A deep transfer learning approach for wearable sleep stage classification with photoplethysmography

A model for identifying potentially inappropriate medication used in older people with dementia: a machine learning study

BACKGROUND

Older adults with dementia often face the risk of potentially inappropriate medication (PIM) use. The quality of PIM evaluation is hindered by researchers' unfamiliarity with evaluation criteria for inappropriate drug use. While traditional machine learning algorithms can enhance evaluation quality, they struggle with the multilabel nature of prescription data.

AIM

This study aimed to combine six machine learning algorithms and three multilabel classification models to identify correlations in prescription information and develop an optimal model to identify PIMs in older adults with dementia.

METHOD

This study was conducted from January 1, 2020, to December 31, 2020. We used cluster sampling to obtain prescription data from patients 65 years and older with dementia. We assessed PIMs using the 2019 Beers criteria, the most authoritative and widely recognized standard for PIM detection. Our modeling process used three problem transformation methods (binary relevance, label powerset, and classifier chain) and six classification algorithms.

RESULTS

We identified 18,338 older dementia patients and 36 PIMs types. The classifier chain + categorical boosting (CatBoost) model demonstrated superior performance, with the highest accuracy (97.93%), precision (95.39%), recall (94.07%), F1 score (95.69%), and subset accuracy values (97.41%), along with the lowest Hamming loss value (0.0011) and an acceptable duration of the operation (371s).

CONCLUSION

This research introduces a pioneering CC + CatBoost warning model for PIMs in older dementia patients, utilizing machine-learning techniques. This model enables a quick and precise identification of PIMs, simplifying the manual evaluation process.

Sleep assessment using EEG-based wearables - A systematic review

Polysomnography (PSG) is the reference standard of sleep measurement, but is burdensome for the participant and labor intensive. Affordable electroencephalography (EEG)-based wearables are easy to use and are gaining popularity, yet selecting the most suitable device is a challenge for clinicians and researchers. In this systematic review, we aim to provide a comprehensive overview of available EEG-based wearables to measure human sleep. For each wearable, an overview will be provided regarding validated population and reported measurement properties. A systematic search was conducted in the databases OVID MEDLINE, Embase.com and CINAHL. A machine learning algorithm (ASReview) was utilized to screen titles and abstracts for eligibility. In total, 60 papers were selected, covering 34 unique EEG-based wearables. Feasibility studies indicated good tolerance, high compliance, and success rates. The 42 included validation studies were conducted across diverse populations and showed consistently high accuracy in sleep staging detection. Therefore, the recent advancements in EEG-based wearables show great promise as alternative for PSG and for at-home sleep monitoring. Users should consider factors like user-friendliness, comfort, and costs, as these devices vary in features and pricing, impacting their suitability for individual needs.

Improved sleep stage predictions by deep learning of photoplethysmogram and respiration patterns

Sleep staging is a crucial tool for diagnosing and monitoring sleep disorders, but the standard clinical approach using polysomnography (PSG) in a sleep lab is time-consuming, expensive, uncomfortable, and limited to a single night. Advancements in sensor technology have enabled home sleep monitoring, but existing devices still lack sufficient accuracy to inform clinical decisions. To address this challenge, we propose a deep learning architecture that combines a convolutional neural network and bidirectional long short-term memory to accurately classify sleep stages. By supplementing photoplethysmography (PPG) signals with respiratory sensor inputs, we demonstrated significant improvements in prediction accuracy and Cohen's kappa (k) for 2- (92.7 %; k = 0.768), 3- (80.2 %; k = 0.714), 4- (76.8 %, k = 0.550), and 5-stage (76.7 %, k = 0.616) sleep classification using raw data. This relatively translatable approach, with a less intensive AI model and leveraging only a few, inexpensive sensors, shows promise in accurately staging sleep. This has potential for diagnosing and managing sleep disorders in a more accessible and practical manner, possibly even at home.

Sleep staging algorithm based on smartwatch sensors for healthy and sleep apnea populations

OBJECTIVE

Sleep stages can provide valuable insights into an individual's sleep quality. By leveraging movement and heart rate data collected by modern smartwatches, it is possible to enable the sleep staging feature and enhance users' understanding about their sleep and health conditions.

METHOD

In this paper, we present and validate a recurrent neural network based model with 23 input features extracted from accelerometer and photoplethysmography sensors data for both healthy and sleep apnea populations. We designed a lightweight and fast solution to enable the prediction of sleep stages for each 30-s epoch. This solution was developed using a large dataset of 1522 night recordings collected from a highly heterogeneous population and different versions of Samsung smartwatch.

RESULTS

In the classification of four sleep stages (wake, light, deep, and rapid eye movements sleep), the proposed solution achieved 71.6 % of balanced accuracy and a Cohen's kappa of 0.56 in a test set with 586 recordings.

CONCLUSION

The results presented in this paper validate our proposal as a competitive wearable solution for sleep staging. Additionally, the use of a large and diverse data set contributes to the robustness of our solution, and corroborates the validation of algorithm's performance. Some additional analysis performed for healthy and sleep apnea population demonstrated that algorithm's performance has low correlation with demographic variables.

Expert-level sleep staging using an electrocardiography-only feed-forward neural network

Reliable classification of sleep stages is crucial in sleep medicine and neuroscience research for providing valuable insights, diagnoses, and understanding of brain states. The current gold standard method for sleep stage classification is polysomnography (PSG). Unfortunately, PSG is an expensive and cumbersome process involving numerous electrodes, often conducted in an unfamiliar clinic and annotated by a professional. Although commercial devices like smartwatches track sleep, their performance is well below PSG. To address these disadvantages, we present a feed-forward neural network that achieves gold-standard levels of agreement using only a single lead of electrocardiography (ECG) data. Specifically, the median five-stage Cohen's kappa is 0.725 on a large, diverse dataset of 5 to 90-year-old subjects. Comparisons with a comprehensive meta-analysis of between-human inter-rater agreement confirm the non-inferior performance of our model. Finally, we developed a novel loss function to align the training objective with Cohen's kappa. Our method offers an inexpensive, automated, and convenient alternative for sleep stage classification-further enhanced by a real-time scoring option. Cardiosomnography, or a sleep study conducted with ECG only, could take expert-level sleep studies outside the confines of clinics and laboratories and into realistic settings. This advancement democratizes access to high-quality sleep studies, considerably enhancing the field of sleep medicine and neuroscience. It makes less-expensive, higher-quality studies accessible to a broader community, enabling improved sleep research and more personalized, accessible sleep-related healthcare interventions.

Generalized sleep decoding with basal ganglia signals in multiple movement disorders

Sleep disturbances profoundly affect the quality of life in individuals with neurological disorders. Closed-loop deep brain stimulation (DBS) holds promise for alleviating sleep symptoms, however, this technique necessitates automated sleep stage decoding from intracranial signals. We leveraged overnight data from 121 patients with movement disorders (Parkinson's disease, Essential Tremor, Dystonia, Essential Tremor, Huntington's disease, and Tourette's syndrome) in whom synchronized polysomnograms and basal ganglia local field potentials were recorded, to develop a generalized, multi-class, sleep specific decoder - BGOOSE. This generalized model achieved 85% average accuracy across patients and across disease conditions, even in the presence of recordings from different basal ganglia targets. Furthermore, we also investigated the role of electrocorticography on decoding performances and proposed an optimal decoding map, which was shown to facilitate channel selection for optimal model performances. BGOOSE emerges as a powerful tool for generalized sleep decoding, offering exciting potentials for the precision stimulation delivery of DBS and better management of sleep disturbances in movement disorders.

Photoplethysmography based atrial fibrillation detection: a continually growing field

Objective. Atrial fibrillation (AF) is a prevalent cardiac arrhythmia associated with significant health ramifications, including an elevated susceptibility to ischemic stroke, heart disease, and heightened mortality. Photoplethysmography (PPG) has emerged as a promising technology for continuous AF monitoring for its cost-effectiveness and widespread integration into wearable devices. Our team previously conducted an exhaustive review on PPG-based AF detection before June 2019. However, since then, more advanced technologies have emerged in this field.Approach. This paper offers a comprehensive review of the latest advancements in PPG-based AF detection, utilizing digital health and artificial intelligence (AI) solutions, within the timeframe spanning from July 2019 to December 2022. Through extensive exploration of scientific databases, we have identified 57 pertinent studies.Significance. Our comprehensive review encompasses an in-depth assessment of the statistical methodologies, traditional machine learning techniques, and deep learning approaches employed in these studies. In addition, we address the challenges encountered in the domain of PPG-based AF detection. Furthermore, we maintain a dedicated website to curate the latest research in this area, with regular updates on a regular basis.

Research and application of deep learning-based sleep staging: Data, modeling, validation, and clinical practice

Over the past few decades, researchers have attempted to simplify and accelerate the process of sleep stage classification through various approaches; however, only a few such approaches have gained widespread acceptance. Artificial intelligence technology, particularly deep learning, is promising for earning the trust of the sleep medicine community in automated sleep-staging systems, thus facilitating its application in clinical practice and integration into daily life. We aimed to comprehensively review the latest methods that are applying deep learning for enhancing sleep staging efficiency and accuracy. Starting from the requisite "data" for constructing deep learning algorithms, we elucidated the current landscape of this domain and summarized the fundamental modeling process, encompassing signal selection, data pre-processing, model architecture, classification tasks, and performance metrics. Furthermore, we reviewed the applications of automated sleep staging in scenarios such as sleep-disorder screening, diagnostic procedures, and health monitoring and management. Finally, we conducted an in-depth analysis and discussion of the challenges and future in intelligent sleep staging, particularly focusing on large-scale sleep datasets, interdisciplinary collaborations, and human-computer interactions.

InsightSleepNet: the interpretable and uncertainty-aware deep learning network for sleep staging using continuous Photoplethysmography

BACKGROUND

This study was conducted to address the existing drawbacks of inconvenience and high costs associated with sleep monitoring. In this research, we performed sleep staging using continuous photoplethysmography (PPG) signals for sleep monitoring with wearable devices. Furthermore, our aim was to develop a more efficient sleep monitoring method by considering both the interpretability and uncertainty of the model's prediction results, with the goal of providing support to medical professionals in their decision-making process.

METHOD

The developed 4-class sleep staging model based on continuous PPG data incorporates several key components: a local attention module, an InceptionTime module, a time-distributed dense layer, a temporal convolutional network (TCN), and a 1D convolutional network (CNN). This model prioritizes both interpretability and uncertainty estimation in its prediction results. The local attention module is introduced to provide insights into the impact of each epoch within the continuous PPG data. It achieves this by leveraging the TCN structure. To quantify the uncertainty of prediction results and facilitate selective predictions, an energy score estimation is employed. By enhancing both the performance and interpretability of the model and taking into consideration the reliability of its predictions, we developed the InsightSleepNet for accurate sleep staging.

RESULT

InsightSleepNet was evaluated using three distinct datasets: MESA, CFS, and CAP. Initially, we assessed the model's classification performance both before and after applying an energy score threshold. We observed a significant improvement in the model's performance with the implementation of the energy score threshold. On the MESA dataset, prior to applying the energy score threshold, the accuracy was 84.2% with a Cohen's kappa of 0.742 and weighted F1 score of 0.842. After implementing the energy score threshold, the accuracy increased to a range of 84.8-86.1%, Cohen's kappa values ranged from 0.75 to 0.78 and weighted F1 scores ranged from 0.848 to 0.861. In the case of the CFS dataset, we also noted enhanced performance. Before the application of the energy score threshold, the accuracy stood at 80.6% with a Cohen's kappa of 0.72 and weighted F1 score of 0.808. After thresholding, the accuracy improved to a range of 81.9-85.6%, Cohen's kappa values ranged from 0.74 to 0.79 and weighted F1 scores ranged from 0.821 to 0.857. Similarly, on the CAP dataset, the initial accuracy was 80.6%, accompanied by a Cohen's kappa of 0.73 and weighted F1 score was 0.805. Following the application of the threshold, the accuracy increased to a range of 81.4-84.3%, Cohen's kappa values ranged from 0.74 to 0.79 and weighted F1 scores ranged from 0.813 to 0.842. Additionally, by interpreting the model's predictions, we obtained results indicating a correlation between the peak of the PPG signal and sleep stage classification.

CONCLUSION

InsightSleepNet is a 4-class sleep staging model that utilizes continuous PPG data, serves the purpose of continuous sleep monitoring with wearable devices. Beyond its primary function, it might facilitate in-depth sleep analysis by medical professionals and empower them with interpretability for intervention-based predictions. This capability can also support well-informed clinical decision-making, providing valuable insights and serving as a reliable second opinion in medical settings.

Imputing missing sleep data from wearables with neural networks in real-world settings

Sleep is a critical component of health and well-being but collecting and analyzing accurate longitudinal sleep data can be challenging, especially outside of laboratory settings. We propose a simple neural network model titled SOMNI (Sleep data restOration using Machine learning and Non-negative matrix factorIzation [NMF]) for imputing missing rest-activity data from actigraphy, which can enable clinicians to better handle missing data and monitor sleep-wake cycles of individuals with highly irregular sleep-wake patterns. The model consists of two hidden layers and uses NMF to capture hidden longitudinal sleep-wake patterns of individuals with disturbed sleep-wake cycles. Based on this, we develop two approaches: the individual approach imputes missing data based on the data from only one participant, while the global approach imputes missing data based on the data across multiple participants. Our models are tested with shift and non-shift workers' data from three independent hospitals. Both approaches can accurately impute missing data up to 24 hours of long dataset (>50 days) even for shift workers with extremely irregular sleep-wake patterns (AUC > 0.86). On the other hand, for short dataset (~15 days), only the global model is accurate (AUC > 0.77). Our approach can be used to help clinicians monitor sleep-wake cycles of patients with sleep disorders outside of laboratory settings without relying on sleep diaries, ultimately improving sleep health outcomes.

Obstructive sleep apnea diagnosis and beyond using portable monitors

Obstructive sleep apnea (OSA) is a chronic sleep and breathing disorder with significant health complications, including cardiovascular disease and neurocognitive impairments. To ensure timely treatment, there is a need for a portable, accurate and rapid method of diagnosing OSA. This review examines the use of various physiological signals used in the detection of respiratory events and evaluates their effectiveness in portable monitors (PM) relative to gold standard polysomnography. The primary objective is to explore the relationship between these physiological parameters and OSA, their application in calculating the apnea hypopnea index (AHI), the standard metric for OSA diagnosis, and the derivation of non-AHI metrics that offer additional diagnostic value. It is found that increasing the number of parameters in PMs does not necessarily improve OSA detection. Several factors can cause performance variations among different PMs, even if they extract similar signals. The review also highlights the potential of PMs to be used beyond OSA diagnosis. These devices possess parameters that can be utilized to obtain endotypic and other non-AHI metrics, enabling improved characterization of the disorder and personalized treatment strategies. Advancements in PM technology, coupled with thorough evaluation and validation of these devices, have the potential to revolutionize OSA diagnosis, personalized treatment, and ultimately improve health outcomes for patients with OSA. By identifying the key factors influencing performance and exploring the application of PMs beyond OSA diagnosis, this review aims to contribute to the ongoing development and utilization of portable, efficient, and effective diagnostic tools for OSA.

Survey of Transfer Learning Approaches in the Machine Learning of Digital Health Sensing Data

Machine learning and digital health sensing data have led to numerous research achievements aimed at improving digital health technology. However, using machine learning in digital health poses challenges related to data availability, such as incomplete, unstructured, and fragmented data, as well as issues related to data privacy, security, and data format standardization. Furthermore, there is a risk of bias and discrimination in machine learning models. Thus, developing an accurate prediction model from scratch can be an expensive and complicated task that often requires extensive experiments and complex computations. Transfer learning methods have emerged as a feasible solution to address these issues by transferring knowledge from a previously trained task to develop high-performance prediction models for a new task. This survey paper provides a comprehensive study of the effectiveness of transfer learning for digital health applications to enhance the accuracy and efficiency of diagnoses and prognoses, as well as to improve healthcare services. The first part of this survey paper presents and discusses the most common digital health sensing technologies as valuable data resources for machine learning applications, including transfer learning. The second part discusses the meaning of transfer learning, clarifying the categories and types of knowledge transfer. It also explains transfer learning methods and strategies, and their role in addressing the challenges in developing accurate machine learning models, specifically on digital health sensing data. These methods include feature extraction, fine-tuning, domain adaptation, multitask learning, federated learning, and few-/single-/zero-shot learning. This survey paper highlights the key features of each transfer learning method and strategy, and discusses the limitations and challenges of using transfer learning for digital health applications. Overall, this paper is a comprehensive survey of transfer learning methods on digital health sensing data which aims to inspire researchers to gain knowledge of transfer learning approaches and their applications in digital health, enhance the current transfer learning approaches in digital health, develop new transfer learning strategies to overcome the current limitations, and apply them to a variety of digital health technologies.

The 2023 wearable photoplethysmography roadmap

Photoplethysmography is a key sensing technology which is used in wearable devices such as smartwatches and fitness trackers. Currently, photoplethysmography sensors are used to monitor physiological parameters including heart rate and heart rhythm, and to track activities like sleep and exercise. Yet, wearable photoplethysmography has potential to provide much more information on health and wellbeing, which could inform clinical decision making. This Roadmap outlines directions for research and development to realise the full potential of wearable photoplethysmography. Experts discuss key topics within the areas of sensor design, signal processing, clinical applications, and research directions. Their perspectives provide valuable guidance to researchers developing wearable photoplethysmography technology.

A comprehensive review of machine learning algorithms and their application in geriatric medicine: present and future

The increasing access to health data worldwide is driving a resurgence in machine learning research, including data-hungry deep learning algorithms. More computationally efficient algorithms now offer unique opportunities to enhance diagnosis, risk stratification, and individualised approaches to patient management. Such opportunities are particularly relevant for the management of older patients, a group that is characterised by complex multimorbidity patterns and significant interindividual variability in homeostatic capacity, organ function, and response to treatment. Clinical tools that utilise machine learning algorithms to determine the optimal choice of treatment are slowly gaining the necessary approval from governing bodies and being implemented into healthcare, with significant implications for virtually all medical disciplines during the next phase of digital medicine. Beyond obtaining regulatory approval, a crucial element in implementing these tools is the trust and support of the people that use them. In this context, an increased understanding by clinicians of artificial intelligence and machine learning algorithms provides an appreciation of the possible benefits, risks, and uncertainties, and improves the chances for successful adoption. This review provides a broad taxonomy of machine learning algorithms, followed by a more detailed description of each algorithm class, their purpose and capabilities, and examples of their applications, particularly in geriatric medicine. Additional focus is given on the clinical implications and challenges involved in relying on devices with reduced interpretability and the progress made in counteracting the latter via the development of explainable machine learning.

Modeling the Impact of Inter-Rater Disagreement on Sleep Statistics Using Deep Generative Learning

Sleep staging is the process by which an overnight polysomnographic measurement is segmented into epochs of 30 seconds, each of which is annotated as belonging to one of five discrete sleep stages. The resulting scoring is graphically depicted as a hypnogram, and several overnight sleep statistics are derived, such as total sleep time and sleep onset latency. Gold standard sleep staging as performed by human technicians is time-consuming, costly, and comes with imperfect inter-scorer agreement, which also results in inter-scorer disagreement about the overnight statistics. Deep learning algorithms have shown promise in automating sleep scoring, but struggle to model inter-scorer disagreement in sleep statistics. To that end, we introduce a novel technique using conditional generative models based on Normalizing Flows that permits the modeling of the inter-rater disagreement of overnight sleep statistics, termed U-Flow. We compare U-Flow to other automatic scoring methods on a hold-out test set of 70 subjects, each scored by six independent scorers. The proposed method achieves similar sleep staging performance in terms of accuracy and Cohen's kappa on the majority-voted hypnograms. At the same time, U-Flow outperforms the other methods in terms of modeling the inter-rater disagreement of overnight sleep statistics. The consequences of inter-rater disagreement about overnight sleep statistics may be great, and the disagreement potentially carries diagnostic and scientifically relevant information about sleep structure. U-Flow is able to model this disagreement efficiently and can support further investigations into the impact inter-rater disagreement has on sleep medicine and basic sleep research.

A real-time, personalized sleep intervention using mathematical modeling and wearable devices

The prevalence of artificial light exposure has enabled us to be active any time of the day or night, leading to the need for high alertness outside of traditional daytime hours. To address this need, we developed a personalized sleep intervention framework that analyzes real-world sleep-wake patterns obtained from wearable devices to maximize alertness during specific target periods. Our framework utilizes a mathematical model that tracks the dynamic sleep pressure and circadian rhythm based on the user's sleep history. In this way, the model accurately predicts real-time alertness, even for shift workers with complex sleep and work schedules (N = 71, t = 13~21 days). This allowed us to discover a new sleep-wake pattern called the adaptive circadian split sleep, which incorporates a main sleep period and a late nap to enable high alertness during both work and non-work periods of shift workers. We further developed a mobile application that integrates this framework to recommend practical, personalized sleep schedules for individual users to maximize their alertness during a targeted activity time based on their desired sleep onset and available sleep duration. This can reduce the risk of errors for those who require high alertness during nontraditional activity times and improve the health and quality of life for those leading shift work-like lifestyles.

Challenges of Applying Automated Polysomnography Scoring at Scale

Automatic polysomnography analysis can be leveraged to shorten scoring times, reduce associated costs, and ultimately improve the overall diagnosis of sleep disorders. Multiple and diverse strategies have been attempted for implementation of this technology at scale in the routine workflow of sleep centers. The field, however, is complex and presents unsolved challenges in a number of areas. Recent developments in computer science and artificial intelligence are nevertheless closing the gap. Technological advances are also opening new pathways for expanding our current understanding of the domain and its analysis.

Automatic sleep-stage classification of heart rate and actigraphy data using deep and transfer learning approaches

Manual sleep-stage scoring based on full-night polysomnography data recorded in a sleep lab has been the gold standard of clinical sleep medicine. This costly and time-consuming approach is unfit for long-term studies as well as assessment of sleep on a population level. With the vast amount of physiological data becoming available from wrist-worn devices, deep learning techniques provide an opportunity for fast and reliable automatic sleep-stage classification tasks. However, training a deep neural network requires large annotated sleep databases, which are not available for long-term epidemiological studies. In this paper, we introduce an end-to-end temporal convolutional neural network able to automatically score sleep stages from raw heartbeat RR interval (RRI) and wrist actigraphy data. Moreover, a transfer learning approach enables the training of the network on a large public database (Sleep Heart Health Study, SHHS) and its subsequent application to a much smaller database recorded by a wristband device. The transfer learning significantly shortens training time and improves sleep-scoring accuracy from 68.9% to 73.8% and inter-rater reliability (Cohen's kappa) from 0.51 to 0.59. We also found that for the SHHS database, automatic sleep-scoring accuracy using deep learning shows a logarithmic relationship with the training size. Although deep learning approaches for automatic sleep scoring are not yet comparable to the inter-rater reliability among sleep technicians, performance is expected to significantly improve in the near future when more large public databases become available. We anticipate those deep learning techniques, when combined with our transfer learning approach, will leverage automatic sleep scoring of physiological data from wearable devices and enable the investigation of sleep in large cohort studies.

Technologies for sleep monitoring at home: wearables and nearables

Sleep is an essential part of our lives and daily sleep monitoring is crucial for maintaining good health and well-being. Traditionally, the gold standard method for sleep monitoring is polysomnography using various sensors attached to the body; however, it is limited with regards to long-term sleep monitoring in a home environment. Recent advancements in wearable and nearable technology have made it possible to monitor sleep at home. In this review paper, the technologies that are currently available for sleep stages and sleep disorder monitoring at home are reviewed using wearable and nearable devices. Wearables are devices that are worn on the body, while nearables are placed near the body. These devices can accurately monitor sleep stages and sleep disorder in a home environment. In this study, the benefits and limitations of each technology are discussed, along with their potential to improve sleep quality.

Feasibility of Transfer Learning from Finger PPG to In-Ear PPG

The success of deep learning methods has enabled many modern wearable health applications, but has also highlighted the critical caveat of their extremely data hungry nature. While the widely explored wrist and finger photoplethysmography (PPG) sites are less affected, given the large available databases, this issue is prohibitive to exploring the full potential of novel recording locations such as in-ear wearables. To this end, we assess the feasibility of transfer learning from finger PPG to in-ear PPG in the context of deep learning for respiratory monitoring. This is achieved by introducing an encoder-decoder framework which is set up to extract respiratory waveforms from PPG, whereby simultaneously recorded gold standard respiratory waveforms (capnography, impedance pneumography and air flow) are used as a training reference. Next, the data augmentation and training pipeline is examined for both training on finger PPG and the subsequent fine tuning on in-ear PPG. The results indicate that, through training on two large finger PPG data sets (95 subjects) and then retraining on our own small in-ear PPG data set (6 subjects), the model achieves lower and more consistent test error for the prediction of the respiratory waveforms, compared to training on the small in-ear data set alone. This conclusively demonstrates the feasibility of transfer learning from finger PPG to in-ear PPG, leading to better generalisation across a wide range of respiratory rates.

A deep learning model based on the combination of convolutional and recurrent neural networks to enhance pulse oximetry ability to classify sleep stages in children with sleep apnea

Characterization of sleep stages is essential in the diagnosis of sleep-related disorders but relies on manual scoring of overnight polysomnography (PSG) recordings, which is onerous and labor-intensive. Accordingly, we aimed to develop an accurate deep-learning model for sleep staging in children suffering from pediatric obstructive sleep apnea (OSA) using pulse oximetry signals. For this purpose, pulse rate (PR) and blood oxygen saturation (SpO2) from 429 childhood OSA patients were analyzed. A CNN-RNN architecture fed with PR and SpO2 signals was developed to automatically classify wake (W), non-Rapid Eye Movement (NREM), and REM sleep stages. This architecture was composed of: (i) a convolutional neural network (CNN), which learns stage-related features from raw PR and SpO2 data; and (ii) a recurrent neural network (RNN), which models the temporal distribution of the sleep stages. The proposed CNN-RNN model showed a high performance for the automated detection of W/NREM/REM sleep stages (86.0% accuracy and 0.743 Cohen's kappa). Furthermore, the total sleep time estimated for each children using the CNN-RNN model showed high agreement with the manually derived from PSG (intra-class correlation coefficient = 0.747). These results were superior to previous works using CNN-based deep-learning models for automatic sleep staging in pediatric OSA patients from pulse oximetry signals. Therefore, the combination of CNN and RNN allows to obtain additional information from raw PR and SpO2 data related to sleep stages, thus being useful to automatically score sleep stages in pulse oximetry tests for children evaluated for suspected OSA.Clinical Relevance-This research establishes the usefulness of a CNN-RNN architecture to automatically score sleep stages in pulse oximetry tests for pediatric OSA diagnosis.

A computationally efficient algorithm for wearable sleep staging in clinical populations

This study describes a computationally efficient algorithm for 4-class sleep staging based on cardiac activity and body movements. Using an accelerometer to calculate gross body movements and a reflective photoplethysmographic (PPG) sensor to determine interbeat intervals and a corresponding instantaneous heart rate signal, a neural network was trained to classify between wake, combined N1 and N2, N3 and REM sleep in epochs of 30 s. The classifier was validated on a hold-out set by comparing the output against manually scored sleep stages based on polysomnography (PSG). In addition, the execution time was compared with that of a previously developed heart rate variability (HRV) feature-based sleep staging algorithm. With a median epoch-per-epoch κ of 0.638 and accuracy of 77.8% the algorithm achieved an equivalent performance when compared to the previously developed HRV-based approach, but with a 50-times faster execution time. This shows how a neural network, without leveraging any a priori knowledge of the domain, can automatically "discover" a suitable mapping between cardiac activity and body movements, and sleep stages, even in patients with different sleep pathologies. In addition to the high performance, the reduced complexity of the algorithm makes practical implementation feasible, opening up new avenues in sleep diagnostics.

Quantifying the impact of data characteristics on the transferability of sleep stage scoring models

Deep learning models for scoring sleep stages based on single-channel EEG have been proposed as a promising method for remote sleep monitoring. However, applying these models to new datasets, particularly from wearable devices, raises two questions. First, when annotations on a target dataset are unavailable, which different data characteristics affect the sleep stage scoring performance the most and by how much? Second, when annotations are available, which dataset should be used as the source of transfer learning to optimize performance? In this paper, we propose a novel method for computationally quantifying the impact of different data characteristics on the transferability of deep learning models. Quantification is accomplished by training and evaluating two models with significant architectural differences, TinySleepNet and U-Time, under various transfer configurations in which the source and target datasets have different recording channels, recording environments, and subject conditions. For the first question, the environment had the highest impact on sleep stage scoring performance, with performance degrading by over 14% when sleep annotations were unavailable. For the second question, the most useful transfer sources for TinySleepNet and the U-Time models were MASS-SS1 and ISRUC-SG1, containing a high percentage of N1 (the rarest sleep stage) relative to the others. The frontal and central EEGs were preferred for TinySleepNet. The proposed approach enables full utilization of existing sleep datasets for training and planning model transfer to maximize the sleep stage scoring performance on a target problem when sleep annotations are limited or unavailable, supporting the realization of remote sleep monitoring.

Cross-Domain Transfer of EEG to EEG or ECG Learning for CNN Classification Models

Electroencephalography (EEG) is often used to evaluate several types of neurological brain disorders because of its noninvasive and high temporal resolution. In contrast to electrocardiography (ECG), EEG can be uncomfortable and inconvenient for patients. Moreover, deep-learning techniques require a large dataset and a long time for training from scratch. Therefore, in this study, EEG-EEG or EEG-ECG transfer learning strategies were applied to explore their effectiveness for the training of simple cross-domain convolutional neural networks (CNNs) used in seizure prediction and sleep staging systems, respectively. The seizure model detected interictal and preictal periods, whereas the sleep staging model classified signals into five stages. The patient-specific seizure prediction model with six frozen layers achieved 100% accuracy for seven out of nine patients and required only 40 s of training time for personalization. Moreover, the cross-signal transfer learning EEG-ECG model for sleep staging achieved an accuracy approximately 2.5% higher than that of the ECG model; additionally, the training time was reduced by >50%. In summary, transfer learning from an EEG model to produce personalized models for a more convenient signal can both reduce the training time and increase the accuracy; moreover, challenges such as data insufficiency, variability, and inefficiency can be effectively overcome.

A Scalable Framework for Closed-Loop Neuromodulation with Deep Learning

Closed-loop neuromodulation measures dynamic neural or physiological activity to optimize interventions for clinical and nonclinical behavioral, cognitive, wellness, attentional, or general task performance enhancement. Conventional closed-loop stimulation approaches can contain biased biomarker detection (decoders and error-based triggering) and stimulation-type application. We present and verify a novel deep learning framework for designing and deploying flexible, data-driven, automated closed-loop neuromodulation that is scalable using diverse datasets, agnostic to stimulation technology (supporting multi-modal stimulation: tACS, tDCS, tFUS, TMS), and without the need for personalized ground-truth performance data. Our approach is based on identified periods of responsiveness - detected states that result in a change in performance when stimulation is applied compared to no stimulation. To demonstrate our framework, we acquire, analyze, and apply a data-driven approach to our open sourced GX dataset, which includes concurrent physiological (ECG, EOG) and neuronal (EEG) measures, paired with continuous vigilance/attention-fatigue tracking, and High-Definition transcranial electrical stimulation (HD-tES). Our framework's decision process for intervention application identified 88.26% of trials as correct applications, showed potential improvement with varying stimulation types, or missed opportunities to stimulate, whereas 11.25% of trials were predicted to stimulate at inopportune times. With emerging datasets and stimulation technologies, our unifying and integrative framework; leveraging deep learning (Convolutional Neural Networks - CNNs); demonstrates the adaptability and feasibility of automated multimodal neuromodulation for both clinical and nonclinical applications.

Contactless Camera-Based Sleep Staging: The HealthBed Study

Polysomnography (PSG) remains the gold standard for sleep monitoring but is obtrusive in nature. Advances in camera sensor technology and data analysis techniques enable contactless monitoring of heart rate variability (HRV). In turn, this may allow remote assessment of sleep stages, as different HRV metrics indirectly reflect the expression of sleep stages. We evaluated a camera-based remote photoplethysmography (PPG) setup to perform automated classification of sleep stages in near darkness. Based on the contactless measurement of pulse rate variability, we use a previously developed HRV-based algorithm for 3 and 4-class sleep stage classification. Performance was evaluated on data of 46 healthy participants obtained from simultaneous overnight recording of PSG and camera-based remote PPG. To validate the results and for benchmarking purposes, the same algorithm was used to classify sleep stages based on the corresponding ECG data. Compared to manually scored PSG, the remote PPG-based algorithm achieved moderate agreement on both 3 class (Wake-N1/N2/N3-REM) and 4 class (Wake-N1/N2-N3-REM) classification, with average κ of 0.58 and 0.49 and accuracy of 81% and 68%, respectively. This is in range with other performance metrics reported on sensing technologies for wearable sleep staging, showing the potential of video-based non-contact sleep staging.

Contactless sleep posture measurements for demand-controlled sleep thermal comfort: A pilot study

Thermal comfort during sleep is essential for both sleep quality and human health while sleeping. There are currently few effective contactless methods for detecting the sleep thermal comfort at any time of day or night. In this paper, a vision-based detection approach for human thermal comfort while sleeping was proposed, which is intended to avoid overcooling/overheating supply, meet the thermal comfort needs of human sleep, and improve human sleep quality and health. Based on 438 valid questionnaire surveys, 10 types of thermal comfort sleep postures were summarized. By using a large number of data captured, a fundamental framework of detection algorithm was constructed to detect human sleeping postures, and corresponding weighting model was established. A total of 2.65 million frames of posture data in natural sleep status were collected, and thermal comfort-related sleep postures dataset was created. Finally, the robustness and effectiveness of the proposed algorithm were validated. The validation results show that the sleeping posture and human skeleton keypoints can be used for estimating sleeping thermal comfort, and the the quilt coverage area can be fused to improve the detection accuracy.

Sleep classification using Consumer Sleep Technologies and AI: A review of the current landscape

Classifying sleep stages in real-time represents considerable potential, for instance in enabling interactive noise masking in noisy environments when persons are in a state of light sleep or to support clinical staff in analyzing sleep patterns etc. However, the current gold standard for classifying sleep stages, Polysomnography (PSG), is too cumbersome to apply outside controlled hospital settings and requires manual as well as highly specialized knowledge to classify sleep stages. Using data from Consumer Sleep Technologies (CSTs) to inform machine learning algorithms represent a promising opportunity for automating the process of classifying sleep stages, also in settings outside the confinements of clinical expert settings. This study reviews 27 papers that use CSTs in combination with Artificial Intelligence (AI) models to classify sleep stages. AI models and their performance are described and compared to synthesize current state of the art in sleep stage classification with CSTs. Furthermore, gaps in the current approaches are shown and how these AI models could be improved in the near-future. Lastly, the challenges of designing interactions for users that are asleep are highlighted pointing towards avenues of more interactive sleep interventions based on AI-infused CSTs solutions.

Deep Transfer Learning Enables Robust Prediction of Antimicrobial Resistance for Novel Antibiotics

Antimicrobial resistance (AMR) has become one of the serious global health problems, threatening the effective treatment of a growing number of infections. Machine learning and deep learning show great potential in rapid and accurate AMR predictions. However, a large number of samples for the training of these models is essential. In particular, for novel antibiotics, limited training samples and data imbalance hinder the models’ generalization performance and overall accuracy. We propose a deep transfer learning model that can improve model performance for AMR prediction on small, imbalanced datasets. As our approach relies on transfer learning and secondary mutations, it is also applicable to novel antibiotics and emerging resistances in the future and enables quick diagnostics and personalized treatments.

Adaptive scheduling of acceleration and gyroscope for motion artifact cancelation in photoplethysmography

BACKGROUND AND OBJECTIVE

Recently, various algorithms have been introduced using wrist-worn photoplethysmography (PPG) to provide high accuracy of instantaneous heart rate (HR) estimation, including during high-intensity exercise. Most studies focus on using acceleration and/or gyroscope signals for the motion artifact (MA) reference, which attenuates or cancels out noise from the MA-corrupted PPG signals. We aim to open and pave the path to find an appropriate MA reference selection for MA cancelation in PPG.

METHODS

We investigated how the acceleration and gyroscope reference signals correlate with the MAs of the distorted PPG signals and derived both mathematically and experimentally an adaptive MA reference selection approach. We applied our algorithm to five state-of-the-art (SOTA) methods for the performance evaluation. In addition, we compared the four MA reference selection approaches, i.e. with acceleration signal only, with gyroscope signal only, with both signals, and using our proposed adaptive selection.

RESULTS

When applied to 47 PPG recordings acquired during intensive physical exercise from two different datasets, our proposed adaptive MA reference selection method provided higher accuracy than the other MA selection approaches for all five SOTA methods.

CONCLUSION

Our proposed adaptive MA reference selection approach can be used in other MA cancelation methods and reduces the HR estimation error.

SIGNIFICANCE

We believe that this study helps researchers to address acceleration and gyroscope signals as accurate MA references, which eventually improves the overall performance for estimating HRs through the various algorithms developed by research groups.

A systematic review of deep learning methods for modeling electrocardiograms during sleep

Sleep is one of the most important human physiological activities and plays an essential role in human health. Polysomnography (PSG) is the gold standard for measuring sleep quality and disorders, but it is time-consuming, labor-intensive, and prone to errors. Current research has confirmed the correlations between sleep and the respiratory/circulatory system. Electrocardiography (ECG) is convenient to perform, and ECG data are rich in breathing information. Therefore, sleep research based on ECG data has become popular. Currently, deep learning (DL) methods have achieved promising results on predictive health care tasks using ECG signals. Therefore, in this review, we systematically identify recent research studies and analyze them from the perspectives of data, model, and task. We discuss the shortcomings, summarize the findings, and highlight the potential opportunities. For sleep-related tasks, many ECG-based DL methods produce more accurate results than traditional approaches by combining multiple signal features and model structures. Methods that are more interpretable, scalable, and transferable will become ubiquitous in the daily practice of medicine and ambient-assisted-living applications. This paper is the first systematic review of ECG-based DL methods for sleep tasks.

Application of photoplethysmography signals for healthcare systems: An in-depth review

BACKGROUND AND OBJECTIVES

Photoplethysmography (PPG) is a device that measures the amount of light absorbed by the blood vessel, blood, and tissues, which can, in turn, translate into various measurements such as the variation in blood flow volume, heart rate variability, blood pressure, etc. Hence, PPG signals can produce a wide variety of biological information that can be useful for the detection and diagnosis of various health problems. In this review, we are interested in the possible health disorders that can be detected using PPG signals.

METHODS

We applied PRISMA guidelines to systematically search various journal databases and identified 43 PPG studies that fit the criteria of this review.

RESULTS

Twenty-five health issues were identified from these studies that were classified into six categories: cardiac, blood pressure, sleep health, mental health, diabetes, and miscellaneous. Various routes were employed in these PPG studies to perform the diagnosis: machine learning, deep learning, and statistical routes. The studies were reviewed and summarized.

CONCLUSIONS

We identified limitations such as poor standardization of sampling frequencies and lack of publicly available PPG databases. We urge that future work should consider creating more publicly available databases so that a wide spectrum of health problems can be covered. We also want to promote the use of PPG signals as a potential precision medicine tool in both ambulatory and hospital settings.

Automatic sleep staging of EEG signals: recent development, challenges, and future directions

Modern deep learning holds a great potential to transform clinical practice on human sleep. Teaching a machine to carry out routine tasks would be a tremendous reduction in workload for clinicians. Sleep staging, a fundamental step in sleep practice, is a suitable task for this and will be the focus in this article. Recently, automatic sleep staging systems have been trained to mimic manual scoring, leading to similar performance to human sleep experts, at least on scoring of healthy subjects. Despite tremendous progress, we have not seen automatic sleep scoring adopted widely in clinical environments. This review aims to give a shared view of the authors on the most recent state-of-the-art development in automatic sleep staging, the challenges that still need to be addressed, and the future directions for automatic sleep scoring to achieve clinical value.

Hybrid Sleep Stage Classification for Clinical Practices across Different Polysomnography Systems Using Frontal EEG

Automatic bio-signal processing and scoring have been a popular topic in recent years. This includes sleep stage classification, which is time-consuming when carried out by hand. Multiple sleep stage classification has been proposed in recent years. While effective, most of these processes are trained and validated against a singular set of data in uniformed pre-processing, whilst in a clinical environment, polysomnography (PSG) may come from different PSG systems that use different signal processing methods. In this study, we present a generalized sleep stage classification method that uses power spectra and entropy. To test its generality, we first trained our system using a uniform dataset and then validated it against another dataset with PSGs from different PSG systems. We found that the system achieved an accuracy of 0.80 and that it is highly consistent across most PSG records. A few samples of NREM3 sleep were classified poorly, and further inspection showed that these samples lost crucial NREM3 features due to aggressive filtering. This implies that the system’s effectiveness can be evaluated by human knowledge. Overall, our classification system shows consistent performance against PSG records that have been collected from different PSG systems, which gives it high potential in a clinical environment.