Why Use Ultrasensitive Sleep Sensors in Healthcare

🛏️ Revolutionizing Sleep Monitoring: From Wristbands to Real Biomarkers Traditional wearables fall short when it comes to sleep diagnostics—they miss direct respiratory signals, which are vital for identifying sleep stages and disorders like sleep apnea. This new research introduces a low-power, skin-integrated mechanoacoustic (LMA) sensor that changes the game. It doesn't just guess your sleep from motion—it listens to your breath and heartbeat. https://lnkd.in/g_yZW69p 🔬 Key innovations: - Multimodal sensor captures respiratory rate, heart rate variability (HRV), respiration rate variability (RRV), body movement, and more. -Paired with LMA-SleepNet, an interpretable machine learning model that detects sleep stages and apnea events with clinical-grade accuracy. - Uses physiology-based features like baroreflex and muscle tone—giving deeper insights than motion-based trackers. Outperforms other wearables in real-world accuracy. 📊 Why this matters: - Directly measures respiration—a core but missing biomarker in most wearables. - Enables continuous, personalized, and explainable sleep tracking in the home or clinic. - Opens doors for smart OSA detection, snoring tracking, and even future on-body therapeutic interventions. 💡 Bonus: Real-time UTC synchronization allows scalable multi-sensor studies across environments and populations. 🔁 This is more than a device—it’s a complete hardware-software platform for next-gen sleep and health monitoring, with huge potential for precision healthcare, chronic disease management, and behavioral science. 👀 Sleep isn’t just rest—it’s integrated physiological data. And now, we can measure it better than ever. #SleepScience #WearableTech #DigitalHealth #MachineLearning #SleepApnea #RespiratoryHealth #PrecisionMedicine #Bioengineering #HealthTech #HRV #RRV

Published today in the Proceedings of the National Academy of Sciences PNAS, our paper on data analytics approaches for monitoring sleep patterns using a soft, wireless electronic device designed with a high-bandwidth accelerometer and configured to gently mount on the suprasternal notch – an information-rich anatomical location for recording diverse mechano-acoustic activities, from subtle vibrations of the skin to bulk movements of the body. Digital filtering of the resulting data yields a broad range of characteristic features associated with heart rate, respiratory rate, respiratory sounds, body orientation and many others. This paper focuses on advanced machine learning algorithms that operate not only on these features but also on the raw data and an associated collection derived quantities. Training relies on recordings from human subjects in a sleep laboratory, where clinical-grade polysomnography systems and scoring by professional sleep clinicians set the ground truth. The resulting technology – soft, skin-interfaced sensors and machine learning algorithms – determine sleep patterns with fidelity that lies beyond that of traditional wrist or finger-mounted wearables. One interesting and intuitive finding - especially for anyone who has had children – is that respiratory sounds, rates, durations, depths and their temporal variations are powerful indicators of sleep onset and quality, yet not typically captured directly with home sleep monitors. Prof. Yayun Du (former postdoc, now on the faculty at Vanderbilt University), Jianyu Gu (former MS student, now a PhD student at Dartmouth College with former postdoc Prof. Wei Ouyang) and Shiyuan Duan (former MS student, now a PhD student at the University of Illinois Urbana-Champaign with former postdoc Prof. Cunjiang Yu) and Jacob Trueb (software engineer and data scientist at our Querrey Simpson Institute for Bioelectronics) contributed equally to this project. Deeply grateful to them for their excellent work, and to our main clinical collaborator on this project – Dr. Charles Davies, head of Sleep Medicine at Carle Hospital. We also thank senior colleagues Prof. Yonggang Huang (Northwestern University) and Dr. Andrew N. Carr (Procter & Gamble) for their important contributions. On-going work involves the use of this system to quantify sleep in pediatric patients, including those with Down syndrome, in collaborations with clinicians and sleep medicine experts at Ann & Robert H. Lurie Children's Hospital of Chicago – Dr. Debra Weese-Mayer and Dr. Ilya Khaytin.  Looking forward to publishing the results of these studies in the near future! https://lnkd.in/gnPk-K7h

🎉 Exciting News! 🎉 Our paper, “Interpretable Feature-Based Machine Learning for Automatic Sleep Detection Using Photoplethysmography,” is now published in Nature Portfolio npj Biosensing! In simple terms, we’ve shown how a common light-based sensor (#PPG)—the same technology found in many fitness bands—can accurately tell when you’re asleep or awake, without needing complex EEG equipment. Why this matters: ------------------- 1) Transparent decisions: Unlike “black box” #AI methods, our approach clearly shows why it labels each moment as #sleep or #wake. This transparency builds confidence for both clinicians and everyday users. 2) Broad clinical relevance: We trained and tested our model on a unique sleep database that includes patients with sleep‐disordered breathing (#SDB), insomnia, periodic leg movements (#PLM), restless leg syndrome (#RLS), REM behavior disorder (#RBD), nocturnal frontal lobe epilepsy (#NFLE), and narcolepsy. By demonstrating robust performance across these varied sleep pathologies, our work ensures reliable sleep detection in real‐world, clinical scenarios. 3) High accuracy: Using expert‐annotated #EEG patterns as ground truth, our model achieves nearly 90 % accuracy with only PPG data—matching or exceeding more complex, multi‐sensor systems. 4) Easy and comfortable: Sleep can now be tracked at home or in a clinic without bulky equipment, just a simple wrist/finger‐worn PPG sensor, making long‐term monitoring more practical and patient‐friendly. Congratulations to my ETH master’s students, Karmen Markov and Vera Birrer, for their outstanding work on this project! Your dedication made this breakthrough possible. I’d also like to thank Carlo Menon for his invaluable guidance and support throughout our collaboration. This effort truly bridges Khalifa University and ETH Zürich, combining our strengths to make sleep monitoring more accessible and understandable. Check out the paper here: https://lnkd.in/di2emR25 #SleepTech #Wearables #HealthTech #MachineLearning #Interpretability #KU #ETHZurich