Hidden Markov model segmentation to demarcate trajectories of residual apnoea-hypopnoea index in CPAP-treated sleep apnoea patients to personalize follow-up and prevent treatment failure

A multidisciplinary approach to the home management of continuous positive airway pressure therapy for obstructive sleep apnea: beyond usual care pathways (a narrative review)

Obstructive sleep apnea (OSA) is a common chronic condition that is growing in prevalence, associated with important comorbidities, and has several different phenotypes. Continuous positive airway pressure (CPAP) is the gold standard OSA treatment, but its effectiveness relies on consistent adherence, which can often be difficult to maintain. This narrative review discusses current challenges in the care pathways for CPAP therapy management in OSA, including fragmented care/lack of continuity, inadequate management of comorbidities, suboptimal implementation of digital medicine solutions, and existing reimbursement paradigms. Key tasks to be shared between the appropriate healthcare professionals and providers include technical CPAP follow-up (adherence, effectiveness, alert management), management of comorbidities, and multimodal non-invasive monitoring. What this looks like and who provides the different aspects of care should vary by OSA phenotype, ranging from simple follow-up in primary care (uncomplicated OSA with good CPAP adherence) to multidisciplinary specialist management (high-risk OSA with comorbidities), with regular reassessment to ensure continued alignment with the chosen care plan. In addition to better defining these pathways, how they are reimbursed also needs to be addressed. We suggest that there should be a multidisciplinary approach to symptom reduction and adherence, longitudinal assessment of patient-reported outcomes, and a focus on long-term cardiometabolic health as part of managing CPAP-treated patients with OSA. Facilitated by the appropriate use of digital technologies, these approaches should lead to more personalized care and greater patient engagement, resulting in better long-term adherence and treatment effectiveness. The ultimate goal should be to do better for less.

New management pathways for follow-up of CPAP-treated sleep apnoea patients including digital medicine and multimodal telemonitoring

BACKGROUND

The ever-increasing number of patients diagnosed with obstructive sleep apnoea (OSA) and treated by long-term continuous positive airway pressure (CPAP) overstretches conventional follow-up pathways. New approaches to the management of CPAP-treated patient follow-up are needed to strike a balance between remote monitoring through digital technologies and in-person patient-healthcare-professional contacts. Focusing on the reshaping of the management of care pathways of CPAP-treated patients, with a specific focus on telemonitoring platforms, we aimed to review the evidence on how digital medicine and artificial intelligence (AI) tools are facilitating patient phenotyping and triage, risk stratification and the allocation of resources between the various healthcare professionals for an optimal follow-up of CPAP-treated patients.

PHENOTYPING

OSA is a heterogeneous condition with diverse phenotypes differing in symptoms, comorbidities, demographics, lifestyle and socioeconomic context. Different phenotypes are associated with different CPAP adherence patterns and differing long-term prognosis. This diversity demands greater plurality in management pathways with different types and levels of support to ensure treatment adherence and risk reduction for patients while easing the burden on health services. In multidimensional phenotyping, we discuss alternatives to the apnoea hypopnoea index (AHI) as a measure of OSA severity. Then we consider risk stratification taking advantage of the wealth of CPAP monitoring data already available in databases that can now be exploited using AI and machine learning to direct (stratify) patients into appropriate follow-up management pathways.

INTEGRATED CARE CLINICS FOR HIGH-RISK PATIENTS

We look at the role of integrated OSA care clinics particularly for the management of high-risk patients with low adherence and progression of comorbidities. Here, multidisciplinary teams might propose comorbidity management, and the use of connected wearable devices for long-term monitoring of physical activity, along with remote CPAP monitoring.

REMOTE MANAGEMENT PATHWAYS

The pros and cons of remote management pathways to replace in-person follow-up visits are considered, including the need to re-evaluate CPAP-device reimbursement policies in some countries. While remote CPAP monitoring has become the cornerstone of follow-up providing information on adherence and efficacy, the processing of alerts needs to be improved, particularly regarding mask changes and early detection of CPAP failures.

CHALLENGES

The implementation of CPAP monitoring alone, as well as its extension to multimodal monitoring, can present challenges that remain to be addressed (eg, access to digital care). The extent and components of remote follow-up must be adapted to each specific OSA phenotype. Finally, we give examples of certain patient phenotypes (eg, comorbid insomnia with OSA) with specific follow-up requirements, for which remote (even multimodal) monitoring alone has limitations and the intervention of both sleep specialists and/or their colleagues from other disciplines is needed.

CONCLUSION

Appropriately tailored combined digital and in-person CPAP follow-up pathways would present advantages both for patients with OSA and healthcare services.

The Future of Telemedicine for Obstructive Sleep Apnea Treatment: A Narrative Review

Obstructive sleep apnea is a common type of sleep-disordered breathing associated with multiple comorbidities. Nearly a billion people are estimated to have obstructive sleep apnea, which carries a substantial economic burden, but under-diagnosis is still a problem. Continuous positive airway pressure (CPAP) is the first-line treatment for OSAS. Telemedicine-based interventions (TM) have been evaluated to improve access to diagnosis, increase CPAP adherence, and contribute to easing the follow-up process, allowing healthcare facilities to provide patient-centered care. This narrative review summarizes the evidence available regarding the potential future of telemedicine in the management pathway of OSA. The potential of home sleep studies to improve OSA diagnosis and the importance of remote monitoring for tracking treatment adherence and failure and to contribute to developing patient engagement tools will be presented. Further studies are needed to explore the impact of shifting from teleconsultations to collaborative care models where patients are placed at the center of their care.

Effects of telemedicine-based follow-up management on adults with obstructive sleep apnea: A systematic review and meta-analysis

OBJECTIVES

This meta-analysis aimed to investigate the effects of telemedicine-based follow-up management on adults with obstructive sleep apnea.

METHODS

Publications were searched in the Cochrane Library, PubMed, Scopus, Web of Science and Embase. Studies were selected according to the predefined screening criteria, and their qualities were assessed by the Revised Cochrane risk-of-bias tool for randomized trials. The statistical analyses were performed using Stata12.0 software. It was registered in PROSPERO with the number: CRD42021276414.

RESULTS

A total of 33 articles with 8,689 participants were included. Telemedicine-based follow-up management improved average daily continuous positive airway pressure usage by 36 min (weighted mean difference:0.61;95% confidence interval: 0.39 to 0.83), and the percentage of days with continuous positive airway pressure usage more than four hours by 10.67% in obstructive sleep apnea patients. The meta-analysis of good continuous positive airway pressure compliance showed telemedicine-based follow-up management did not lead to good continuous positive airway pressure compliance (odds ratio: 1.13;95% confidence interval: 0.72 to 1.76). The pooled mean difference of sleep quality was 0.15 (standardized mean difference:0.15; 95% confidence interval: -0.03 to 0.32), and daytime sleepiness was -0.26 (weighted mean difference: -0.26;95% confidence interval: -0.79 to 0.28). The pooled mean difference of apnea hypopnea index was -0.53 (95% confidence interval: -3.58 to 2.51). As for the overall quality of life, the pooled mean difference was -0.25 (standardized mean difference: -0.25;95% confidence interval: -0.25 to 0.76).

CONCLUSION

Telemedicine-based follow-up management was beneficial for continuous positive airway pressure compliance of obstructive sleep apnea patients within six months. However, it could not improve sleep quality, daytime sleepiness, the severity of obstructive sleep apnea, and quality of life in obstructive sleep apnea patients compared with traditional follow-up. Moreover, it was more cost-effective, but there was no consensus on whether it would increase the workload of medical staff.

Remote Monitoring of Positive Airway Pressure Data: Challenges, Pitfalls, and Strategies to Consider for Optimal Data Science Applications

Over recent years, positive airway pressure (PAP) remote monitoring has transformed the management of OSA and produced a large amount of data. Accumulated PAP data provide valuable and objective information regarding patient treatment adherence and efficiency. However, the majority of studies that have analyzed longitudinal PAP remote monitoring have summarized data trajectories in static and simplistic metrics for PAP adherence and the residual apnea-hypopnea index by the use of mean or median values. The aims of this article are to suggest directions for improving data cleaning and processing and to address major concerns for the following data science applications: (1) conditions for residual apnea-hypopnea index reliability, (2) lack of standardization of indicators provided by different PAP models, (3) missing values, and (4) consideration of treatment interruptions. To allow fair comparison among studies and to avoid biases in computation, PAP data processing and management should be conducted rigorously with these points in mind. PAP remote monitoring data contain a wealth of information that currently is underused in the field of sleep research. Improving the quality and standardizing data handling could facilitate data sharing among specialists worldwide and enable artificial intelligence strategies to be applied in the field of sleep apnea.

The individual and societal price of non-adherence to continuous positive airway pressure, contributors and strategies for improvement

INTRODUCTION

Continuous positive airway pressure (CPAP) is the first line therapy for obstructive sleep apnea (OSA). CPAP is highly effective for improving symptoms and quality of life but the major issue is adherence, with up to 50% of OSA discontinuing CPAP in the first 3 years after CPAP initiation.

AREAS COVERED

We present the individual and societal cost of non-adherence to CPAP, factors associated with non-adherence to CPAP, as well as current strategies for improving adherence including telehealth, couples-based interventions and behavioral interventions. We also report on challenges and pitfalls for the visualization and analysis of CPAP remote monitoring platforms.

EXPERT OPINION

CPAP termination rates and adherence to therapy remain major issues despite technical improvements in CPAP devices. The individual and societal price of non-adherence to CPAP for OSA patients goes beyond excessive sleepiness and includes cardiovascular events, all-cause mortality, and increased health costs. Strategies for improving CPAP adherence should be individually tailored and aim to also improve lifestyle habits including physical activity and nutrition. Access to these strategies should be supported by refining visualization dashboards of CPAP remote monitoring platforms, and by disseminating telehealth and innovative analytics, including artificial intelligence.

Factors Associated With Residual Apnea-Hypopnea Index Variability During CPAP Treatment

BACKGROUND

CPAP is the first-line therapy for OSA. A high or variable residual apnea-hypopnea index (rAHI) reflects treatment failure and potentially is triggered by exacerbation of cardiovascular comorbidities. Previous studies showed that high rAHI and large rAHI variability are associated with underlying comorbidities, OSA characteristics at diagnosis, and CPAP equipment, including mask type and settings.

RESEARCH QUESTION

What factors are associated with predefined groups with low to high rAHI variability?

STUDY DESIGN AND METHODS

This registry-based study included patients with a diagnosis of OSA who were receiving CPAP treatment with at least 90 days of CPAP remote monitoring. We applied the hidden Markov model to analyze the day-to-day trajectories of rAHI variability using telemonitoring data. An ordinal logistic regression analysis identified factors associated with a risk of having a higher and more variable rAHI with CPAP treatment.

RESULTS

The 1,126 included patients were middle-aged (median age, 66 years; interquartile range [IQR], 57-73 years), predominantly male (n = 791 [70.3%]), and obese (median BMI, 30.6 kg/m² (IQR, 26.8-35.2 kg/m²). Three distinct groups of rAHI trajectories were identified using hidden Markov modeling: low rAHI variability (n = 393 [35%]), moderate rAHI variability group (n = 420 [37%]), and high rAHI variability group (n = 313 [28%]). In multivariate analysis, factors associated with high rAHI variability were age, OSA severity at diagnosis, heart failure, opioids and alcohol consumption, mental and behavioral disorders, transient ischemic attack and stroke, an oronasal mask, and level of leaks when using CPAP.

INTERPRETATION

Identifying phenotypic traits and factors associated with high rAHI variability will allow early intervention and the development of personalized follow-up pathways for CPAP treatment.

Sleep duration and atrial fibrillation risk in the context of predictive, preventive, and personalized medicine: the Suita Study and meta-analysis of prospective cohort studies

Background

Short and long sleep durations are common behaviors that could predict several cardiovascular diseases. However, the association between sleep duration and atrial fibrillation (AF) risk is not well-established. AF is preventable, and risk prevention approaches could reduce its occurrence. Investigating whether sleep duration could predict AF incidence for possible preventive interventions and determining the impact of various lifestyle and clinical characteristics on this association to personalize such interventions are essential. Herein, we investigated the association between sleep duration and AF risk using a prospective cohort study and a meta-analysis of epidemiological evidence.

Methods

Data of 6898 people, aged 30-84 years, from the Suita Study, were analyzed. AF was diagnosed during the follow-up by ECG, medical records, checkups, and death certificates, while a baseline questionnaire was used to assess sleep duration. The Cox regression was used to compute the hazard ratios (HRs) and 95% confidence intervals (CIs) of AF risk for daily sleep ≤ 6 (short sleep), ≥ 8 (long sleep), and irregular sleep, including night-shift work compared with 7 h (moderate sleep). Then, we combined our results with those from other eligible prospective cohort studies in two meta-analyses for the short and long sleep.

Results

In the Suita Study, within a median follow-up period of 14.5 years, short and irregular sleep, but not long sleep, were associated with the increased risk of AF in the age- and sex-adjusted models: HRs (95% CIs) = 1.36 (1.03, 1.80) and 1.62 (1.16, 2.26) and the multivariable-adjusted models: HRs (95% CIs) = 1.34 (1.01, 1.77) and 1.63 (1.16, 2.30), respectively. The significant associations between short and irregular sleep and AF risk remained consistent across different ages, sex, smoking, and drinking groups. However, they were attenuated among overweight and hypertensive participants. In the meta-analyses, short and long sleep durations were associated with AF risk: pooled HRs (95% CIs) = 1.21 (1.02, 1.42) and 1.18 (1.03, 1.35). No signs of significant heterogeneity across studies or publication bias were detected.

Conclusion

Short, long, and irregular sleep could be associated with increased AF risk. In the context of predictive, preventive, and personalized medicine, sleep duration should be considered in future AF risk scores to stratify the general population for potential personalized lifestyle modification interventions. Sleep management services should be considered for AF risk prevention, and these services should be individualized according to clinical characteristics and lifestyle factors.

Graphical abstract

Supplementary Information

The online version contains supplementary material available at 10.1007/s13167-022-00275-4.