Big Data in sleep apnoea: Opportunities and challenges

ERS Congress 2024: highlights from the Paediatrics Assembly

At #ERSCongress 2024, experts highlighted the need to address healthcare disparities, prevent disease progression and assess the value of AI-driven care to improve outcomes in paediatric respiratory health https://bit.ly/40944lv.

The future of big data: Remote monitoring of positive airway pressure treatment for obstructive sleep apnea - insights from adults and implications for pediatric care

The advent of large expansive datasets has generated substantial interest as a means of developing and implementing unique algorithms that facilitate more precise and personalized interventions. This methodology has permeated the realm of sleep medicine and in the care of patients with sleep disorders. One of the large repositories of information consists of adherence and physiological datasets across long periods of time as derived from patients undergoing positive airway pressure (PAP) treatment for sleep-disordered breathing. Here, we evaluate the extant and yet scarce findings derived from big data in both adults and children receiving PAP for obstructive sleep apnea and suggest future directions towards more expansive utilization of such valuable approaches to improve therapeutic decisions and outcomes.

The Swedish sleep apnea registry (SESAR) cohort - "Real world data" on a national level

INTRODUCTION

The Swedish Sleep Apnea Registry (SESAR) collects clinical data from individual obstructive sleep apnea (OSA) patients since 2010. SESAR has recently been integrated with additional national healthcare data. The current analysis presents the SESAR structure and representative clinical data of a national sleep apnea cohort.

METHODS

Clinical data from unselected patients with a diagnosis of OSA are submitted to the SESAR registry. 48 sleep centers report data from diagnosis, treatment starts with Continuous Positive Airway Pressure (CPAP), oral devices (OD), and Upper Airway Surgery (UAS). Data from follow-up are included. SESAR is linked to mandatory national healthcare data (mortality, comorbidities, procedures, prescriptions) and diagnosis-specific quality registries (e.g. stroke, heart failure, diabetes) within the DISCOVERY project.

RESULTS

83,404 OSA patients have been reported during the diagnostic workup (age 55.4 ± 14.1 years, BMI 30.8 ± 6.5 kg/m2, AHI 25.8 ± 21.6n/h, respectively). At least one cardiometabolic and respiratory comorbidity is recognized in 57 % of female and 53 % of male OSA patients with a linear increase across OSA severity. In 54,468, 7,797, and 390 patients, start of CPAP, OD or UAS treatment is reported, respectively. OD patients have 4 units lower BMI and 10 units lower AHI compared to patients started on CPAP. UAS patients are characterized by 10 years lower age. The degree of daytime sleepiness is comparable between treatment groups with mean Epworth Sleepiness Scale Scores between 9 and 10.

CONCLUSION

SESAR is introduced as a large national registry of OSA patients. SESAR provides a useful tool to highlight OSA management and to perform relevant outcome research.

An Artificial Intelligence-Based Non-Invasive Approach for Cardiovascular Disease Risk Stratification in Obstructive Sleep Apnea Patients: A Narrative Review

Background

Obstructive sleep apnea (OSA) is a severe condition associated with numerous cardiovascular complications, including heart failure. The complex biological and morphological relationship between OSA and atherosclerotic cardiovascular disease (ASCVD) poses challenges in predicting adverse cardiovascular outcomes. While artificial intelligence (AI) has shown potential for predicting cardiovascular disease (CVD) and stroke risks in other conditions, there is a lack of detailed, bias-free, and compressed AI models for ASCVD and stroke risk stratification in OSA patients. This study aimed to address this gap by proposing three hypotheses: (i) a strong relationship exists between OSA and ASCVD/stroke, (ii) deep learning (DL) can stratify ASCVD/stroke risk in OSA patients using surrogate carotid imaging, and (iii) including OSA risk as a covariate with cardiovascular risk factors can improve CVD risk stratification.

Methods

The study employed the Preferred Reporting Items for Systematic reviews and Meta-analyses (PRISMA) search strategy, yielding 191 studies that link OSA with coronary, carotid, and aortic atherosclerotic vascular diseases. This research investigated the link between OSA and CVD, explored DL solutions for OSA detection, and examined the role of DL in utilizing carotid surrogate biomarkers by saving costs. Lastly, we benchmark our strategy against previous studies.

Results

(i) This study found that CVD and OSA are indirectly or directly related. (ii) DL models demonstrated significant potential in improving OSA detection and proved effective in CVD risk stratification using carotid ultrasound as a biomarker. (iii) Additionally, DL was shown to be useful for CVD risk stratification in OSA patients; (iv) There are important AI attributes such as AI-bias, AI-explainability, AI-pruning, and AI-cloud, which play an important role in CVD risk for OSA patients.

Conclusions

DL provides a powerful tool for CVD risk stratification in OSA patients. These results can promote several recommendations for developing unique, bias-free, and explainable AI algorithms for predicting ASCVD and stroke risks in patients with OSA.

[Sleep Innovation]

Advances in sleep medicine have driven significant improvements in the diagnosis and treatment of sleep disorders such as obstructive sleep apnea (OSA). This disorder affects one billion people worldwide and traditionally, diagnosis is based on polysomnography (PSG), a laborious method that requires specialized personnel. However, the integration of artificial intelligence (AI) in sleep medicine has made it possible to automate the analysis of sleep phases and respiratory events with high accuracy.Machine learning algorithms and neural networks have proven to be effective in automatic sleep coding, with hit rates comparable to those of human experts. These advances make it possible to improve the efficiency of sleep labs and to personalize OSA treatment. In addition, techniques such as cluster analysis are used to identify symptomatic patterns and phenotypes, which improves understanding of OSA pathophysiology and optimizes CPAP treatment.However, implementation of AI in hospitals faces technological, ethical, and legal barriers. Challenges include data quality, patient privacy, and the need for specialized personnel. Despite these obstacles, AI and Big Data have the potential to transform medical care for sleep disorders, improving both diagnosis and treatment adherence, provided regulatory and cultural barriers are overcome.

The Cost-Effectiveness of Sleep Apnea Management: A Critical Evaluation of the Impact of Therapy on Health Care Costs

TOPIC IMPORTANCE

OSA is a widespread condition that significantly affects both health and health-related quality of life (HRQoL). If left untreated, OSA can lead to accidents, decreased productivity, and medical complications, resulting in significant economic burdens including the direct costs of managing the disorder. Given the constraints on health care resources, understanding the cost-effectiveness of OSA management is crucial. A key factor in cost-effectiveness is whether OSA therapies reduce medical costs associated with OSA-related complications.

REVIEW FINDINGS

Treatments for OSA have been shown to enhance HRQoL, particularly for symptomatic patients with moderate or severe disease. Economic studies also have demonstrated that these treatments are highly cost-effective. However, although substantial empirical evidence shows that untreated OSA is associated with increased medical costs, uncertainty remains about the impact of OSA treatment on these costs. Randomized controlled trials of positive airway pressure (PAP) therapy have failed to demonstrate cost reductions, but the studies have had important limitations. Observational studies suggest that PAP therapy may temper increases in costs, but only among patients who are highly adherent to treatment. However, the healthy adherer effect is an important potential source of bias in these studies.

SUMMARY

OSA management is cost-effective, although uncertainties persist regarding the therapy's impact on medical costs. Future studies should focus on reducing bias, particularly the healthy adherer effect, and addressing other confounding factors to clarify potential medical cost savings. Promising avenues to further understanding include using quasiexperimental designs, incorporating more sophisticated characterization of OSA severity and symptoms, and leveraging newer technologies (eg, big data, wearables, and artificial intelligence).

A new perspective on OSAS cases with the Baveno classification

OBJECTIVE/BACKGROUND

Since the apnea-hypopnea index (AHI), which is used in the diagnosis and grading of OSAS, does not adequately reflect the clinical perspective of the disease, the Baveno classification of OSA was developed, which allows multicomponent evaluation of OSAS patients. The aim of our study was to evaluate the application of the Baveno classification in clinical practice.

PATIENTS/METHODS

A prospective study was performed on patients diagnosed with OSAS between January 2021 and June 2022. Patients were divided into 4 groups according to Baveno classification (Groups A-D) and three groups as mild, moderate, and severe OSAS according to AHI.

RESULTS

A total of 378 patients (70% male, mean age 48.68 ± 11.81 years) were included in the study. The patients had mild (n: 75; 20%), moderate (n: 88; 23%), and severe (n: 215; 57%) OSAS. According to Baveno classification, patients were included in Groups A (n: 90; 24%), B (n: 105 (28%), C (n: 65; 17%), and D (n: 118; 31%). The mean AHIs of the Baveno groups were similar (p = 0.116). Oxygen desaturation index (ODI) was higher in Groups B and D compared to Group A. The duration of T90 desaturation was longer in Groups C and D compared to Groups A and B (p < 0.05).

CONCLUSIONS

The Baveno classification divided our OSAS cases into equivalent groups. One out of every four patients with mild OSAS was in Group D. This data was noteworthy in that the Baveno classification allows for the identification of symptomatic and comorbid patients with mild OSAS according to AHI and for the application of more effective treatments to these patients. Patients with comorbidities experienced oxygen desaturation for a longer period of time at night, and oxygenation deteriorated in patients with prominent symptoms. Baveno classification was found to be a more reasonable and easily applicable approach in clinical practice.

Identifying clusters of patient comorbidities associated with obstructive sleep apnea using electronic health records

STUDY OBJECTIVES

The objectives of this study were to understand the relative comorbidity burden of obstructive sleep apnea (OSA), determine whether these relationships were modified by sex or age, and identify patient subtypes defined by common comorbidities.

METHODS

Cases with OSA and noncases (controls) were defined using a validated electronic health record (EHR)-based phenotype and matched for age, sex, and time period of follow-up in the EHR. We compared prevalence of the 20 most common comorbidities between matched cases and controls using conditional logistic regression with and without controlling for body mass index. Latent class analysis was used to identify subtypes of OSA cases defined by combinations of these comorbidities.

RESULTS

In total, 60,586 OSA cases were matched to 60,586 controls (from 1,226,755 total controls). Patients with OSA were more likely to have each of the 20 most common comorbidities compared with controls, with odds ratios ranging from 3.1 to 30.8 in the full matched set and 1.3 to 10.2 after body mass index adjustment. Associations between OSA and these comorbidities were generally stronger in females and patients with younger age at diagnosis. We identified 5 distinct subgroups based on EHR-defined comorbidities: High Comorbidity Burden, Low Comorbidity Burden, Cardiovascular Comorbidities, Inflammatory Conditions and Less Obesity, and Inflammatory Conditions and Obesity.

CONCLUSIONS

Our study demonstrates the power of leveraging the EHR to understand the relative health burden of OSA, as well as heterogeneity in these relationships based on age and sex. In addition to enrichment for comorbidities, we identified 5 novel OSA subtypes defined by combinations of comorbidities in the EHR, which may be informative for understanding disease outcomes and improving prevention and clinical care. Overall, this study adds more evidence that OSA is heterogeneous and requires personalized management.

CITATION

Te TT, Keenan BT, Veatch OJ, Boland MR, Hubbard RA, Pack AI. Identifying clusters of patient comorbidities associated with obstructive sleep apnea using electronic health records. J Clin Sleep Med. 2024;20(4):521-533.

Positive Airway Pressure Therapy Predicts Lower Mortality and Major Adverse Cardiovascular Events Incidence in Medicare Beneficiaries with Obstructive Sleep Apnea

Background

Obesity is associated with obstructive sleep apnea (OSA) and cardiovascular risk. Positive airway pressure (PAP) is the first line treatment for OSA, but evidence on its beneficial effect on major adverse cardiovascular events (MACE) prevention is limited. Using claims data, the effects of PAP on mortality and incidence of MACE among Medicare beneficiaries with OSA were examined.

Methods

A cohort of Medicare beneficiaries with ≥2 distinct OSA claims was defined from multi-state, state-wide, multi-year (2011-2020) Medicare fee-for-service claims data. Evidence of PAP initiation and utilization was based on PAP claims after OSA diagnosis. MACE was defined as a composite of myocardial infarction, heart failure, stroke, or coronary revascularization. Doubly robust Cox proportional hazards models with inverse probability of treatment weights estimated treatment effects controlling for sociodemographic and clinical factors.

Results

Among 888,835 beneficiaries with OSA (median age 73 years; 43.9% women; median follow-up 1,141 days), those with evidence of PAP initiation (32.6%) had significantly lower all-cause mortality (HR [95%CI]: 0.53 [0.52-0.54]) and MACE incidence risk (0.90 [0.89-0.91]). Higher quartiles of annual PAP claims were progressively associated with lower mortality (Q2: 0.84 [0.81-0.87], Q3: 0.76 [0.74-0.79], Q4: 0.74 [0.72-0.77]) and MACE incidence risk (Q2: 0.92 [0.89-0.95], Q3: 0.89 [0.86-0.91], Q4: 0.87 [0.85-0.90]).

Conclusion

PAP utilization was associated with lower all-cause mortality and MACE incidence among Medicare beneficiaries with OSA. Results might inform trials assessing the importance of OSA therapy towards minimizing cardiovascular risk and mortality in older adults.

Sleep Testing and Mortality in a Propensity-matched Cohort of Patients with Chronic Obstructive Pulmonary Disease

Rationale: Many advocate the application of propensity-matching methods to real-world data to answer key questions around obstructive sleep apnea (OSA) management. One such question is whether identifying undiagnosed OSA impacts mortality in high-risk populations, such as those with chronic obstructive pulmonary disease (COPD). Objectives: Assess the association of sleep testing with mortality among patients with COPD and a high likelihood of undiagnosed OSA. Methods: We identified patients with COPD and a high likelihood of undiagnosed OSA. We then distinguished those receiving sleep testing within 90 days of index COPD encounters. We calculated propensity scores for testing based on 37 variables and compared long-term mortality in matched groups. In sensitivity analyses, we compared mortality using inverse propensity weighting and instrumental variable methods. We also compared the incidence of nonfatal events including adverse outcomes (hospitalizations and COPD exacerbations) and routine services that are regularly indicated in COPD (influenza vaccination and pulmonary function testing). We compared the incidence of each nonfatal event as a composite outcome with death and separately compared the marginal probability of each nonfatal event independently, with death as a competing risk. Results: Among 135,958 patients, 1,957 (1.4%) received sleep testing. We propensity matched all patients with sleep testing to an equal number without testing, achieving excellent balance on observed confounders, with standardized differences < 0.10. We observed lower mortality risk among patients with sleep testing (incidence rate ratio, 0.88; 95% confidence interval [CI], 0.79-0.99) and similar results using inverse propensity weighting and instrumental variable methods. Contrary to mortality, we found that sleep testing was associated with a similar or greater risk for nonfatal adverse events, including inpatient COPD exacerbations (subhazard ratio, 1.29; 95% CI, 1.02-1.62) and routine services like influenza vaccination (subhazard ratio, 1.26; 95% CI, 1.17-1.36). Conclusions: Our disparate findings can be interpreted in multiple ways. Sleep testing may indeed cause both reduced mortality and greater incidence of nonfatal adverse outcomes and routine services. However, it is also possible that our findings stem from residual confounding by patients' likelihood of accessing care. Given the limitations of propensity-based analyses, we cannot confidently distinguish these two possibilities. This uncertainty highlights the limitations of using propensity-based analyses to guide patient care and policy decisions.

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.

Sleep Apnea Detection Using Wavelet Scattering Transformation and Random Forest Classifier

Obstructive Sleep Apnea (OSA) is a common sleep-breathing disorder that highly reduces the quality of human life. The most powerful method for the detection and classification of sleep apnea is the Polysomnogram. However, this method is time-consuming and cost-inefficient. Therefore, several methods focus on using electrocardiogram (ECG) signals to detect sleep apnea. This paper proposed a novel automated approach to detect and classify apneic events from single-lead ECG signals. Wavelet Scattering Transformation (WST) was applied to the ECG signals to decompose the signal into smaller segments. Then, a set of features, including higher-order statistics and entropy-based features, was extracted from the WST coefficients to formulate a search space. The obtained features were fed to a random forest classifier to classify the ECG segments. The experiment was validated using the 10-fold and hold-out cross-validation methods, which resulted in an accuracy of 91.65% and 90.35%, respectively. The findings were compared with different classifiers to show the significance of the proposed approach. The proposed approach achieved better performance measures than most of the existing methodologies.

Homecare interventions as a Service model for Obstructive sleep Apnea: Delivering personalised phone call using patient profiling and adherence predictions

BACKGROUND AND OBJECTIVE

Obstructive Sleep Apnea (OSA) is a sleep disorder that leads to different pathologies like depression and cardiovascular problems. The first-line medical treatment for OSA is Continuous Positive Airway Pressure (CPAP) therapy. However, this therapy has the lowest adherence level when compared to other homecare therapies. Consequently, the main objective of this paper is to increase this adherence level with methods that can be replicated in a large number of patients.

METHODS

The Homecare Intervention as a Service model can build, verify, and deliver per-sonalised home care interventions. With the Homecare Intervention as a Service model, we build and provide on-demand personalised interventions according to the patient's needs. The 2 core components of this model are patient clustering and CPAP adherence predictions. To define the patient profiles and predict the adherence level, we apply the K-means and the Logistic Regression algorithm respectively. To support these algorithms, we use the CPAP monitoring data and qualitative data on the patients.

RESULTS

We demonstrate that there are 3 patient profiles (non-adherent, attempter, and adherent). We draw a comparison with multiple machine learning algorithms to predict CPAP adherence at 30, 60 and 90 days. In this case, the Logistic Regression gives the best results with a f1-score of 0.84 for30 days, 0.79 for 60 days and 0.76 for 90 days. These newly build profiles were to be used to deliver personalised phone call interventions. The phone call intervention shows an increase in adherence by 1.02 h/night for non-adherent patients and 0.69 h/night for attempter patients.

CONCLUSIONS

This is the first study in CPAP therapy that formalises the process of transforming raw data into effective home care interventions that can be delivered directly to the patients. In fact,it is the first time that both patient characterisation and predictions based on data are used to provide personalised patient management for CPAP therapy. Our model is flexible to be extended to new types of interventions and other homecare therapies.

Experimental Models to Study End-Organ Morbidity in Sleep Apnea: Lessons Learned and Future Directions

Sleep apnea (SA) is a very prevalent sleep breathing disorder mainly characterized by intermittent hypoxemia and sleep fragmentation, with ensuing systemic inflammation, oxidative stress, and immune deregulation. These perturbations promote the risk of end-organ morbidity, such that SA patients are at increased risk of cardiovascular, neurocognitive, metabolic and malignant disorders. Investigating the potential mechanisms underlying SA-induced end-organ dysfunction requires the use of comprehensive experimental models at the cell, animal and human levels. This review is primarily focused on the experimental models employed to date in the study of the consequences of SA and tackles 3 different approaches. First, cell culture systems whereby controlled patterns of intermittent hypoxia cycling fast enough to mimic the rates of episodic hypoxemia experienced by patients with SA. Second, animal models consisting of implementing realistic upper airway obstruction patterns, intermittent hypoxia, or sleep fragmentation such as to reproduce the noxious events characterizing SA. Finally, human SA models, which consist either in subjecting healthy volunteers to intermittent hypoxia or sleep fragmentation, or alternatively applying oxygen supplementation or temporary nasal pressure therapy withdrawal to SA patients. The advantages, limitations, and potential improvements of these models along with some of their pertinent findings are reviewed.

Current and Novel Treatment Options for OSA

Obstructive sleep apnoea is a challenging medical problem due to its prevalence, its impact on quality of life and performance in school and professionally, the implications for risk of accidents, and comorbidities and mortality. Current research has carved out a broad spectrum of clinical phenotypes and defined major pathophysiological components. These findings point to the concept of personalised therapy, oriented on both the distinct clinical presentation and the most relevant pathophysiology in the individual patient. This leads to questions of whether sufficient therapeutic options other than positive airway pressure (PAP) alone are available, for which patients they may be useful, if there are specific indications for single or combined treatment, and whether there is solid scientific evidence for recommendations. This review describes our knowledge on PAP and non-PAP therapies to address upper airway collapsibility, muscle responsiveness, arousability and respiratory drive. The spectrum is broad and heterogeneous, including technical and pharmaceutical options already in clinical use or at an advanced experimental stage. Although there is an obvious need for more research on single or combined therapies, the available data demonstrate the variety of effective options, which should replace the unidirectional focus on PAP therapy.

The analysis of individual pathophysiological composition opens new directions towards personalised treatment of OSA, focusing not only on pharyngeal dilation, but also on technical or pharmaceutical interventions on muscle function or breathing regulationhttps://bit.ly/3sayhkd

Monitoring Long Term Noninvasive Ventilation: Benefits, Caveats and Perspectives

Long term noninvasive ventilation (LTNIV) is a recognized treatment for chronic hypercapnic respiratory failure (CHRF). COPD, obesity-hypoventilation syndrome, neuromuscular disorders, various restrictive disorders, and patients with sleep-disordered breathing are the major groups concerned. The purpose of this narrative review is to summarize current knowledge in the field of monitoring during home ventilation. LTNIV improves symptoms related to CHRF, diurnal and nocturnal blood gases, survival, and health-related quality of life. Initially, patients with LTNIV were most often followed through elective short in-hospital stays to ensure patient comfort, correction of daytime blood gases and nocturnal oxygenation, and control of nocturnal respiratory events. Because of the widespread use of LTNIV, elective in-hospital monitoring has become logistically problematic, time consuming, and costly. LTNIV devices presently have a built-in software which records compliance, leaks, tidal volume, minute ventilation, cycles triggered and cycled by the patient and provides detailed pressure and flow curves. Although the engineering behind this information is remarkable, the quality and reliability of certain signals may vary. Interpretation of the curves provided requires a certain level of training. Coupling ventilator software with nocturnal pulse oximetry or transcutaneous capnography performed at the patient's home can however provide important information and allow adjustments of ventilator settings thus potentially avoiding hospital admissions. Strategies have been described to combine different tools for optimal detection of an inefficient ventilation. Recent devices also allow adapting certain parameters at a distance (pressure support, expiratory positive airway pressure, back-up respiratory rate), thus allowing progressive changes in these settings for increased patient comfort and tolerance, and reducing the requirement for in-hospital titration. Because we live in a connected world, analyzing large groups of patients through treatment of “big data” will probably improve our knowledge of clinical pathways of our patients, and factors associated with treatment success or failure, adherence and efficacy. This approach provides a useful add-on to randomized controlled studies and allows generating hypotheses for better management of HMV.

Barriers of artificial intelligence implementation in the diagnosis of obstructive sleep apnea

Background

Obstructive sleep apnea is a common clinical condition and has a significant impact on the health of patients if untreated. The current diagnostic gold standard for obstructive sleep apnea is polysomnography, which is labor intensive, requires specialists to utilize, expensive, and has accessibility challenges. There are also challenges with awareness and identification of obstructive sleep apnea in the primary care setting. Artificial intelligence systems offer the opportunity for a new diagnostic approach that addresses the limitations of polysomnography and ultimately benefits patients by streamlining the diagnostic expedition.

Main body

The purpose of this project is to elucidate the barriers that exist in the implementation of artificial intelligence systems into the diagnostic context of obstructive sleep apnea. It is essential to understand these challenges in order to proactively create solutions and establish an efficient adoption of this new technology. The literature regarding the evolution of the diagnosis of obstructive sleep apnea, the role of artificial intelligence in the diagnosis, and the barriers in artificial intelligence implementation was reviewed and analyzed.

Conclusion

The barriers identified were categorized into different themes including technology, data, regulation, human resources, education, and culture. Many of these challenges are ubiquitous across artificial intelligence implementation in any medical diagnostic setting. Future research directions include developing solutions to the barriers presented in this project.

Graphical abstract

Electronic health record-derived outcomes in obstructive sleep apnea managed with positive airway pressure tracking systems

STUDY OBJECTIVES

To assess the effectiveness of continuous positive airway pressure (CPAP) management guided by CPAP machine downloads in newly diagnosed patients with obstructive sleep apnea (OSA) using electronic health record-derived health care utilization, biometric variables, and laboratory data.

METHODS

Electronic health record data of patients seen at the University of Utah Sleep Program from 2012-2015 were reviewed to identify patients with new diagnosis of OSA in whom CPAP adherence and residual apnea-hypopnea index as measured by a positive airway pressure adherence tracking device data for ≥ 1 year were available. Biometric data, laboratory data, and system-wide charges were compared in the 1 year before and after CPAP therapy. Subgroups were divided by whether patients met tracking criteria, mean nightly usage, and OSA severity.

RESULTS

976 consecutive, newly diagnosed participants with OSA (median age 55 years, 56.6% male) met inclusion criteria. There was a mean decrease of systolic blood pressure (BP) of 1.2 mm Hg and diastolic BP of 1.0 mm Hg within a year of initiation of CPAP therapy. BP improvements in the subgroup meeting CPAP tracking targets were 1.36 mmHg (systolic) and 1.37 mmHg (diastolic). No significant change was noted in body mass index, glycated hemoglobin, or serum creatinine values within a year of starting CPAP therapy, and health care utilization increased (mean acute care visits 0.22 per year to 0.53 per year; mean charges of $3,997 per year to $8,986 per year).

CONCLUSIONS

An improvement in BP was noted within a year of CPAP therapy in newly diagnosed patients with OSA, with no difference in the magnitude of improvement between those meeting tracking system adherence targets.

CITATION

Locke BW, Neill SE, Howe HE, Crotty MC, Kim J, Sundar KM. Electronic health record-derived outcomes in obstructive sleep apnea managed with positive airway pressure tracking systems. J Clin Sleep Med. 2022;18(3):885-894.

Integration of Artificial Intelligence, Blockchain, and Wearable Technology for Chronic Disease Management: A New Paradigm in Smart Healthcare

Chronic diseases are a growing concern worldwide, with nearly 25% of adults suffering from one or more chronic health conditions, thus placing a heavy burden on individuals, families, and healthcare systems. With the advent of the "Smart Healthcare" era, a series of cutting-edge technologies has brought new experiences to the management of chronic diseases. Among them, smart wearable technology not only helps people pursue a healthier lifestyle but also provides a continuous flow of healthcare data for disease diagnosis and treatment by actively recording physiological parameters and tracking the metabolic state. However, how to organize and analyze the data to achieve the ultimate goal of improving chronic disease management, in terms of quality of life, patient outcomes, and privacy protection, is an urgent issue that needs to be addressed. Artificial intelligence (AI) can provide intelligent suggestions by analyzing a patient's physiological data from wearable devices for the diagnosis and treatment of diseases. In addition, blockchain can improve healthcare services by authorizing decentralized data sharing, protecting the privacy of users, providing data empowerment, and ensuring the reliability of data management. Integrating AI, blockchain, and wearable technology could optimize the existing chronic disease management models, with a shift from a hospital-centered model to a patient-centered one. In this paper, we conceptually demonstrate a patient-centric technical framework based on AI, blockchain, and wearable technology and further explore the application of these integrated technologies in chronic disease management. Finally, the shortcomings of this new paradigm and future research directions are also discussed.

Novel avenues to approach non-CPAP therapy and implement comprehensive OSA care

Recent advances in obstructive sleep apnoea (OSA) pathophysiology and translational research have opened new lines of investigation for OSA treatment and management. Key goals of such investigations are to provide efficacious, alternative treatment and management pathways that are better tailored to individual risk profiles to move beyond the traditional, continuous positive airway pressure (CPAP)-focused, "one size fits all", trial and error approach which is too frequently inadequate for many patients. Identification of different clinical manifestations of OSA (clinical phenotypes) and underlying pathophysiological phenotypes (endotypes), that contribute to OSA have provided novel insights into underlying mechanisms and have underpinned these efforts. Indeed, this new knowledge has provided the framework for precision medicine for OSA to improve treatment success rates with existing non-CPAP therapies such as mandibular advancement devices and upper airway surgery, and newly developed therapies such as hypoglossal nerve stimulation and emerging therapies such as pharmacotherapies and combination therapy. These concepts have also provided insight into potential physiological barriers to CPAP adherence for certain patients. This review summarises the recent advances in OSA pathogenesis, non-CPAP treatment, clinical management approaches and highlights knowledge gaps for future research. OSA endotyping and clinical phenotyping, risk stratification and personalised treatment allocation approaches are rapidly evolving and will further benefit from the support of recent advances in e-health and artificial intelligence.

Obstructive Sleep Apnea compliance: verifications and validations of personalized interventions for PAP therapy

The Positive Airway Pressure (PAP) therapy is the most capable therapy against Obstruction Sleep Apnea (OSA). PAP therapy prevents the narrowing and collapsing of the soft tissues of the upper airway. A patient diagnosed with OSA is expected to use their CPAP machines every night for at least more than 4h for experiencing any clinical improvement. However, for the last two decades, trials were carried out to improve compliance and understand factors impacting compliance, but there were not enough conclusive results. With the advent of big data analytic and real-time monitoring, new opportunities open up to tackle this compliance issue. This paper's significant contribution is a novel framework that blends multiple external verification and validation carried out by different healthcare stakeholders. We provide a systematic verification and validation process to push towards explainable data analytic and automatic learning processes. We also present a complete mHealth solution that includes two mobile applications. The first application is for delivering tailored interventions directly to the patients. The second application is bound to different healthcare stakeholders for the verification and validation process.

Towards Validating the Effectiveness of Obstructive Sleep Apnea Classification from Electronic Health Records Using Machine Learning

Obstructive sleep apnea (OSA) is a common, chronic, sleep-related breathing disorder characterized by partial or complete airway obstruction in sleep. The gold standard diagnosis method is polysomnography, which estimates disease severity through the Apnea-Hypopnea Index (AHI). However, this is expensive and not widely accessible to the public. For effective screening, this work implements machine learning algorithms for classification of OSA. The model is trained with routinely acquired clinical data of 1479 records from the Wisconsin Sleep Cohort dataset. Extracted features from the electronic health records include patient demographics, laboratory blood reports, physical measurements, habitual sleep history, comorbidities, and general health questionnaire scores. For distinguishing between OSA and non-OSA patients, feature selection methods reveal the primary important predictors as waist-to-height ratio, waist circumference, neck circumference, body-mass index, lipid accumulation product, excessive daytime sleepiness, daily snoring frequency and snoring volume. Optimal hyperparameters were selected using a hybrid tuning method consisting of Bayesian Optimization and Genetic Algorithms through a five-fold cross-validation strategy. Support vector machines achieved the highest evaluation scores with accuracy: 68.06%, sensitivity: 88.76%, specificity: 40.74%, F1-score: 75.96%, PPV: 66.36% and NPV: 73.33%. We conclude that routine clinical data can be useful in prioritization of patient referral for further sleep studies.

Big Data in Nephrology

A huge array of data in nephrology is collected through patient registries, large epidemiological studies, electronic health records, administrative claims, clinical trial repositories, mobile health devices and molecular databases. Application of these big data, particularly using machine-learning algorithms, provides a unique opportunity to obtain novel insights into kidney diseases, facilitate personalized medicine and improve patient care. Efforts to make large volumes of data freely accessible to the scientific community, increased awareness of the importance of data sharing and the availability of advanced computing algorithms will facilitate the use of big data in nephrology. However, challenges exist in accessing, harmonizing and integrating datasets in different formats from disparate sources, improving data quality and ensuring that data are secure and the rights and privacy of patients and research participants are protected. In addition, the optimism for data-driven breakthroughs in medicine is tempered by scepticism about the accuracy of calibration and prediction from in silico techniques. Machine-learning algorithms designed to study kidney health and diseases must be able to handle the nuances of this specialty, must adapt as medical practice continually evolves, and must have global and prospective applicability for external and future datasets.

Continuous positive airway pressure adherence trajectories in sleep apnea: Clustering with summed discrete Fréchet and dynamic time warping dissimilarities

BACKGROUND

Obstructive sleep apnea (OSA) is a chronic disease characterized by recurrent pharyngeal collapses during sleep. In most severe cases, continuous positive airway pressure (CPAP) consists in keeping the airways open by administering mild air pressure. This treatment faces adherence issues.

OBJECTIVES

Eight hundred and forty-eight subjects were equipped with CPAP prescribed at the Grenoble University Hospital between 2016 and 2018. Their daily CPAP uses have been recorded during the first 3 months. Our aim is to cluster these adherence time series. With hierarchical agglomerative clustering, we focused on the choices of the dissimilarity measure and the internal cluster validation index (CVI).

METHODS

The Euclidean distance, the dynamic time warping (DTW) and the generalized summed discrete Fréchet dissimilarity were implemented with three linkage strategies ("average," "complete," and "Ward"). The performances of each method (dissimilarity and linkage) were evaluated on a simulation study through the adjusted Rand index (ARI). The Ward linkage with DTW dissimilarity provided the best ARI. Then six different internal CVIs (Silhouette, Calinski Harabasz, Davies Bouldin, Modified Davies Bouldin, Dunn, and COP) were compared on their ability to choose the best number of clusters. The Dunn index beat the others.

RESULTS

CPAP data were clustered with the Ward linkage, the DTW dissimilarity and the Dunn index. It identified six clusters, from a cluster of patients (N = 29 subjects) whose stopped the therapy early on to a cluster (N = 105) with increasing adherence over time. Other clusters were extremely good users (N = 151), good users (N = 150), moderate users (N = 235), and poor adherers (N = 178).

Artificial intelligence and sleep: Advancing sleep medicine

Artificial intelligence (AI) allows analysis of "big data" combining clinical, environmental and laboratory based objective measures to allow a deeper understanding of sleep and sleep disorders. This development has the potential to transform sleep medicine in coming years to the betterment of patient care and our collective understanding of human sleep. This review addresses the current state of the field starting with a broad definition of the various components and analytic methods deployed in AI. We review examples of AI use in screening, endotyping, diagnosing, and treating sleep disorders and place this in the context of precision/personalized sleep medicine. We explore the opportunities for AI to both facilitate and extend providers' clinical impact and present ethical considerations regarding AI derived prognostic information. We cover early adopting specialties of AI in the clinical realm, such as radiology and pathology, to provide a road map for the challenges sleep medicine is likely to face when deploying this technology. Finally, we discuss pitfalls to ensure clinical AI implementation proceeds in the safest and most effective manner possible.

Apnea-hypopnea index supplied by CPAP devices: time for standardization?

BACKGROUND/OBJECTIVE

For obstructive sleep apnea (OSA) patients on continuous positive airway pressure (CPAP) treatment, the apnea-hypopnea index (AHI) is a key measure of treatment efficacy. However, the residual AHI is CPAP brand specific. Here, we studied changes in residual AHI in patients who used two different brands over their treatment history.

PATIENTS/METHODS

Using our CPAP telemonitoring database of 3102 patients, we compared the residual AHI of 69 patients before and after change in their CPAP device.

RESULTS

A paired Wilcoxon signed-rank test revealed a significant difference between brands in the reported AHI, which might be clinically misleading.

CONCLUSIONS

These findings suggest that physicians should be alerted to the differences between brands and learned societies should push for standardization of AHI reporting.

Validating respiratory index of auto-titrating positive airway pressure device with polysomnography

PURPOSE

Positive airway pressure (PAP) devices have been widely used as the first line of treatment in obstructive sleep apnea (OSA). Most advanced PAP devices support the estimation of respiratory index (RI) using the patient's mask airflow. In addition to the compliance factor for PAP device use, which is important for monitoring patient sleep health, RI is also becoming important for monitoring. However, there are few reports that validate RI of a PAP device with polysomnography.

METHODS

Between January 2015 and December 2017, 50 participants were enrolled who were diagnosed with OSA and prescribed auto-titration PAP (APAP) devices. The RIs of participants were measured at night using APAP devices, concurrently with electroencephalography, respiratory inductance plethysmography sensors, and other polysomnographic sensors in a sleep laboratory. The respiratory-related data of APAP were prospectively analyzed with the manually scored polysomnographic data.

RESULTS

The apnea-hypopnea index and apnea index showed a statistically close relationship between the auto-scored respiratory data from the APAP device and the manually scored respiratory data from polysomnographic sensors. Obstructive apnea and central apnea indices showed relatively low correlations. The differences between the auto-scored RI and manually scored RI were influenced by BMI, waist circumference, weight, oxygen saturation, and respiratory distress indices of diagnostic polysomnographic factors.

CONCLUSIONS

The RIs of APAP devices have a tendency to be underestimated or mismatched when compared with polysomnography. Sleep specialists are advised to consider additional anthropometric and diagnostic factors to account for these differences during PAP treatment.

Artificial Intelligence Analysis of Mandibular Movements Enables Accurate Detection of Phasic Sleep Bruxism in OSA Patients: A Pilot Study

PURPOSE

Sleep bruxism (SBx) activity is classically identified by capturing masseter and/or temporalis masticatory muscles electromyographic activity (EMG-MMA) during in-laboratory polysomnography (PSG). We aimed to identify stereotypical mandibular jaw movements (MJM) in patients with SBx and to develop rhythmic masticatory muscles activities (RMMA) automatic detection using an artificial intelligence (AI) based approach.

PATIENTS AND METHODS

This was a prospective, observational study of 67 suspected obstructive sleep apnea (OSA) patients in whom PSG with masseter EMG was performed with simultaneous MJM recordings. The system used to collect MJM consisted of a small hardware device attached on the chin that communicates to a cloud-based infrastructure. An extreme gradient boosting (XGB) multiclass classifier was trained on 79,650 10-second epochs of MJM data from the 39 subjects with a history of SBx targeting 3 labels: RMMA episodes (n=1072), micro-arousals (n=1311), and MJM occurring at the breathing frequency (n=77,267).

RESULTS

Validated on unseen data from 28 patients, the model showed a very good epoch-by-epoch agreement (Kappa = 0.799) and balanced accuracy of 86.6% was found for the MJM events when using RMMA standards. The RMMA episodes were detected with a sensitivity of 84.3%. Class-wise receiver operating characteristic (ROC) curve analysis confirmed the well-balanced performance of the classifier for RMMA (ROC area under the curve: 0.98, 95% confidence interval [CI] 0.97-0.99). There was good agreement between the MJM analytic model and manual EMG signal scoring of RMMA (median bias -0.80 events/h, 95% CI -9.77 to 2.85).

CONCLUSION

SBx can be reliably identified, quantified, and characterized with MJM when subjected to automated analysis supported by AI technology.

Detecting COVID-19 and other respiratory infections in obstructive sleep apnoea patients through CPAP device telemonitoring

Objective

The earliest possible detection of individuals with COVID-19 has been essential to curb the spread of infection. Existing digital tools have been scaled up to address this issue. Every night telemonitoring data on continuous positive airway pressure (CPAP) device use, the first-line therapy for obstructive sleep apnoea (OSA), is collected worldwide. We asked whether the changes in CPAP adherence patterns of might constitute an alert for COVID-19.

Methods

We analysed preliminary results of telemonitoring data, recorded between February 1 and April 30, 2020, on OSA patients followed by our sleep clinics and diagnosed with COVID-19.

Results

CPAP telemonitoring data from the first 19 patients diagnosed with COVID-19 showed a clear decrease or halt in adherence in the 20 days immediately preceding COVID-19 diagnosis compared to an earlier period (p < 0.01).

Conclusion

Patterns of continuous positive airway pressure device use by obstructive sleep apnoea patients collected through telemonitoring can indicate the onset of COVID-19 symptoms. Existing telemonitoring platforms could be immediately used to screen for COVID-19, and for other respiratory infections, in this large at-risk population.

The future of sleep-disordered breathing: A public health crisis

Find the whole series here https://onlinelibrary.wiley.com/doi/toc/10.1111/(ISSN)1440-1843.new-frontiers-in-sleep-disordered-breathing See cover image.