Sleep Tracking Technologies

Performance of seven consumer sleep-tracking devices compared with polysomnography Link: https://lnkd.in/enH5U5Gs Study Objectives Consumer sleep-tracking devices are widely used and becoming more technologically advanced, creating strong interest from researchers and clinicians for their possible use as alternatives to standard actigraphy. We, therefore, tested the performance of many of the latest consumer sleep-tracking devices, alongside actigraphy, versus the gold-standard sleep assessment technique, polysomnography (PSG). Methods In total, 34 healthy young adults (22 women; 28.1 ± 3.9 years, mean ± SD) were tested on three consecutive nights (including a disrupted sleep condition) in a sleep laboratory with PSG, along with actigraphy (Philips Respironics Actiwatch 2) and a subset of consumer sleep-tracking devices. Altogether, four wearable (Fatigue Science Readiband, Fitbit Alta HR, Garmin Fenix 5S, Garmin Vivosmart 3) and three nonwearable (EarlySense Live, ResMed S+, SleepScore Max) devices were tested. Sleep/wake summary and epoch-by-epoch agreement measures were compared with PSG. Results Most devices (Fatigue Science Readiband, Fitbit Alta HR, EarlySense Live, ResMed S+, SleepScore Max) performed as well as or better than actigraphy on sleep/wake performance measures, while the Garmin devices performed worse. Overall, epoch-by-epoch sensitivity was high (all ≥0.93), specificity was low-to-medium (0.18–0.54), sleep stage comparisons were mixed, and devices tended to perform worse on nights with poorer/disrupted sleep. Conclusions Consumer sleep-tracking devices exhibited high performance in detecting sleep, and most performed equivalent to (or better than) actigraphy in detecting wake. Device sleep stage assessments were inconsistent. Findings indicate that many newer sleep-tracking devices demonstrate promising performance for tracking sleep and wake. Devices should be tested in different populations and settings to further examine their wider validity and utility. #sleep #sleephealth #sleepapnea #sleeptrends #sleep2025 #health #healthcare #sleepapnea #osa #cpap

1 in 5 Americans struggles with chronic sleep disorders. That’s 65 million people and a massive untapped healthtech opportunity. We’ve solved fitness, nutrition, even telemedicine. But sleep? Not yet. And that’s surprising - because sleep touches everything: metabolism, mental health, cardiovascular risk, even neurodegeneration. So where’s the opportunity? ▶ 1. Diagnostics without labs Sleep testing is still built around $1,000-a-night lab studies. Resmed and Withings have built strong home-diagnostic ecosystems, and Eight Sleep - now valued near $1B - dominates the consumer segment. But clinical validation, cost, and physician integration remain open gaps for new entrants. ▶ 2. Continuous monitoring that predicts Most wearables stop at tracking.The next step is prediction - spotting apnea, insomnia, or circadian drift before they become chronic. Startups that turn longitudinal sleep data into actionable risk models will own this space. ▶ 3. Affordable treatment at scale Cognitive Behavioral Therapy (CBT-I) is the gold standard, but it’s expensive to access. Somryst proved the model could go FDA-cleared, though assets were later acquired after Pear’s bankruptcy. While Sleeprate remains consumer-focused. So the real play? Lower-cost, hybrid care models that combine digital CBT with primary-care integration. ▶ 4. Sleep as part of chronic care Sleep isn’t a niche category - it connects to every major chronic disease. Large employers and payers are starting to integrate sleep into chronic-disease programs. So the next wave of startups will integrate sleep health into cardiology, mental wellness, and metabolic programs. We talk about trillion-dollar opportunities in longevity and mental health. But sleep might be the most solvable one - if we stop treating it like a lifestyle issue and start building it like a healthcare vertical. What do you think? Is sleep the most overlooked category in the wellness-to-healthcare transition? #entrepreneurship #startup #healthtech

𝗪𝗶𝘁𝗵 𝗮 $𝟵𝟲𝗠 𝗰𝗼𝗻𝘁𝗿𝗮𝗰𝘁, 𝗢𝘂𝗿𝗮 𝗥𝗶𝗻𝗴 𝗵𝗮𝘀 𝗻𝗼𝘄 𝗯𝗲𝗰𝗼𝗺𝗲 𝗽𝗮𝗿𝘁 𝗼𝗳 𝗻𝗮𝘁𝗶𝗼𝗻𝗮𝗹 𝘀𝗲𝗰𝘂𝗿𝗶𝘁𝘆 𝗶𝗻𝗳𝗿𝗮𝘀𝘁𝗿𝘂𝗰𝘁𝘂𝗿𝗲. Yesterday, ŌURA announced it’s opening a new manufacturing facility in Fort Worth, Texas to support its biggest customer, the Department of Defense. The DoD has already deployed tens of thousands of Oura Rings since 2019. In 2024, it signed a $96M contract to scale distribution further. Of course this is a big sales win, but it also ads to their product trust. Few professions outside the military can give health products more credibility. It’s as much a brand move as it is a business one. The Pentagon cares about a sleep wearable because Oura has proven it can deliver in extreme environments. 1️⃣ Fatigue risk management: After fatigue-related accidents killed 17 sailors in 2017, the Navy launched its largest fatigue study. Today, 1,600 sailors on the USS Gerald R. Ford wear Oura Rings so commanders can track readiness in real time and sailors can own their recovery. 2️⃣ Training prediction: The Army equipped 400+ soldiers with Oura Rings during field exercises. The data predicted which soldiers would pass equipment qualification on the first try, unlocking personalized training. 3️⃣ Early illness detection: The Defense Innovation Unit paired Oura with AI to create RATE, a system that flagged COVID-19 infections before symptoms. The model is now being applied to other illnesses that spread fast in close quarters. 4️⃣ Stress and resilience: The Air Force gave 1,000+ Oura Rings to new leaders to monitor stress. Instead of waiting for burnout, leadership gets objective data to intervene. Other wearables are also evolving beyond fitness: → The Apple Watch is FDA-cleared for EKGs and ran a 400,000-person heart study that caught atrial fibrillation early. → WHOOP straps were used in a six-month Army study in Alaska, helping squad leaders spot hidden burnout. → Empatica and BIOSTRAP supply medical-grade wearables to NIH and BARDA for real-time illness tracking and long COVID studies. → Hexoskin biometric shirts are worn by astronauts and fighter pilots, tracking ECG, respiration, and fatigue in harsh conditions. In 2019, fewer than 10% of wearables had FDA clearance. Today, it’s more than 25%. The market grew from about $17B in 2019 to over $45B in 2024, and could hit $70–80B by 2028. Clinical trials using wearables jumped from fewer than 20 in 2018 to more than 250 in 2023. Wearables keep moving beyond simple “lifestyle gadgets.” They now track HRV, skin temperature, oxygen levels, respiration, blood pressure, glucose, and early signs of infection or cognitive strain. They’re also becoming tools for leaders to keep teams healthy and performing at their best. Predictive, proactive readiness is becoming the standard. It proved consumer health tech can meet the highest bar of resilience, accuracy, and trust. This is where I believe the future of wearables is headed.

The biggest raise in sleep tech history. Eight Sleep just closed a $100M round. The company is calling its next phase an AI Sleep Agent, a personalized layer between your body and your environment that learns from your nightly data and adapts in real time. But the bigger story? They’re going after FDA clearance. That’s not just sleep optimization anymore, it’s a jump into regulated health tech. And it’s exactly the kind of wellness → healthcare convergence I’ve been talking about. Eight Sleep is just the latest, and one of the clearest, examples of this shift. For them, it unlocks clinical claims, physician adoption, and potentially employer or insurer channels. Why this matters... → 𝗙𝗿𝗼𝗺 𝘁𝗿𝗮𝗰𝗸𝗶𝗻𝗴 𝘁𝗼 𝗶𝗻𝘁𝗲𝗿𝘃𝗲𝗻𝘁𝗶𝗼𝗻 Most sleep tools just report, but Eight Sleep is moving toward active adjustments and health monitoring. They say their system can already track cardiovascular and respiratory patterns with strong validation results. If proven, sleep becomes a measurable lever for metabolism, recovery, and cognition. → 𝗖𝗼𝗻𝘀𝘂𝗺𝗲𝗿 𝘁𝗼 𝗰𝗹𝗶𝗻𝗶𝗰𝗮𝗹 FDA approval would legitimize Eight Sleep with doctors and hospitals while creating new reimbursement pathways. Wellness brands rarely cross this line, if they succeed, it sets a template for other recovery tools. → 𝗙𝘂𝗹𝗹-𝘀𝘁𝗮𝗰𝗸 𝘀𝗹𝗲𝗲𝗽 𝗵𝗲𝗮𝗹𝘁𝗵 This isn’t just a mattress cover. It’s hardware + sensors, AI + software, and now a regulated pathway. That end-to-end stack could define how sleep is treated at home, in clinics, and in performance settings. → 𝗗𝗶𝘀𝘁𝗿𝗶𝗯𝘂𝘁𝗶𝗼𝗻 𝗲𝘅𝗽𝗮𝗻𝗱𝘀 Plans include retail stores, international expansion (with China in focus), and new price tiers. If they pair clinical credibility with broader access, sleep tech could move from premium gadget to mainstream health utility. What to watch -> regulatory path (which clearances they pursue), clinical outcomes (not just dashboards), pricing and access, and how they handle sensitive biometric data. TLDR: If Eight Sleep can turn sleep into a regulated, personalized intervention, it upgrades the bed from comfort product to health platform, with ripple effects across recovery, cardiometabolic care, and longevity. ♻️ Repost this to share with anyone tracking recovery and longevity. Follow me at Delphine Le Grand for more.

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

The most interesting AI shift right now isn't happening in chatbots or copilots. It's happening in a mattress. The next phase is AI that works without you asking. Systems that detect what's happening in real time and adjust on their own. Sleep is one of the first places this is actually working. Sleep Number's sensor-enabled beds track your movement, breathing, heart rate, and temperature throughout the night. But they don't just give you a report in the morning. The bed adjusts support under your body and manages temperature while you're asleep, based on what it's sensing in the moment. As Sleep Number CEO Linda Findley put it, "Let's not just tell you how you slept. Let's actually improve your sleep." That's a different standard for AI. One that closes the gap between insight and action without asking anything from you. And look, the numbers back it up. One Sleep Number mattress reports an average of 52.5 additional minutes of restful sleep per night. Not from sleeping longer. From making the time you already spend in bed more restorative. We're just getting started with what AI can do when it stops waiting for a prompt. I wrote more about this here: https://lnkd.in/gP3UYJ-6

A new study showed that consumer sleep trackers ŌURA Ring, Fitbit (now part of Google), and Apple Watch achieved >90% sleep-wake accuracy and 70-78% accuracy when determining sleep stages compared to polysomnography With the growing popularity of wearable #sleep tracking devices, millions of consumers now rely on these technologies to monitor and improve their sleep health. Given this widespread adoption, it's crucial to evaluate the accuracy of these devices against gold standard measurements. A recent study published in Sensors MDPI addressed this need by comparing three popular consumer sleep tracking devices - the Oura Ring Gen3, Fitbit Sense 2, and Apple Watch Series 8 - to polysomnography (PSG), the benchmark for sleep assessment. Conducted on 35 healthy adults aged 20-50 years, this research provides valuable insights into how well these wearable devices measure various aspects of sleep in a controlled setting. Key findings include: 1. All three devices demonstrated high sensitivity (≥90%) in detecting sleep versus wake states, surpassing many older research-grade actigraphy devices. The Oura Ring showed substantial agreement with PSG in determining specific sleep stages (Kappa > 0.61), while the Fitbit and Apple Watch demonstrated moderate agreement (Kappa < 0.61). 2. For nightly summary estimates, the Oura Ring was not significantly different from PSG in 7 out of 8 measures, only overestimating sleep latency by 5 minutes. 3. The Fitbit significantly overestimated light sleep by 18 minutes and underestimated deep sleep by 15 minutes compared to PSG. 4. The Apple Watch underestimated wake time by 7 minutes, deep sleep by 43 minutes, and wake after sleep onset by 10 minutes, while overestimating light sleep by 45 minutes. 5. A limitation is that only a single night of data was collected, and the devices were only compared to PSG during scheduled sleep episodes in healthy participants rather than across a 24 h interval, which is the way most wearables are used. The study highlights that while these consumer devices perform well in distinguishing between sleep and wake states, their accuracy in measuring specific sleep stages varies. The Oura Ring demonstrated the most consistent performance across different sleep parameters, although all devices had limitations in accurately measuring deep and REM sleep. This research provides valuable information for consumers and healthcare professionals considering the use of wearable sleep tracking devices. However, it's important to note that the study was conducted on healthy adults in a controlled setting, and further research is needed to evaluate device performance in populations with sleep disorders or in more naturalistic environments. P.S. Congrats to the sleep team at Brigham and Women's Hospital and Harvard Medical School for doing the study! Study: https://lnkd.in/dZThiegT #sleepmedicine #sleephealth #neuroscience #medtech #healthtech #science #research #education

Most people think their wearable “detects” sleep. In reality, it infers sleep, using physiology—and the underlying science is worth understanding. Lets look at ŌURA this week. The Oura Ring relies on multisensor fusion—infrared PPG (photoplethysmography) , 3-axis accelerometry, skin temperature, and respiratory signals derived from the pulse waveform. Sleep/wake is then classified using 30-second epochs (windows) via machine-learning models trained against in-lab polysomnography (PSG). In validation studies, Oura achieves ~90% accuracy for sleep detection and high agreement with ECG for nighttime HR/HRV. Staging (REM, light, deep) uses a neural network architecture integrating HRV patterns, motion suppression, temperature stability, and waveform morphology. We are essentially matching patterns derived from the ring (PPG, movement, temp, etc) to how our autonomic nervous system behaves in different stages of "sleep". - Deep sleep: HR and respiratory rate stability - REM: HR and respiratory rate variability in the absence of movement - Wake: HR and respiratory rate variability in the presence of movement Clinical take aways: Wearables like Oura are excellent for trends—sleep duration, timing, HRV, temperature, and stability—but should be interpreted as probabilistic estimates, not clinical staging or diagnostics. Limitations: The more pathologic or fragmented ones sleep, the more "inaccurate" the output...As sleep efficiency drops the output becomes less reliable. How I use these tools: We use Oura as a behavioral and recovery tool, not a substitute for formal sleep testing. When patients understand its strengths (consistency, trend detection) and limitations (no EEG), it becomes far more valuable. One the things you'll notice in the graphs is the very high specificity of finding Deep and REM sleep. #Sleep #SleepScience #Longevity #HealthTech #Wearables #OuraRing Empower Sleep ================================================== This week I’ll be researching and sharing the science of wearables and Sleep Medicine...Stay tuned for more on Apple, Garmin, Ultrahuman Fitbit (now part of Google).... Next week we will spend some time reviewing the different peptides known to enhance/modulate sleep... Follow me for a daily dose of sleep science that you can apply in your life or share with your family.