Sensor-Based Digital Health Technology Enables Digital Medicine for Sleep-Related Breathing Diseases
Bibliographic record
Abstract
Abstract Rationale: Sleep-related breathing diseases are common yet underdiagnosed and undertreated. Single night polysomnography is costly, burdensome and not feasible for continued monitoring of severity or therapeutic response over time. Patients may benefit from serial assessments across an end-to-end patient journey from screening through treatment initiation and monitoring to long-term treatment adherence. This requires sensor-based fit-for-purpose measurements for health care providers (HCPs) to stratify risk and confirm response to therapy. Methods: We developed a Connected Wearable software platform for use with a wearable proximal finger-mounted pulse oximeter to enable serial overnight recordings of SpO2 and pulse rate (transmittance-based photoplethysmography) and motion (3-axis accelerometer). Sensor-based fit-for-purpose measurements include the oxygen desaturation index (ODI4), time below 90% (T90), hypoxic burden (HB), heart rate response (ΔHR), and heart rate burden (HRB). Platform components include a patient mobile app, cloud infrastructure, sleep algorithm engine, and web dashboards customizable according to clinical needs or research study designs. The sleep algorithm engine analyzes and calculates the sensor-based fit-for-purpose measurements and electronic patient reported outcomes (ePROs). Detailed nightly reports are shared with HCPs through a dedicated clinician web portal, a subset of analyses can be shared directly with the patient through the mobile app. Results: The Connected Wearable platform has been deployed in 2 ongoing clinical trials across 51 clinical sites (US: 48, Canada: 3) in 104 patients with OSA resulting in 2,017 overnight recordings to date (expected total enrollment N=800 patients). One trial is a one year open-label extension study for a phase 3 pharmacologic treatment program. During this study, people with OSA are monitored during a pre-treatment baseline period and then during treatment initiation (low dose period, full dose period, and then quarterly during the treatment maintenance period). The second trial adds the Connected Wearable platform to a health coaching program that aims to improve CPAP adherence in 30 participants with 30 matched controls. Participants, their HCP, and their health coach all have access to the Connected Wearable platform to provide more insights into treatment usage and efficacy that may help guide coaching interventions to improve treatment success. Conclusions: The Connected Wearable platform provides reliable, scalable, sensor-based digital health technology to acquire and analyze relevant digital biomarkers for serial, multi-night assessments to monitor sleep-related breathing diseases. The system has been successfully rolled out in two ongoing clinical trials for sleep-related breathing diseases, providing new insights into patient responses and treatment efficacy.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.019 | 0.008 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".