Artificial intelligence in sleep medicine: background and implications for clinicians

MFS-DBF: A trustworthy multichannel feature sieve and decision boundary formulation system for Obstructive Sleep Apnea detection

The fine identification of sleep apnea events is instrumental in Obstructive Sleep Apnea (OSA) diagnosis. The development of sleep apnea event detection algorithms based on polysomnography is becoming a research hotspot in medical signal processing. In this paper, we propose an Inverse-Projection based Visualization System (IPVS) for sleep apnea event detection algorithms. The IPVS consists of a feature dimensionality reduction module and a feature reconstruction module. First, features of blood oxygen saturation and nasal airflow are extracted and used as input data for event analysis. Then, visual analysis is conducted on the feature distribution for apnea events. Next, dimensionality reduction and reconstruction methods are combined to achieve the dynamic visualization of sleep apnea event feature sets and the visual analysis of classifier decision boundaries. Moreover, the decision-making consistency is explored for various sleep apnea event detection classifiers, which provides researchers and users with an intuitive understanding of the detection algorithm. We applied the IPVS to an OSA detection algorithm with an accuracy of 84% and a diagnostic accuracy of 92% on a publicly available dataset. The experimental results show that the consistency between our visualization results and prior medical knowledge provides strong evidence for the practicality of the proposed system. For clinical practice, the IPVS can guide users to focus on samples with higher uncertainty presented by the OSA detection algorithm, reducing the workload and improving the efficiency of clinical diagnosis, which in turn increases the value of trust.

Comparison of automated deep neural network against manual sleep stage scoring in clinical data

OBJECTIVE

To compare the accuracy and generalizability of an automated deep neural network and the Philip Sleepware G3™ Somnolyzer system (Somnolyzer) for sleep stage scoring using American Academy of Sleep Medicine (AASM) guidelines.

METHODS

Sleep recordings from 104 participants were analyzed by a convolutional neural network (CNN), the Somnolyzer and skillful technicians. Evaluation metrics were derived for different combinations of sleep stages. A further comparison between the Somnolyzer and the CNN model using a single-channel signal as input was also performed. Sleep recordings from 263 participants with a lower prevalence of OSA served as a cross-validation dataset to validate the generalizability of the CNN model.

RESULTS

The overall agreement between automated and manual scoring for sleep staging in 104 participants outperformed that of the Somnolyzer according to various metrics (accuracy: 81.81 % vs. 77.07 %; F1: 76.36 % vs. 73.80 %; Cohen's kappa: 0.7403 vs. 0.6848). The results showed that the left electrooculography (EOG) single-channel model had minor advantages over the Somnolyzer. In terms of consistency with manual sleep staging, the CNN model demonstrated superior performance in identifying more pronounced sleep transitions, particularly in the N2 stage and sleep latency metrics. Conversely, the Somnolyzer showed enhanced proficiency in the analysis of REM stages, notably in measuring REM latency. The accuracy in the cross-validation set of 263 participants was also above 80 %.

CONCLUSIONS

The CNN-based automated deep neural network outperformed the Somnolyzer and is sufficiently accurate for sleep study analyses using the AASM classification criteria.

Diagnosing OSA and Insomnia at Home Based Only on an Actigraphy Total Sleep Time and RIP Belts an Algorithm "Nox Body Sleep™"

Purpose

The COVID-19 pandemic has influenced clinical sleep protocols with stricter hospital disinfection requirements. Facing these new rules, we tested if a new artificial intelligence (AI) algorithm: The Nox BodySleep™ (NBS) developed without airflow signals for the analysis of sleep might assess pertinently sleep in patients with Obstructive Sleep Apnea (OSA) and chronic insomnia (CI) as a control group, compared to polysomnography (PSG) manual scoring.

Patients-Methods

NBS is a recurrent neural network model that estimates Wake, NREM, and REM states, given features extracted from activity and respiratory inductance plethysmography (RIP) belt signals (Nox A1 PSG). Sleep states from 139 PSG studies (CI N = 72; OSA N = 67) were analyzed by NBS and compared to manually scored PSG using positive percentage agreement, negative percentage agreement, and overall agreement metrics. Similarly, we compared common sleep parameters and OSA severity using sleep states estimated by NBS for each recording and compared to manual scoring using Bland-Altman analysis and intra-class correlation coefficient.

Results

For 127,170 sleep epochs, an overall agreement of 83% was reached for Wake, NREM and REM states (92% for REM states in CI patients) between NBS and manually scored PSG. Overall agreement for estimating OSA severity was 100% for moderate-severe OSA and 91% for minimal OSA. The absolute errors of the apnea-hypopnea index (AHI) and total sleep time (TST) were significantly lower for the NBS compared to no scoring of sleep. The intra-class correlation was higher for AHI and significantly higher for TST using the NBS compared to no scoring of sleep.

Conclusion

NBS gives sleep states, parameters and AHI with a good positive and negative percentage agreement, compared with manually scored PSG.

An optimized framework for processing multicentric polysomnographic data incorporating expert human oversight

Introduction

Polysomnographic recordings are essential for diagnosing many sleep disorders, yet their detailed analysis presents considerable challenges. With the rise of machine learning methodologies, researchers have created various algorithms to automatically score and extract clinically relevant features from polysomnography, but less research has been devoted to how exactly the algorithms should be incorporated into the workflow of sleep technologists. This paper presents a sophisticated data collection platform developed under the Sleep Revolution project, to harness polysomnographic data from multiple European centers.

Methods

A tripartite platform is presented: a user-friendly web platform for uploading three-night polysomnographic recordings, a dedicated splitter that segments these into individual one-night recordings, and an advanced processor that enhances the one-night polysomnography with contemporary automatic scoring algorithms. The platform is evaluated using real-life data and human scorers, whereby scoring time, accuracy, and trust are quantified. Additionally, the scorers were interviewed about their trust in the platform, along with the impact of its integration into their workflow.

Results

We found that incorporating AI into the workflow of sleep technologists both decreased the time to score by up to 65 min and increased the agreement between technologists by as much as 0.17 κ.

Discussion

We conclude that while the inclusion of AI into the workflow of sleep technologists can have a positive impact in terms of speed and agreement, there is a need for trust in the algorithms.

Paediatric sleep diagnostics in the 21st century: the era of "sleep-omics"?

Paediatric sleep diagnostics is performed using complex multichannel tests in specialised centres, limiting access and availability and resulting in delayed diagnosis and management. Such investigations are often challenging due to patient size (prematurity), tolerability, and compliance with "gold standard" equipment. Children with sensory/behavioural issues, at increased risk of sleep disordered breathing (SDB), often find standard diagnostic equipment difficult.SDB can have implications for a child both in terms of physical health and neurocognitive development. Potential sequelae of untreated SDB includes failure to thrive, cardiopulmonary disease, impaired learning and behavioural issues. Prompt and accurate diagnosis of SDB is important to facilitate early intervention and improve outcomes.The current gold-standard diagnostic test for SDB is polysomnography (PSG), which is expensive, requiring the interpretation of a highly specialised physiologist. PSG is not feasible in low-income countries or outwith specialist sleep centres. During the coronavirus disease 2019 pandemic, efforts were made to improve remote monitoring and diagnostics in paediatric sleep medicine, resulting in a paradigm shift in SDB technology with a focus on automated diagnosis harnessing artificial intelligence (AI). AI enables interrogation of large datasets, setting the scene for an era of "sleep-omics", characterising the endotypic and phenotypic bedrock of SDB by drawing on genetic, lifestyle and demographic information. The National Institute for Health and Care Excellence recently announced a programme for the development of automated home-testing devices for SDB. Scorer-independent scalable diagnostic approaches for paediatric SDB have potential to improve diagnostic accuracy, accessibility and patient tolerability; reduce health inequalities; and yield downstream economic and environmental benefits.

An Artificial Intelligence Platform to Stratify the Risk of Experiencing Sleep Disturbance in University Students After Analyzing Psychological Health, Lifestyle, and Sports: A Multicenter Externally Validated Study

Background

Sleep problems are prevalent among university students, yet there is a lack of effective models to assess the risk of sleep disturbance. Artificial intelligence (AI) provides an opportunity to develop a platform for evaluating the risk. This study aims to develop and validate an AI platform to stratify the risk of experiencing sleep disturbance for university students.

Methods

A total of 2243 university students were included, with 1882 students from five universities comprising the model derivation group and 361 students from two additional universities forming the external validation group. Six machine learning techniques, including extreme gradient boosting machine (eXGBM), decision tree (DT), k-nearest neighbor (KNN), random forest (RF), neural network (NN), and support vector machine (SVM), were employed to train models using the same set of features. The models' prediction performance was assessed based on discrimination and calibration, and feature importance was determined using Shapley Additive exPlanations (SHAP) analysis.

Results

The prevalence of sleep disturbance was 44.69% in the model derivation group and 49.58% in the external validation group. Among the developed models, eXGBM exhibited superior performance, surpassing other models in metrics such as area under the curve (0.779, 95% CI: 0.728-0.830), accuracy (0.710), precision (0.737), F1 score (0.692), Brier score (0.193), and log loss (0.569). Calibration and decision curve analyses demonstrated favorable calibration ability and clinical net benefits, respectively. SHAP analysis identified five key features: stress score, severity of depression, vegetable consumption, age, and sedentary time. The AI platform was made available online at https://sleepdisturbancestudents-xakgzwectsw85cagdgkax9.streamlit.app/, enabling users to calculate individualized risk of sleep disturbance.

Conclusion

Sleep disturbance is prevalent among university students. This study presents an AI model capable of identifying students at high risk for sleep disturbance. The AI platform offers a valuable resource to guide interventions and improve sleep outcomes for university students.

Artificial Intelligence Models for the Automation of Standard Diagnostics in Sleep Medicine-A Systematic Review

Sleep disorders, prevalent in the general population, present significant health challenges. The current diagnostic approach, based on a manual analysis of overnight polysomnograms (PSGs), is costly and time-consuming. Artificial intelligence has emerged as a promising tool in this context, offering a more accessible and personalized approach to diagnosis, particularly beneficial for under-served populations. This is a systematic review of AI-based models for sleep disorder diagnostics that were trained, validated, and tested on diverse clinical datasets. An extensive search of PubMed and IEEE databases yielded 2114 articles, but only 18 met our stringent selection criteria, underscoring the scarcity of thoroughly validated AI models in sleep medicine. The findings emphasize the necessity of a rigorous validation of AI models on multimodal clinical data, a step crucial for their integration into clinical practice. This would be in line with the American Academy of Sleep Medicine's support of AI research.

Artificial intelligence in sleep medicine: Present and future

Artificial intelligence (AI) has impacted many areas of healthcare. AI in healthcare uses machine learning, deep learning, and natural language processing to analyze copious amounts of healthcare data and yield valuable outcomes. In the sleep medicine field, a large amount of physiological data is gathered compared to other branches of medicine. This field is primed for innovations with the help of AI. A good quality of sleep is crucial for optimal health. About one billion people are estimated to have obstructive sleep apnea worldwide, but it is difficult to diagnose and treat all the people with limited resources. Sleep apnea is one of the major contributors to poor health. Most of the sleep apnea patients remain undiagnosed. Those diagnosed with sleep apnea have difficulty getting it optimally treated due to several factors, and AI can help in this situation. AI can also help in the diagnosis and management of other sleep disorders such as insomnia, hypersomnia, parasomnia, narcolepsy, shift work sleep disorders, periodic leg movement disorders, etc. In this manuscript, we aim to address three critical issues about the use of AI in sleep medicine: (1) How can AI help in diagnosing and treating sleep disorders? (2) How can AI fill the gap in the care of sleep disorders? and (3) What are the ethical and legal considerations of using AI in sleep medicine?

Perspective: A resident's role in promoting safe machine-learning tools in sleep medicine

Residents and fellows can play a helpful role in promoting safe and effective machine-learning tools in sleep medicine. Here we highlight the importance of establishing ground truths, considering key variables, and prioritizing transparency and accountability in the development of machine-learning tools within the field of artificial intelligence. Through understanding, communication, and collaboration, in-training physicians have a meaningful opportunity to help progress the field toward safe machine-learning tools in sleep medicine.

CITATION

Smith CM, Vendrame M. Perspective: a resident's role in promoting safe machine-learning tools in sleep medicine. J Clin Sleep Med. 2023;19(11):1985-1987.

Consumer Wearable Sleep Trackers: Are They Ready for Clinical Use?

As the importance of good sleep continues to gain public recognition, the market for sleep-monitoring devices continues to grow. Modern technology has shifted from simple sleep tracking to a more granular sleep health assessment. We examine the available functionalities of consumer wearable sleep trackers (CWSTs) and how they perform in healthy individuals and disease states. Additionally, the continuum of sleep technology from consumer-grade to medical-grade is detailed. As this trend invariably grows, we urge professional societies to develop guidelines encompassing the practical clinical use of CWSTs and how best to incorporate them into patient care plans.

Obstructive sleep apnea event detection using explainable deep learning models for a portable monitor

Background

Polysomnography (PSG) is the gold standard for detecting obstructive sleep apnea (OSA). However, this technique has many disadvantages when using it outside the hospital or for daily use. Portable monitors (PMs) aim to streamline the OSA detection process through deep learning (DL).

Materials and methods

We studied how to detect OSA events and calculate the apnea-hypopnea index (AHI) by using deep learning models that aim to be implemented on PMs. Several deep learning models are presented after being trained on polysomnography data from the National Sleep Research Resource (NSRR) repository. The best hyperparameters for the DL architecture are presented. In addition, emphasis is focused on model explainability techniques, concretely on Gradient-weighted Class Activation Mapping (Grad-CAM).

Results

The results for the best DL model are presented and analyzed. The interpretability of the DL model is also analyzed by studying the regions of the signals that are most relevant for the model to make the decision. The model that yields the best result is a one-dimensional convolutional neural network (1D-CNN) with 84.3% accuracy.

Conclusion

The use of PMs using machine learning techniques for detecting OSA events still has a long way to go. However, our method for developing explainable DL models demonstrates that PMs appear to be a promising alternative to PSG in the future for the detection of obstructive apnea events and the automatic calculation of AHI.

Subject-level Normalization to Improve A-phase Detection of Cyclic Alternating Pattern in Sleep EEG

Automatic detection systems for activation phases (A-phase) of the cyclic alternating pattern (CAP) in electroencephalograms (EEG) are designed to automatically score A-phases in any individual but typically fail to factor in EEG signal variations between individuals, e.g. due to sleep disorders, recording site differences or equipment differences. Here, we investigate the effect of subject-level normalization on the performance of an automatic A-phase detection system consisting of a recurrent neural network. We compared the classification performance of various subject-level normalization methods to the standard training set normalization. Systems were trained and tested on subjects with different sleep disorders using the publicly available CAP Sleep Database on Physionet. Subject-level normalization using Zscore or median and interquartile range (IQR) increases the F1-score for A1-phases by +11-22% (Z-Score: +11-20%, Median/IQR: +16-22%), for A2-phases by +2-9% (Z-Score: +59%, Median/IQR: +2-7%), for A3-phases by -1 - +8% (Z-Score: +3-8%, Median/IQR: -1-+5%) as compared to the standard training data normalization when tested across sleep disorders. Our results show that subject-level normalization drastically improves the precision of A-phase detection in case the training population differs from the testing population.Clinical Relevance- Subject-level normalisation improves the automatic CAP scoring system performances for the general population by minimizing the effect of individual EEG differences.

Clinical applications of artificial intelligence in sleep medicine: a sleep clinician's perspective

BACKGROUND

The past few years have seen a rapid emergence of artificial intelligence (AI)-enabled technology in the field of sleep medicine. AI refers to the capability of computer systems to perform tasks conventionally considered to require human intelligence, such as speech recognition, decision-making, and visual recognition of patterns and objects. The practice of sleep tracking and measuring physiological signals in sleep is widely practiced. Therefore, sleep monitoring in both the laboratory and ambulatory environments results in the accrual of massive amounts of data that uniquely positions the field of sleep medicine to gain from AI.

METHOD

The purpose of this article is to provide a concise overview of relevant terminology, definitions, and use cases of AI in sleep medicine. This was supplemented by a thorough review of relevant published literature.

RESULTS

Artificial intelligence has several applications in sleep medicine including sleep and respiratory event scoring in the sleep laboratory, diagnosing and managing sleep disorders, and population health. While still in its nascent stage, there are several challenges which preclude AI's generalizability and wide-reaching clinical applications. Overcoming these challenges will help integrate AI seamlessly within sleep medicine and augment clinical practice.

CONCLUSION

Artificial intelligence is a powerful tool in healthcare that may improve patient care, enhance diagnostic abilities, and augment the management of sleep disorders. However, there is a need to regulate and standardize existing machine learning algorithms prior to its inclusion in the sleep clinic.

Differentiation of central disorders of hypersomnolence with manual and artificial-intelligence-derived polysomnographic measures

Differentiation of central disorders of hypersomnolence (DOH) is challenging but important for patient care. This study aimed to investigate whether biomarkers derived from sleep structure evaluated both by manual scoring as well as with artificial intelligence (AI) algorithms allow distinction of patients with different DOH. We included video-polysomnography data of 40 narcolepsy type 1 (NT1), 26 narcolepsy type 2 (NT2), 23 patients with idiopathic hypersomnia (IH) and 54 participants with subjective excessive daytime sleepiness (sEDS). Sleep experts manually scored sleep stages. A previously validated AI algorithm was employed to obtain automatic hypnograms and hypnodensity graphs (where each epoch is represented as a mixture of sleep stage probabilities). One-thousand-three features describing sleep architecture and instability were extracted from manual/automatic hypnogram and hypnodensity graphs. After feature selection, random forest classifiers were trained and tested in a 5-fold-cross-validation scheme to distinguish groups pairwise (NT1-vs-NT2, NT1-vs-IH, …) and single groups from the pooled remaining ones (NT1-vs-rest, NT2-vs-rest,…). The accuracy/F1-score values obtained in the test sets were: 0.74 ± 0.04/0.79 ± 0.05 (NT1-vs-NT2), 0.89 ± 0.09/0.91 ± 0.08 (NT1-vs-IH), 0.93 ± 0.06/0.91 ± 0.07 (NT1-vs-sEDS), 0.88 ± 0.04/0.80 ± 0.07 (NT1-vs-rest), 0.65 ± 0.10/0.70 ± 0.09 (NT2-vs-IH), 0.72 ± 0.12/0.60 ± 0.10 (NT2-vs-sEDS), 0.54 ± 0.19/0.38 ± 0.13 (NT2-vs-rest), 0.57 ± 0.11/0.35 ± 0.18 (IH-vs-sEDS), 0.71 ± 0.08/0.35 ± 0.10 (IH-vs-rest) and 0.76 ± 0.08/0.71 ± 0.13 (sEDS-vs-rest). The results confirm previous findings on sleep instability in patients with NT1 and show that combining manual and automatic AI-based sleep analysis could be useful for better distinction of NT2 from IH, but no precise sleep biomarker of NT2 or IH could be identified. Validation in a larger and multi-centric cohort is needed to confirm these findings.

Clinical validation of a mandibular movement signal based system for the diagnosis of pediatric sleep apnea

BACKGROUND

Given the high prevalence and risk for outcomes associated with pediatric obstructive sleep apnea (OSA), there is a need for simplified diagnostic approaches. A prospective study in 140 children undergoing in-laboratory polysomnography (PSG) evaluates the accuracy of a recently developed system (Sunrise) to estimate respiratory efforts by monitoring sleep mandibular movements (MM) for the diagnosis of OSA (Sunrise™).

METHODS

Diagnosis and severity were defined by an obstructive apnea/hypopnea index (OAHI) ≥ 1 (mild), ≥ 5 (moderate), and ≥ 10 events/h (severe). Agreement between PSG and Sunrise™ was assessed by Bland-Altman method comparing respiratory disturbances hourly index (RDI) (obstructive apneas, hypopneas, and respiratory effort-related arousals) during PSG (PSG_RDI), and Sunrise RDI (Sr_RDI). Performance of Sr_RDI was determined via ROC curves evaluating the device sensitivity and specificity at PSG_OAHI ≥ 1, 5, and 15 events/h.

RESULTS

A median difference of 1.57 events/h, 95% confidence interval: -2.49 to 8.11 was found between Sr_RDI and PSG_RDI. Areas under the ROC curves of Sr_RDI were 0.75 (interquartile range [IQR]: 0.72-0.78), 0.90 (IQR: 0.86-0.92) and 0.95 (IQR: 0.90-0.99) for detecting children with PSG_OAHI ≥ 1, PSG_OAHI ≥ 5, or PSG_ OAHI ≥ 10, respectively.

CONCLUSION

MM automated analysis shows significant promise to diagnose moderate-to-severe pediatric OSA.

The Sleep Revolution project: the concept and objectives

Obstructive sleep apnea is linked to severe health consequences such as hypertension, daytime sleepiness, and cardiovascular disease. Nearly a billion people are estimated to have obstructive sleep apnea with a substantial economic burden. However, the current diagnostic parameter of obstructive sleep apnea, the apnea-hypopnea index, correlates poorly with related comorbidities and symptoms. Obstructive sleep apnea severity is measured by counting respiratory events, while other physiologically relevant consequences are ignored. Furthermore, as the clinical methods for analysing polysomnographic signals are outdated, laborious, and expensive, most patients with obstructive sleep apnea remain undiagnosed. Therefore, more personalised diagnostic approaches are urgently needed. The Sleep Revolution, funded by the European Union's Horizon 2020 Research and Innovation Programme, aims to tackle these shortcomings by developing machine learning tools to better estimate obstructive sleep apnea severity and phenotypes. This allows for improved personalised treatment options, including increased patient participation. Also, implementing these tools will alleviate the costs and increase the availability of sleep studies by decreasing manual scoring labour. Finally, the project aims to design a digital platform that functions as a bridge between researchers, patients, and clinicians, with an electronic sleep diary, objective cognitive tests, and questionnaires in a mobile application. These ambitious goals will be achieved through extensive collaboration between 39 centres, including expertise from sleep medicine, computer science, and industry and by utilising tens of thousands of retrospectively and prospectively collected sleep recordings. With the commitment of the European Sleep Research Society and Assembly of National Sleep Societies, the Sleep Revolution has the unique possibility to create new standardised guidelines for sleep medicine.

Video-polysomnography procedures for diagnosis of rapid eye movement sleep behavior disorder (RBD) and the identification of its prodromal stages: guidelines from the International RBD Study Group

Video-polysomnography (v-PSG) is essential for diagnosing rapid eye movement (REM) sleep behavior disorder (RBD). Although there are current American Academy of Sleep Medicine standards to diagnose RBD, several aspects need to be addressed to achieve harmonization across sleep centers. Prodromal RBD is a stage in which symptoms and signs of evolving RBD are present, but do not yet meet established diagnostic criteria for RBD. However, the boundary between prodromal and definite RBD is still unclear. As a common effort of the Neurophysiology Working Group of the International RBD Study Group, this manuscript addresses the need for comprehensive and unambiguous v-PSG recommendations to diagnose RBD and identify prodromal RBD. These include: (1) standardized v-PSG technical settings; (2) specific considerations for REM sleep scoring; (3) harmonized methods for scoring REM sleep without atonia; (4) consistent methods to analyze video and audio recorded during v-PSGs and to classify movements and vocalizations; (5) clear v-PSG guidelines to diagnose RBD and identify prodromal RBD. Each section follows a common template: The current recommendations and methods are presented, their limitations are outlined, and new recommendations are described. Finally, future directions are presented. These v-PSG recommendations are intended for both practicing clinicians and researchers. Classification and quantification of motor events, RBD episodes, and vocalizations are however intended for research purposes only. These v-PSG guidelines will allow collection of homogeneous data, providing objective v-PSG measures and making future harmonized multicentric studies and clinical trials possible.

A Clinical Decision Support System for Sleep Staging Tasks With Explanations From Artificial Intelligence: User-Centered Design and Evaluation Study

Background

Despite the unprecedented performance of deep learning algorithms in clinical domains, full reviews of algorithmic predictions by human experts remain mandatory. Under these circumstances, artificial intelligence (AI) models are primarily designed as clinical decision support systems (CDSSs). However, from the perspective of clinical practitioners, the lack of clinical interpretability and user-centered interfaces hinders the adoption of these AI systems in practice.

Objective

This study aims to develop an AI-based CDSS for assisting polysomnographic technicians in reviewing AI-predicted sleep staging results. This study proposed and evaluated a CDSS that provides clinically sound explanations for AI predictions in a user-centered manner.

Methods

Our study is based on a user-centered design framework for developing explanations in a CDSS that identifies why explanations are needed, what information should be contained in explanations, and how explanations can be provided in the CDSS. We conducted user interviews, user observation sessions, and an iterative design process to identify three key aspects for designing explanations in the CDSS. After constructing the CDSS, the tool was evaluated to investigate how the CDSS explanations helped technicians. We measured the accuracy of sleep staging and interrater reliability with macro-F1 and Cohen κ scores to assess quantitative improvements after our tool was adopted. We assessed qualitative improvements through participant interviews that established how participants perceived and used the tool.

Results

The user study revealed that technicians desire explanations that are relevant to key electroencephalogram (EEG) patterns for sleep staging when assessing the correctness of AI predictions. Here, technicians wanted explanations that could be used to evaluate whether the AI models properly locate and use these patterns during prediction. On the basis of this, information that is closely related to sleep EEG patterns was formulated for the AI models. In the iterative design phase, we developed a different visualization strategy for each pattern based on how technicians interpreted the EEG recordings with these patterns during their workflows. Our evaluation study on 9 polysomnographic technicians quantitatively and qualitatively investigated the helpfulness of the tool. For technicians with <5 years of work experience, their quantitative sleep staging performance improved significantly from 56.75 to 60.59 with a P value of .05. Qualitatively, participants reported that the information provided effectively supported them, and they could develop notable adoption strategies for the tool.

Conclusions

Our findings indicate that formulating clinical explanations for automated predictions using the information in the AI with a user-centered design process is an effective strategy for developing a CDSS for sleep staging.

Current and future strategies for diagnostic and management of obstructive sleep apnea

INTRODUCTION

Obstructive sleep apnea (OSA) is a common sleep disorder with multiple comorbidities including hypertension, diabetes, and cardiovascular disorders. Detected based on an overnight sleep study is called polysomnography (PSG); OSA still remains undiagnosed in majority of the population mainly attributed to lack of awareness. To overcome the limitations posed by PSG such as patient discomfort and overnight hospitalization, newer technologies are being explored. In addition, challenges associated with current management of OSA using continuous positive airway pressure (CPAP), etc. presents several pitfalls.

AREAS COVERED

Conventional and modern detection/management techniques including PSG, CPAP, smart wearable/pillows, bio-motion sensors, etc., have both pros and cons. To fulfill the limitations in OSA diagnostics, there is an imperative need for new technology for screening of symptomatic and more importantly asymptomatic OSA patients to reduce the risk of several associated life-threatening comorbidities. In this line, molecular marker-based diagnostics have shown great promises.

EXPERT OPINION

A detailed overview is presented on the OSA management and diagnostic approaches and recent advances in the molecular screening methods. The potentials of biomarker-based detection and its limitations are also portrayed and a comparison between the standard, current modern approaches, and promising futuristic technologies for OSA diagnostics and management is set forth.ABBREVIATIONS AHI: Apnea hypopnea index; AI: artificial intelligence; CAM: Cell adhesion molecules; CPAP: Continuous Positive Airway Pressure; COVID-19: Coronavirus Disease 2019; CVD: Cardiovascular disease; ELISA: Enzyme linked immunosorbent assay; HSAT: Home sleep apnea testing; IR-UWB: Impulse radio-ultra wideband; MMA: maxillomandibular advancement; PSG: Polysomnography; OSA: Obstructive sleep apnea; SOD: Superoxide dismutase; QD: Quantum dot.

Machine learning-based prediction of adherence to continuous positive airway pressure (CPAP) in obstructive sleep apnea (OSA)

Continuous positive airway pressure (CPAP) is the "gold-standard" therapy for obstructive sleep apnea (OSA), but the main problem is the poor adherence. Therefore, we have searched for the causes of poor adherence to CPAP therapy by applying predictive machine learning (ML) methods. The study was conducted on OSAs in nighttime therapy with CPAP. An outpatient follow-up was planned at 3, 6, 12 months. We collected several parameters at the baseline visit and after dividing all patients into two groups (Adherent and Non-adherent) according to therapy adherence, we compared them. Statistical differences between the two groups were not found according to baseline characteristics, except gender (P< .01). Therefore, we applied ML to predict CPAP adherence, and these predictive models showed an accuracy and sensitivity of 68.6% and an AUC (area under the curve) of 72.9% through the SVM (support vector machine) classification method. The identification of factors predictive of long-term CPAP adherence is complex, but our proof of concept seems to demonstrate the utility of ML to identify subjects poorly adherent to therapy. Therefore, application of these models to larger samples could aid in the careful identification of these subjects and result in important savings in healthcare spending.

Evaluation of Automated Hypnogram Analysis on Multi-Scored Polysomnographies

A new method for automated sleep stage scoring of polysomnographies is proposed that uses a random forest approach to model feature interactions and temporal effects. The model mostly relies on features based on the rules from the American Academy of Sleep Medicine, which allows medical experts to gain insights into the model. A common way to evaluate automated approaches to constructing hypnograms is to compare the one produced by the algorithm to an expert's hypnogram. However, given the same data, two expert annotators will construct (slightly) different hypnograms due to differing interpretations of the data or individual mistakes. A thorough evaluation of our method is performed on a multi-labeled dataset in which both the inter-rater variability as well as the prediction uncertainties are taken into account, leading to a new standard for the evaluation of automated sleep stage scoring algorithms. On all epochs, our model achieves an accuracy of 82.7%, which is only slightly lower than the inter-rater disagreement. When only considering the 63.3% of the epochs where both the experts and algorithm are certain, the model achieves an accuracy of 97.8%. Transition periods between sleep stages are identified and studied for the first time. Scoring guidelines for medical experts are provided to complement the certain predictions by scoring only a few epochs manually. This makes the proposed method highly time-efficient while guaranteeing a highly accurate final hypnogram.

Towards Validating the Effectiveness of Obstructive Sleep Apnea Classification from Electronic Health Records Using Machine Learning

Obstructive sleep apnea (OSA) is a common, chronic, sleep-related breathing disorder characterized by partial or complete airway obstruction in sleep. The gold standard diagnosis method is polysomnography, which estimates disease severity through the Apnea-Hypopnea Index (AHI). However, this is expensive and not widely accessible to the public. For effective screening, this work implements machine learning algorithms for classification of OSA. The model is trained with routinely acquired clinical data of 1479 records from the Wisconsin Sleep Cohort dataset. Extracted features from the electronic health records include patient demographics, laboratory blood reports, physical measurements, habitual sleep history, comorbidities, and general health questionnaire scores. For distinguishing between OSA and non-OSA patients, feature selection methods reveal the primary important predictors as waist-to-height ratio, waist circumference, neck circumference, body-mass index, lipid accumulation product, excessive daytime sleepiness, daily snoring frequency and snoring volume. Optimal hyperparameters were selected using a hybrid tuning method consisting of Bayesian Optimization and Genetic Algorithms through a five-fold cross-validation strategy. Support vector machines achieved the highest evaluation scores with accuracy: 68.06%, sensitivity: 88.76%, specificity: 40.74%, F1-score: 75.96%, PPV: 66.36% and NPV: 73.33%. We conclude that routine clinical data can be useful in prioritization of patient referral for further sleep studies.

An LSTM Network for Apnea and Hypopnea Episodes Detection in Respiratory Signals

One of the most common sleep disorders is sleep apnea. It manifests itself by episodes of shallow breathing or pauses in breathing during the night. Diagnosis of this disease involves polysomnography examination, which is expensive. Alternatively, diagnostic doctors can be supported with recordings from the in-home polygraphy sensors. Furthermore, numerous attempts for providing an automated apnea episodes annotation algorithm have been made. Most of them, however, do not distinguish between apnea and hypopnea episodes. In this work, a novel solution for epoch-based annotation problem is presented. Utilizing an architecture based on the long short-term memory (LSTM) networks, the proposed model provides locations of sleep disordered breathing episodes and identifies them as either apnea or hypopnea. To achieve this, special pre- and postprocessing steps have been designed. The obtained labels can be then used for calculation of the respiratory event index (REI), which serves as a disease severity indicator. The input for the model consists of the oronasal airflow along with the thoracic and abdominal respiratory effort signals. Performance of the proposed architecture was verified on the SHHS-1 and PhysioNet Sleep databases, obtaining mean REI classification error of 9.24/10.52 with standard deviation of 11.61/7.92 (SHHS-1/PhysioNet). Normal breathing, hypopnea and apnea differentiation accuracy is assessed on both databases, resulting in the correctly classified samples percentage of 86.42%/84.35%, 49.30%/58.28% and 68.20%/69.50% for normal breathing, hypopnea and apnea classes, respectively. Overall accuracies are 80.66%/82.04%. Additionally, the effect of wake periods is investigated. The results show that the proposed model can be successfully used for both episode classification and REI estimation tasks.

Digital phenotyping of sleep patterns among heterogenous samples of Latinx adults using unsupervised learning

OBJECTIVE

This study aimed to identify sleep disturbance subtypes ("phenotypes") among Latinx adults based on objective sleep data using a flexible unsupervised machine learning technique.

METHODS

This study was an analysis of sleep data from three cross-sectional studies of the Precision in Symptom Self-Management Center at Columbia University. All studies focused on sleep health in Latinx adults at increased risk for sleep disturbance. Data on total sleep time (TST), time in bed (TIB), wake after sleep onset (WASO), sleep efficiency (SE), number of awakenings (NOA) and the mean length of nightly awakenings were collected using wrist-mounted accelerometers. Cluster analysis of the sleep data was conducted using an unsupervised machine learning approach that relies on mixtures of multivariate generalized linear mixed models.

RESULTS

The analytic sample included 494 days of data from 118 adults (Ages 19-77). A 3-cluster model provided the best fit based on deviance indices (ie, DΔ∼ -75 and -17 from 1- and 2- to 3-cluster models, respectively) and likelihood ratio (P_diff ∼ 0.93). Phenotype 1 (n = 64) was associated with greater likelihood of overall adequate SE and less variability in SE and WASO. Phenotype 2 (n = 11) was characterized by higher NOAs, and greater WASO and TIB than the other phenotypes. Phenotype 3 (n = 43) was characterized by greater variability in SE, bed times and awakening times.

CONCLUSION

Robust digital data-driven modeling approaches can be useful for detecting sleep phenotypes from heterogenous patient populations, and have implications for designing precision sleep health strategies for management and early detection of sleep problems.

Artificial Intelligence Analysis of EEG Amplitude in Intensive Heart Care

This article first studied the morphological characteristics of the EEG for intensive cardiac care; that is, based on the analysis of the mechanism of disease diagnosis and treatment, a signal processing and machine learning model was constructed. Then, the methods of signal preprocessing, signal feature extraction, new neural network model structure, training mechanism, optimization algorithm, and efficiency are studied, and experimental verification is carried out for public data sets and clinical big data. Then, the principle of intensive cardiac monitoring, the mechanism of disease diagnosis, the types of arrhythmia, and the characteristics of the typical signal are studied, and the rhythm performance, individual variability, and neurophysiological basis of electrical signals in intensive cardiac monitoring are researched. Finally, the automatic signal recognition technology is studied. In order to improve the training speed and generalization ability, a multiclassification model based on Least Squares Twin Support Vector Machine (LS-TWIN-SVM) is proposed. The computational complexity of the classification model algorithm is compared, and intelligence is adopted. The optimization algorithm selects the parameters of the classifier and uses the EEG signal to simulate the model. Support Vector Machines and their improved algorithms have achieved the ultimum in shallow neural networks and have achieved good results in the classification and recognition of bioelectric signals. The LS-TWIN-SVM algorithm proposed in this paper has achieved good results in the classification and recognition of bioelectric signals. It can perform bioinformatics processing on intensive cardiac care EEG signals, systematically biometric information, diagnose diseases, the real-time detection, auxiliary diagnosis, and rehabilitation of patients.

Interrater sleep stage scoring reliability between manual scoring from two European sleep centers and automatic scoring performed by the artificial intelligence-based Stanford-STAGES algorithm

STUDY OBJECTIVES

The objective of this study was to evaluate interrater reliability between manual sleep stage scoring performed in 2 European sleep centers and automatic sleep stage scoring performed by the previously validated artificial intelligence-based Stanford-STAGES algorithm.

METHODS

Full night polysomnographies of 1,066 participants were included. Sleep stages were manually scored in Berlin and Innsbruck sleep centers and automatically scored with the Stanford-STAGES algorithm. For each participant, we compared (1) Innsbruck to Berlin scorings (INN vs BER); (2) Innsbruck to automatic scorings (INN vs AUTO); (3) Berlin to automatic scorings (BER vs AUTO); (4) epochs where scorers from Innsbruck and Berlin had consensus to automatic scoring (CONS vs AUTO); and (5) both Innsbruck and Berlin manual scorings (MAN) to the automatic ones (MAN vs AUTO). Interrater reliability was evaluated with several measures, including overall and sleep stage-specific Cohen's κ.

RESULTS

Overall agreement across participants was substantial for INN vs BER (κ = 0.66 ± 0.13), INN vs AUTO (κ = 0.68 ± 0.14), CONS vs AUTO (κ = 0.73 ± 0.14), and MAN vs AUTO (κ = 0.61 ± 0.14), and moderate for BER vs AUTO (κ = 0.55 ± 0.15). Human scorers had the highest disagreement for N1 sleep (κ_N1 = 0.40 ± 0.16 for INN vs BER). Automatic scoring had lowest agreement with manual scorings for N1 and N3 sleep (κ_N1 = 0.25 ± 0.14 and κ_N3 = 0.42 ± 0.32 for MAN vs AUTO).

CONCLUSIONS

Interrater reliability for sleep stage scoring between human scorers was in line with previous findings, and the algorithm achieved an overall substantial agreement with manual scoring. In this cohort, the Stanford-STAGES algorithm showed similar performances to the ones achieved in the original study, suggesting that it is generalizable to new cohorts. Before its integration in clinical practice, future independent studies should further evaluate it in other cohorts.

Machine learning for image-based detection of patients with obstructive sleep apnea: an exploratory study

PURPOSE

In 2-dimensional lateral cephalometric radiographs, patients with severe obstructive sleep apnea (OSA) exhibit a more crowded oropharynx in comparison with non-OSA. We tested the hypothesis that machine learning, an application of artificial intelligence (AI), could be used to detect patients with severe OSA based on 2-dimensional images.

METHODS

A deep convolutional neural network was developed (n = 1258; 90%) and tested (n = 131; 10%) using data from 1389 (100%) lateral cephalometric radiographs obtained from individuals diagnosed with severe OSA (n = 867; apnea hypopnea index > 30 events/h sleep) or non-OSA (n = 522; apnea hypopnea index < 5 events/h sleep) at a single center for sleep disorders. Three kinds of data sets were prepared by changing the area of interest using a single image: the original image without any modification (full image), an image containing a facial profile, upper airway, and craniofacial soft/hard tissues (main region), and an image containing part of the occipital region (head only). A radiologist also performed a conventional manual cephalometric analysis of the full image for comparison.

RESULTS

The sensitivity/specificity was 0.87/0.82 for full image, 0.88/0.75 for main region, 0.71/0.63 for head only, and 0.54/0.80 for the manual analysis. The area under the receiver-operating characteristic curve was the highest for main region 0.92, for full image 0.89, for head only 0.70, and for manual cephalometric analysis 0.75.

CONCLUSIONS

A deep convolutional neural network identified individuals with severe OSA with high accuracy. Future research on this concept using AI and images can be further encouraged when discussing triage of OSA.

Confidence-Based Framework Using Deep Learning for Automated Sleep Stage Scoring

STUDY OBJECTIVES

Automated sleep stage scoring is not yet vigorously used in practice because of the black-box nature and the risk of wrong predictions. The objective of this study was to introduce a confidence-based framework to detect the possibly wrong predictions that would inform clinicians about which epochs would require a manual review and investigate the potential to improve accuracy for automated sleep stage scoring.

METHODS

We used 702 polysomnography studies from a local clinical dataset (SNUBH dataset) and 2804 from an open dataset (SHHS dataset) for experiments. We adapted the state-of-the-art TinySleepNet architecture to train the classifier and modified the ConfidNet architecture to train an auxiliary confidence model. For the confidence model, we developed a novel method, Dropout Correct Rate (DCR), and the performance of it was compared with other existing methods.

RESULTS

Confidence estimates (0.754) reflected accuracy (0.758) well in general. The best performance for differentiating correct and wrong predictions was shown when using the DCR method (AUROC: 0.812) compared to the existing approaches which largely failed to detect wrong predictions. By reviewing only 20% of epochs that received the lowest confidence values, the overall accuracy of sleep stage scoring was improved from 76% to 87%. For patients with reduced accuracy (ie, individuals with obesity or severe sleep apnea), the possible improvement range after applying confidence estimation was even greater.

CONCLUSION

To the best of our knowledge, this is the first study applying confidence estimation on automated sleep stage scoring. Reliable confidence estimates by the DCR method help screen out most of the wrong predictions, which would increase the reliability and interpretability of automated sleep stage scoring.

Recent Advances in the Application of Artificial Intelligence in Otorhinolaryngology-Head and Neck Surgery

This study presents an up-to-date survey of the use of artificial intelligence (AI) in the field of otorhinolaryngology, considering opportunities, research challenges, and research directions. We searched PubMed, the Cochrane Central Register of Controlled Trials, Embase, and the Web of Science. We initially retrieved 458 articles. The exclusion of non-English publications and duplicates yielded a total of 90 remaining studies. These 90 studies were divided into those analyzing medical images, voice, medical devices, and clinical diagnoses and treatments. Most studies (42.2%, 38/90) used AI for image-based analysis, followed by clinical diagnoses and treatments (24 studies). Each of the remaining two subcategories included 14 studies. Machine learning and deep learning have been extensively applied in the field of otorhinolaryngology. However, the performance of AI models varies and research challenges remain.