overestimated total sleep time, and underestimated wake after sleep onset and sleep onset latency. After correction of bias, Fitbit-delivered measures of sleep onset latency did not significantly differ of those provided by PSG. Conclusions: Fitbit wearable devices showed an acceptable sensitivity but poor specificity. Consumer sleep trackers still have insufficient accuracy for clinical settings, especially in clinical populations. Solving technical issues and optimizing clinically-oriented features could make them apt for their use in clinical practice in a nondistant future.
We introduce PyHHMM, an object-oriented open-source Python implementation of Heterogeneous-Hidden Markov Models (HHMMs). In addition to HMM's basic core functionalities, such as different initialization algorithms and classical observations models, i.e., continuous and multinoulli, PyHHMM distinctively emphasizes features not supported in similar available frameworks: a heterogeneous observation model, missing data inference, different model order selection criterias, and semi-supervised training. These characteristics result in a feature-rich implementation for researchers working with sequential data. PyHHMM relies on the numpy, scipy, scikit-learn, and seaborn Python packages, and is distributed under the Apache-2.0 License. PyHHMM's source code is publicly available on Github 1 to facilitate adoptions and future contributions. A detailed documentation 2 , which covers examples of use and models' theoretical explanation, is available. The package can be installed through the Python Package Index (PyPI).
Activity detection in atrial fibrillation (AF) electrograms (EGMs) is a key concept to understand the mechanisms of this frequent arrhythmia and design new strategies for its treatment. We present a new method that employs Hidden Markov Models (HMMs) to identify activity presence in bipolar EGMs. The method is fully unsupervised and hence it does not require labeled training data. The HMM activity detection method was validated and compared to the non-linear energy operator (NLEO) method for a set of manually annotated EGMs. The HMM performed better than the NLEO and exhibited more robustness in the presence of low voltage fragmented EGMs.
Time series forecasting is an important problem across many domains, playing a crucial role in multiple realworld applications. In this paper, we propose a forecasting architecture that combines deep autoregressive models with a Spectral Attention (SA) module, which merges global and local frequency domain information in the model's embedded space. By characterizing in the spectral domain the embedding of the time series as occurrences of a random process, our method can identify global trends and seasonality patterns. Two spectral attention models, global and local to the time series, integrate this information within the forecast and perform spectral filtering to remove time series's noise. The proposed architecture has a number of useful properties: it can be effectively incorporated into well-know forecast architectures, requiring a low number of parameters and producing interpretable results that improve forecasting accuracy. We test the Spectral Attention Autoregressive Model (SAAM) on several well-know forecast datasets, consistently demonstrating that our model compares favorably to state-of-the-art approaches.
Sleep constitutes a key indicator of human health, performance, and quality of life. Sleep deprivation has long been related to the onset, development, and worsening of several mental and metabolic disorders, constituting an essential marker for preventing, evaluating, and treating different health conditions. Sleep Activity Recognition methods can provide indicators to assess, monitor, and characterize subjects' sleep-wake cycles and detect behavioral changes. In this work, we propose a general method that continuously operates on passively sensed data from smartphones to characterize sleep and identify significant sleep episodes. Thanks to their ubiquity, these devices constitute an excellent alternative data source to profile subjects' biorhythms in a continuous, objective, and non-invasive manner, in contrast to traditional sleep assessment methods that usually rely on intrusive and subjective procedures. A Heterogeneous Hidden Markov Model is used to model a discrete latent variable process associated with the Sleep Activity Recognition task in a self-supervised way. We validate our results against sleep metrics reported by tested wearables, proving the effectiveness of the proposed approach and advocating its use to assess sleep without more reliable sources.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.