arXiv subjects

Thomas Penzel

Publications and source records attributed to Thomas Penzel.

12 recordsLinked to original sources

arXiv2026

The Breakthrough of Sleep: A Contactless Approach for Accurate Sleep Stage Detection Using the Sleepal AI Lamp

Sleep staging is essential for the assessment of sleep quality and the diagnosis of sleep-related disorders. Conventional polysomnography (PSG), while considered the gold standard, is intrusive, labor-intensive, and unsuitable for long-term monitoring. This study evaluates the performance of the Sleepal AI Lamp, a contactless, radar-based consumer-grade sleep tracker, in comparison with gold-standard polysomnography (PSG), using a large-scale dataset comprising 1022 overnight recordings. We extract multi-scale respiratory and motion-related features from radar signals to train a frequency-augmented deep learning model. For the binary sleep-wake classification task, experimental results demonstrated that the model achieved an accuracy of 92.8% alongside a macro-averaged F1 score of 0.895. For four-stage classification (wake, light NREM (N1 + N2), deep NREM (N3), REM), the model achieved an accuracy of 78.5% with a Cohen's kappa coefficient of 0.695 in healthy individuals and maintained a stable accuracy of 77.2% with a kappa of 0.677 in a heterogeneous population including patients with varying severities of obstructive sleep apnea (OSA). These experimental results demonstrate that the sleep staging performance of the contactless Sleepal AI Lamp is in high agreement with expert-labeled PSG sleep stages. Our findings suggest that non-contact radar sensing, combined with advanced temporal modeling, can provide reliable sleep staging performance without requiring physical contact or wearable devices. Owing to its unobtrusive nature, ease of deployment, and robustness to long-term use, the contactless Sleepal AI Lamp shows strong potential for clinical screening, home-based sleep assessment, and continuous longitudinal sleep monitoring in real-world medical and healthcare applications.

eess.SP↗

arXiv2026

Holter-to-Sleep: AI-Enabled Repurposing of Single-Lead ECG for Sleep Phenotyping

Sleep disturbances are tightly linked to cardiovascular risk, yet polysomnography (PSG)-the clinical reference standard-remains resource-intensive and poorly suited for multi-night, home-based, and large-scale screening. Single-lead electrocardiography (ECG), already ubiquitous in Holter and patch-based devices, enables comfortable long-term acquisition and encodes sleep-relevant physiology through autonomic modulation and cardiorespiratory coupling. Here, we present a proof-of-concept Holter-to-Sleep framework that, using single-lead ECG as the sole input, jointly supports overnight sleep phenotyping and Holter-grade cardiac phenotyping within the same recording, and further provides an explicit analytic pathway for scalable cardio-sleep association studies. The framework is developed and validated on a pooled multi-center PSG sample of 10,439 studies spanning four public cohorts, with independent external evaluation to assess cross-cohort generalizability, and additional real-world feasibility assessment using overnight patch-ECG recordings via objective-subjective consistency analysis. This integrated design enables robust extraction of clinically meaningful overnight sleep phenotypes under heterogeneous populations and acquisition conditions, and facilitates systematic linkage between ECG-derived sleep metrics and arrhythmia-related Holter phenotypes. Collectively, the Holter-to-Sleep paradigm offers a practical foundation for low-burden, home-deployable, and scalable cardio-sleep monitoring and research beyond traditional PSG-centric workflows.

eess.SP↗

arXiv2025

World of ScoreCraft: Novel Multi Scorer Experiment on the Impact of a Decision Support System in Sleep Staging

Manual scoring of polysomnography (PSG) is a time intensive task, prone to inter scorer variability that can impact diagnostic reliability. This study investigates the integration of decision support systems (DSS) into PSG scoring workflows, focusing on their effects on accuracy, scoring time, and potential biases toward recommendations from artificial intelligence (AI) compared to human generated recommendations. Using a novel online scoring platform, we conducted a repeated measures study with sleep technologists, who scored traditional and self applied PSGs. Participants were occasionally presented with recommendations labeled as either human or AI generated. We found that traditional PSGs tended to be scored slightly more accurately than self applied PSGs, but this difference was not statistically significant. Correct recommendations significantly improved scoring accuracy for both PSG types, while incorrect recommendations reduced accuracy. No significant bias was observed toward or against AI generated recommendations compared to human generated recommendations. These findings highlight the potential of AI to enhance PSG scoring reliability. However, ensuring the accuracy of AI outputs is critical to maximizing its benefits. Future research should explore the long term impacts of DSS on scoring workflows and strategies for integrating AI in clinical practice.

cs.HC↗

arXiv2024

NeuroSleepNet: A Multi-Head Self-Attention Based Automatic Sleep Scoring Scheme with Spatial and Multi-Scale Temporal Representation Learning

Objective: Automatic sleep scoring is crucial for diagnosing sleep disorders. Existing frameworks based on Polysomnography often rely on long sequences of input signals to predict sleep stages, which can introduce complexity. Moreover, there is limited exploration of simplifying representation learning in sleep scoring methods. Methods: In this study, we propose NeuroSleepNet, an automatic sleep scoring method designed to classify the current sleep stage using only the microevents in the current input signal, without the need for past inputs. Our model employs supervised spatial and multi-scale temporal context learning and incorporates a transformer encoder to enhance representation learning. Additionally, NeuroSleepNet is optimized for balanced performance across five sleep stages by introducing a logarithmic scale-based weighting technique as a loss function. Results: NeuroSleepNet achieved similar and comparable performance with current state-of-the-art results. The best accuracy, macro-F1 score, and Cohen's kappa were 86.1 percent, 80.8 percent, and 0.805 for Sleep-EDF expanded; 82.0 percent, 76.3 percent, and 0.753 for MESA; 80.5 percent, 76.8 percent, and 0.738 for Physio2018; and 86.7 percent, 80.9 percent, and 0.804 for the SHHS database. Conclusion: NeuroSleepNet demonstrates that even with a focus on computational efficiency and a purely supervised learning approach, it is possible to achieve performance that is comparable to state-of-the-art methods. Significance: Our study simplifies automatic sleep scoring by focusing solely on microevents in the current input signal while maintaining remarkable performance. This offers a streamlined alternative for sleep diagnosis applications.

eess.SP↗

arXiv2023

STREAMLINE: An Automated Machine Learning Pipeline for Biomedicine Applied to Examine the Utility of Photography-Based Phenotypes for OSA Prediction Across International Sleep Centers

While machine learning (ML) includes a valuable array of tools for analyzing biomedical data, significant time and expertise is required to assemble effective, rigorous, and unbiased pipelines. Automated ML (AutoML) tools seek to facilitate ML application by automating a subset of analysis pipeline elements. In this study we develop and validate a Simple, Transparent, End-to-end Automated Machine Learning Pipeline (STREAMLINE) and apply it to investigate the added utility of photography-based phenotypes for predicting obstructive sleep apnea (OSA); a common and underdiagnosed condition associated with a variety of health, economic, and safety consequences. STREAMLINE is designed to tackle biomedical binary classification tasks while adhering to best practices and accommodating complexity, scalability, reproducibility, customization, and model interpretation. Benchmarking analyses validated the efficacy of STREAMLINE across data simulations with increasingly complex patterns of association. Then we applied STREAMLINE to evaluate the utility of demographics (DEM), self-reported comorbidities (DX), symptoms (SYM), and photography-based craniofacial (CF) and intraoral (IO) anatomy measures in predicting any OSA or moderate/severe OSA using 3,111 participants from Sleep Apnea Global Interdisciplinary Consortium (SAGIC). OSA analyses identified a significant increase in ROC-AUC when adding CF to DEM+DX+SYM to predict moderate/severe OSA. A consistent but non-significant increase in PRC-AUC was observed with the addition of each subsequent feature set to predict any OSA, with CF and IO yielding minimal improvements. Application of STREAMLINE to OSA data suggests that CF features provide additional value in predicting moderate/severe OSA, but neither CF nor IO features meaningfully improved the prediction of any OSA beyond established demographics, comorbidity and symptom characteristics.

cs.LG↗

arXiv2021

From sleep medicine to medicine during sleep: A clinical perspective

Sleep has a profound influence on the physiology of body systems and biological processes. Molecular studies have shown circadian-regulated shifts in protein expression patterns across human tissues, further emphasizing the unique functional, behavioral and pharmacokinetic landscape of sleep. Thus, many pathological processes are also expected to exhibit sleep-specific manifestations. Nevertheless, sleep is seldom utilized for the study, detection and treatment of non-sleep-specific pathologies. Modern advances in biosensor technologies have enabled remote, non-invasive recording of a growing number of physiologic parameters and biomarkers. Sleep is an ideal time frame for the collection of long and clean physiological time series data which can then be analyzed using data-driven algorithms such as deep learning. In this perspective paper, we aim to highlight the potential of sleep as an auspicious time for diagnosis, management and therapy of nonsleep-specific pathologies. We introduce key clinical studies in selected medical fields, which leveraged novel technologies and the advantageous period of sleep to diagnose, monitor and treat pathologies. We then discuss possible opportunities to further harness this new paradigm and modern technologies to explore human health and disease during sleep and to advance the development of novel clinical applications: From sleep medicine to medicine during sleep.

q-bio.QM↗

arXiv2020

Digital biomarkers and artificial intelligence for mass diagnosis of atrial fibrillation in a population sample at risk of sleep disordered breathing

Atrial fibrillation (AF) is the most prevalent arrhythmia and is associated with a five-fold increase in stroke risk. Many individuals with AF go undetected. These individuals are often asymptomatic. There are ongoing debates on whether mass screening for AF is to be recommended. However, there is incentive in performing screening for specific at risk groups such as individuals suspected of sleep-disordered breathing where an important association between AF and obstructive sleep apnea (OSA) has been demonstrated. We introduce a new methodology leveraging digital biomarkers and recent advances in artificial intelligence (AI) for the purpose of mass AF diagnosis. We demonstrate the value of such methodology in a large population sample at risk of sleep disordered breathing. Four databases, totaling n=3,088 patients and p=26,913 hours of ECG raw data were used. Three of the databases (n=125, p=2,513) were used for training a machine learning model in recognizing AF events from beat-to-beat interval time series. The visit 1 of the sleep heart health study database (SHHS1, n=2,963, p=24,400) consists of overnight polysomnographic (PSG) recordings, and was considered as the test set. In SHHS1, expert inspection identified a total of 70 patients with a prominent AF rhythm. Model prediction on the SHHS1 showed an overall Se=0.97,Sp=0.99,NPV=0.99,PPV=0.67 in classifying individuals with or without prominent AF. PPV was non-inferior (p=0.03) for individuals with an apnea-hypopnea index (AHI) > 15 versus AHI < 15. Over 22% of correctly identified prominent AF rhythm cases were not documented as AF in the SHHS1. Individuals with prominent AF can be automatically diagnosed from an overnight single channel ECG recording, with an accuracy unaffected by the presence of OSA. AF detection from overnight ECG recording revealed a large proportion of undiagnosed AF and may enhance the phenotyping of OSA.

eess.SP↗

arXiv2014

Sleep apnea-hypopnea quantification by cardiovascular data analysis

Sleep apnea is the most common sleep disturbance and it is an important risk factor for cardiovascular disorders. Its detection relies on a polysomnography, a combination of diverse exams. In order to detect changes due to sleep disturbances such as sleep apnea occurrences, without the need of combined recordings, we mainly analyze systolic blood pressure signals (maximal blood pressure value of each beat to beat interval). Nonstationarities in the data are uncovered by a segmentation procedure, which provides local quantities that are correlated to apnea-hypopnea events. Those quantities are the average length and average variance of stationary patches. By comparing them to an apnea score previously obtained by polysomnographic exams, we propose an apnea quantifier based on blood pressure signal. This furnishes an alternative procedure for the detection of apnea based on a single time series, with an accuracy of 82%.

physics.med-ph↗

arXiv2007

Experimental evidence for phase synchronization transitions in human cardio-respiratory system

Transitions in the dynamics of complex systems can be characterized by changes in the synchronization behavior of their components. Taking the human cardio-respiratory system as an example and using an automated procedure for screening the synchrograms of 112 healthy subjects we study the frequency and the distribution of synchronization episodes under different physiological conditions that occur during sleep. We find that phase synchronization between heartbeat and breathing is significantly enhanced during non-rapid-eye-movement (non-REM) sleep (deep sleep and light sleep) and reduced during REM sleep. Our results suggest that the synchronization is mainly due to a weak influence of the breathing oscillator upon the heartbeat oscillator, which is disturbed in the presence of long-term correlated noise, superimposed by the activity of higher brain regions during REM sleep.

physics.data-an↗

arXiv2003

Quantification of Sleep Fragmentation Through the Analysis of Sleep-Stage Transitions

We introduce new quantitative approaches to study sleep-stage transitions with the goal of addressing the two following questions: (i) Can the new approaches provide more information on the structure of sleep-stage transitions? (ii) How does sleep fragmentation in patients with sleep apnea affect the structure of sleep-stage transitions? Our new results show that the distribution of sleep and wake duration have different functional forms, indicating fundamental differences in the dynamics between sleep and wake control. The difference remains even in the fragmented sleep of sleep apnea. The fragmentation of sleep in sleep apnea results in a shorter wake duration and interrupts the structure of sleep-stage transitions of sleep apnea subjects, causing the loss of certain particular transition paths.

cond-mat↗

arXiv2002

Characterization of Sleep Stages by Correlations of Heartbeat Increments

We study correlation properties of the magnitude and the sign of the increments in the time intervals between successive heartbeats during light sleep, deep sleep, and REM sleep using the detrended fluctuation analysis method. We find short-range anticorrelations in the sign time series, which are strong during deep sleep, weaker during light sleep and even weaker during REM sleep. In contrast, we find long-range positive correlations in the magnitude time series, which are strong during REM sleep and weaker during light sleep. We observe uncorrelated behavior for the magnitude during deep sleep. Since the magnitude series relates to the nonlinear properties of the original time series, while the signs series relates to the linear properties, our findings suggest that the nonlinear properties of the heartbeat dynamics are more pronounced during REM sleep. Thus, the sign and the magnitude series provide information which is useful in distinguishing between the sleep stages.

cond-mat.stat-mech↗

arXiv2002

Dynamics of Sleep-Wake Transitions During Sleep

We study the dynamics of the awakening during the night for healthy subjects and find that the wake and the sleep periods exhibit completely different behavior: the durations of wake periods are characterized by a scale-free power-law distribution, while the durations of sleep periods have an exponential distribution with a characteristic time scale. We find that the characteristic time scale of sleep periods changes throughout the night. In contrast, there is no measurable variation in the power-law behavior for the durations of wake periods. We develop a stochastic model which agrees with the data and suggests that the difference in the dynamics of sleep and wake states arises from the constraints on the number of microstates in the sleep-wake system.

cond-mat.stat-mech↗