New research from Nox Research, presented at the 2025 AASM Sleep Medicine Disruptors conference, offers fresh insights into how sleep disorders can be more accurately diagnosed, more effectively treated, and more equitably addressed across diverse patient populations.
Together, these studies contribute to a more holistic understanding of sleep health, including improvements in diagnostic accuracy, care accessibility, and long-term treatment outcomes.
Focus on diagnostic accuracy through conclusive HSAT
For Nox, a conclusive home-based sleep apnea testing (HSAT) means three things: it produces an accurate AHI and other core clinical parameters, it works reliably across patient groups, and it provides insights that help patients succeed on treatment. The abstract “Improving Diagnostic Accuracy in Home Sleep Apnea Testing with Nox AI Scoring” (DeepRESP K241960) shows how DeepRESP, applied to recordings from Nox recorders with abdomen/thorax respiratory inductance plethysmography (RIP) sensors, is designed to deliver conclusive HSAT. Analysis of the largest validation dataset for an FDA-cleared HSAT system demonstrates that DeepRESP improves the accuracy of AHI by enabling sleep staging and arousal scoring in HSAT studies without adding the burden of EEG for patients, providing enhanced diagnostic insights compared to traditional HSAT metrics.
A key reason many HSATs are effectively inconclusive is that the device-reported Respiratory Event Index (REI) can underestimate the true AHI. REI underestimation typically occurs when hypopneas end in arousal rather than oxygen desaturation and when sleep is not recorded; the result is false negatives or inconclusive studies. Patients who receive a negative or inconclusive HSAT result frequently do not complete an in-lab PSG and therefore do not receive diagnosis or treatment for their sleep disorder. Producing a conclusive HSAT on the first test — one that yields an accurate AHI and arousal assessment, and may support clinicians in making more informed decisions earlier in the care pathway. AI technology plays a central role in responsibly supporting clinical decision-making in this setting, leading to greater accuracy, transforming traditionally inconclusive HSAT results into conclusive diagnostic outcomes on the first try.
Abstract lead author and Nox Medical’s VP of Artificial Intelligence and Data Research, Jón S. Ágústsson explains, “From a physiology perspective, we know well how sleep stages and arousals impact breathing movements. Using the Nox RIP sensors we are able to measure these changes in breathing movements and leverage this information to train an AI model capable of scoring these events based on the changes in breathing movement.”
The reason this approach yields conclusive HSAT is the RIP signal itself. Nox’s abdomen/thorax RIP captures respiratory effort, thorax–abdomen phase relationships (including paradoxical breathing), and the subtle breathing-pattern changes that accompany arousals. DeepRESP’s AI models are trained to recognize these breathing signatures and to produce automated sleep staging and arousal scoring from breathing movement alone. The resulting AHI, arousal index, and sleep-stage outputs are more consistent with PSG and deliver the treatment-relevant insights clinicians need, helping them choose therapies, monitor response, and support patient success on treatment.
How can value-based care improve access and better management of sleep disorders?
Another critical question in sleep care is access. Access to sleep specialists has been challenging for people who live in rural areas because most sleep disorders centers are located in urban areas. Another Nox Research abstract presented real-world data examining the time it takes from receiving a sleep evaluation to initiating treatment for patients in rural and urban areas.
The abstract addressed how value-based care, with its emphasis on patient outcomes and cost-effectiveness, can form the basis for a better approach to managing chronic sleep disorders. Examining Nox Health’s virtual comprehensive sleep healthcare model to evaluate and treat obstructive sleep apnea, the findings revealed that our clinically integrated, virtual care model can deliver care at speeds comparable to those in urban areas. This demonstrates a sleep healthcare model that is efficient and accessible, irrespective of location, while maintaining consistent quality standards for patients. The Nox role is to support physicians, health systems, and home care providers and work alongside them to ensure that every pathway to sleep care is easy to navigate, accessible, connected, and comprehensive.
Lead author Jason Ong explains, “This study is important because it shows that a value-based sleep telemedicine model can overcome the barriers to care that have traditionally been a problem for those living in rural areas.”
Improvements in insomnia care with prescription digital CBT-I
Although insomnia is one of the most prevalent sleep disorders (10-15% of adults)1, few receive first-line therapy (Cognitive-Behavioral-Therapy for Insomnia, CBT-I). While CBT-I is an effective insomnia treatment and can improve co-occurring chronic conditions, a number of barriers prevent broad access to CBT-I.
The final abstract featured a real-world study evaluating the effectiveness of Somryst, an FDA-cleared dCBT-I for chronic insomnia by Nox Medical. The study presented results over 18 and 24 months. dCBT-I (Somryst) was associated with sustained improvements in insomnia severity, depressive symptoms, and anxiety symptoms out to two years post-treatment. These findings demonstrate the long-term durability of our digital therapeutic for insomnia in real-world settings.
“Seeing sustained positive outcomes in insomnia at 18 months and 24 months after a 9-week digital treatment is exciting,” lead author Frances Thorndike shares. “There is such need for patients with insomnia and very limited treatment resources; opening access to first-line treatment and seeing these positive sustained results is an important step for offering comprehensive care for patients with sleep disorders.”
Long-term durability is a crucial element in evaluating behavioral health interventions. These results reinforce the potential for digital therapeutics to offer lasting benefits when integrated into evidence-based care models.
Advancing a holistic view of sleep health
Sleep disturbances rarely occur in isolation. More than 80% of those with OSA have multiple comorbid conditions across a diverse range of cardiovascular and cerebrovascular diseases, pulmonary, and metabolic disorders.2,3 Examining diagnostic accuracy, treatment access, and long-term therapeutic outcomes together expands the understanding of how sleep disorders are identified, managed, and improved over time – necessary steps for offering connected, comprehensive care to the patients we care for. Nox is committed to advancing sleep medicine with continuous research in this area.
Dive into the full range of Nox Research.
These abstracts were presented at the 2025 AASM Sleep Medicine Disruptors Conference, November 14-15, 2025 in Austin, Texas.
References
- American Psychiatric Association. Diagnostic and Statistical Manual of Mental Disorders (DSM-5-TR), Fifth edition – Text Revision. 2022.
- Bonsignore MR, Baiamonte P, Mazzuca E, Castrogiovanni A, Marrone O. Obstructive sleep apnea and comorbidities: a dangerous liaison. Multidiscip Respir Med. 2019;14:8. doi:10.1186/s40248-019-0172-9
- Yeghiazarians Y, Jneid H, Tietjens JR, et al. Obstructive Sleep Apnea and Cardiovascular Disease: A Scientific Statement From the American Heart Association. Circulation. 2021;144(3):e56-e67. doi:10.1161/CIR.0000000000000988
Topic: Events
