The Respiratory Signature: A Novel Concept to Leverage Continuous Positive Airway Pressure Therapy as an Early Warning System for Exacerbations of Common Diseases such as Heart Failure

Challenges of Applying Automated Polysomnography Scoring at Scale

Automatic polysomnography analysis can be leveraged to shorten scoring times, reduce associated costs, and ultimately improve the overall diagnosis of sleep disorders. Multiple and diverse strategies have been attempted for implementation of this technology at scale in the routine workflow of sleep centers. The field, however, is complex and presents unsolved challenges in a number of areas. Recent developments in computer science and artificial intelligence are nevertheless closing the gap. Technological advances are also opening new pathways for expanding our current understanding of the domain and its analysis.

Early identification of heart failure deterioration through respiratory monitoring with adaptive servo-ventilation

Cardiac decompensation is associated with worse prognosis in patients with heart failure. Reliable methods to predict cardiac decompensation events are not yet available. Sleep-disordered breathing (SDB) is a frequent comorbidity in heart failure, and it has been shown to correlate with heart failure severity. This prospective observational trial investigated SDB characteristics in patients with heart failure with the aim to identify patterns that may predict early cardiac decompensation. Patients with heart failure with diagnosed SDB and hospitalised for cardiac decompensation were prospectively enrolled and treated with adaptive servo-ventilation (ASV). SDB characteristics, daily body weight and clinical cardiac decompensation events were collected over a 1-year follow-up. Clinical events were categorised by an independent clinical event committee. A total of 43 patients were enrolled (81% male, mean [SD] age 71 [11] years, body mass index 30 kg/m² , 95% New York Heart Association function class III or IV, mean [SD] left ventricular ejection fraction 37% [11%], median apnea-hypopnoea index [AHI] of 37 events/h). A total of 48 cardiac decompensation events were recorded during the 1-year study period. Respiratory rate was found to be significantly lower in patients with cardiac decompensation. The AHI and applied inspiratory pressure ASV-device support were significantly increased 10 days before a clinical cardiac decompensation event. Device usage was also found to be significantly decreased 2 nights before cardiac decompensation. Device-derived respiratory data in ASV therapy devices for SDB may therefore serve as a monitoring tool to predict early clinical cardiac decompensation events. Prediction and avoidance of cardiac decompensation, in turn, may attenuate serious health consequences in patients with heart failure.

Cheyne-Stokes Breathing as a Predictive Indicator of Heart Failure in Patients With Obstructive Sleep Apnea; A Retrospective Case Control Study Using Continuous Positive Airway Pressure Remote Monitoring Data

Objective

We conducted a retrospective case control study to examine whether remote monitoring of Cheyne-Stokes breathing (CSB) was useful for predicting the onset of heart failure (HF) in patients with obstructive sleep apnea (OSA) on continuous positive airway pressure (CPAP).

Methods

Among patients with OSA treated at our hospital, 33 patients with HF that occurred between July 2014 and May 2021 [11 patients with acute HF (AHF); 22 patients with chronic HF (CHF) exacerbation] were included in the HF group. Of the 618 stable patients, 149 patients with a 30-days average CSB rate (CSB%) ≧1% were included in the non-HF control group. The chronologic change of CSB% were compared among the AHF, CHF and Control groups. Furthermore, of the 149 patients in the non-HF control group, 44 patients were matched for CSB%, body mass index, and sex in a ratio of 1:2 to 22 patients with CHF. The average cycle length (CL) of CSB was compared among three groups: CHF in stable period (CHF-stable group), CHF in exacerbation period (CHF-exacerbation group), and control group. In addition, according to the status of HF, receiver operating characteristic (ROC) curves were generated to determine the optimal cut-off points for variation of CSB% and CL.

Results

Chronological change in CSB% among the three groups was significantly different. Standard deviation of CSB% (SD CSB%) before onset HF was significantly higher in both the AHF and CHF groups than in the control group. The CL of CSB was significantly longer in the CHF group than in the control group and was longer during the exacerbation period than during the stable period. The optimal cut-off value of CL that could differentiate patients with and without the onset of HF was 68.9 s.

Conclusion

The HF group demonstrated greater CSB variations and longer CL than the non-HF control group. Furthermore, the CL was longer during the exacerbation period of HF even in the same patient. These results suggest that remote monitoring of CPAP device data for CSB variations and CL might allow early prediction of the onset and exacerbation of HF.

Implantable cardiac devices in sleep apnoea diagnosis: A systematic review and meta-analysis

BACKGROUND

A particularly high burden of sleep apnoea is reported in patients treated with cardiac implants such as pacemakers and defibrillators. Sleep apnoea diagnosis remains a complex procedure mainly based on sleep and respiratory indices captured by polysomnography (PSG) or respiratory polygraphy (PG).

AIM

We aimed to evaluate the performance of implantable cardiac devices for sleep apnoea diagnosis compared to reference methods.

METHOD

Systematic structured literature searches were performed in PubMed, Embase and. Cochrane Library was performed to identify relevant studies. Quantitative characteristics of the studies were summarized and a qualitative synthesis was performed by a randomized bivariate meta-analysis and completed by pre-specified sensitivity analyses for different implant types and brands.

RESULTS

16 studies involving 999 patients met inclusion criteria and were included in the meta-analysis. The majority of patients were men, of mean age of 64 ± 4.6 years. Sensitivity of cardiac implants for sleep apnoea diagnosis ranged from 60 to 100%, specificity from 50 to 100% with a prevalence of sleep apnoea varying from 22 to 91%. For an apnoea-hypopnoea index threshold ≥30 events/h during polysomnography (corresponding to severe sleep apnoea), the overall performance of the implants was relevant with a sensitivity of 78% and a specificity of 79%. Subgroup analyses on implant type and brand provided no additional information owing to the small number of studies.

CONCLUSION

The respiratory disturbance index provided by cardiac implants is clinically relevant and might improve access to sleep apnoea diagnosis in at-risk cardiovascular populations. PROSPERO Registration number: CRD42020181656.

CPAP telemonitoring can track Cheyne-Stokes respiration and detect serious cardiac events: The AlertApnée Study

BACKGROUND AND OBJECTIVE

Case reports have suggested that continuous positive airway pressure (CPAP) telemonitoring can detect the onset of acute cardiac events such as decompensated heart failure (HF) or atrial fibrillation through an increase in the apnoea-hypopnoea index (AHI) and onset of Cheyne-Stokes Respiration (CSR). This study addressed whether long-term remote CPAP treatment telemonitoring revealing CSR can help detect serious cardiac events (SCEs) in obstructive sleep apnoea (OSA) patients.

METHODS

This monocentric prospective cohort study included adults receiving CPAP therapy for OSA with daily telemonitoring. Any sudden increase in AHI generated an alert for the home healthcare provider to download CPAP data to identify CSR. A medical consultation was scheduled if CSR was detected.

RESULTS

We included 555 adults (412 men; 57% with known cardiovascular comorbidities). During the 1-year follow-up, 78 CSR episodes were detected in 74 patients (CSR+). The main conditions associated with incident CSR were HF (24 patients [30.8%]), ventilatory instability (21, 26.9%), leaks (13, 16.7%), medications inducing central apnoeas (baclofen, ticagrelor, opioids) (7, 9.0%), arrhythmias (6, 7.7%) and renal failure (2, 2.6%). Fifteen (20.3%) CSR+ patients had a confirmed SCE. In univariable analysis, a CSR episode increased the risk of an SCE by 13.8-fold (5.7-35.6) (p < 0.0001), with an adjusted OR of 5.7 (2.0-16.8) in multivariable analysis.

CONCLUSION

Long-term telemonitoring of patients on CPAP treatment can alert CSR episodes and allows early detection of SCEs in patients with or without known cardiac comorbidities.

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

BACKGROUND

Continuous positive airway pressure (CPAP), the reference treatment for obstructive sleep apnoea (OSA), is used by millions of individuals worldwide with remote telemonitoring providing daily information on CPAP usage and efficacy, a currently underused resource. Here, we aimed to implement data science methods to provide tools for personalizing follow-up and preventing treatment failure.

METHODS

We analysed telemonitoring data from adults prescribed CPAP treatment. Our primary objective was to use Hidden Markov models (HMMs) to identify the underlying state of treatment efficacy and enable early detection of deterioration. Secondary goals were to identify clusters of rAHI trajectories which need distinct therapeutic strategies.

RESULTS

From telemonitoring records of 2860 CPAP-treated patients (age: 66.31 ± 12.92 years, 69.9% male), HMM estimated three states differing in variability within a given state and probability of shifting from one state to another. The daily inferred state informs on the need for a personalized action, while the sequence of states is a predictive indicator of treatment failure. Six clusters of rAHI trajectories were identified ranging from well-controlled patients (cluster 0: 669 (23%); mean rAHI 0.58 ± 0.59 events/h) to the most unstable (cluster 5: 470 (16%); mean rAHI 9.62 ± 5.62 events/h). CPAP adherence was 30 min higher in cluster 0 compared to clusters 4 and 5 (P value < 0.01).

CONCLUSION

This new approach based on HMM might constitute the backbone for deployment of patient-centred CPAP management improving the personalized interpretation of telemonitoring data, identifying individuals for targeted therapy and preventing treatment failure or abandonment.

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1007/s13167-021-00264-z.

Periodic breathing in patients with stable obstructive sleep apnea on long-term continuous positive airway pressure treatment: a retrospective study using CPAP remote monitoring data

PURPOSE

The purpose of this study was to investigate the rate of periodic breathing (PB) and factors associated with the emergence or persistence of PB in patients with obstructive sleep apnea (OSA) by continuous positive airway pressure (CPAP) remote monitoring data.

METHODS

This was a retrospective cohort study on 775 patients who had used the same model CPAP machine for at least 1 year as of September 1, 2020. The data were analyzed online using the dedicated analysis system. Using exporter software, average apnea/hypopnea index (AHI), average central apnea index (CAI), and average the rate of PB time (PB%) were cited.

RESULTS

Among 618 patients analyzed (age 61.7 ± 12.2 years, male 89%, BMI 27.2 ± 4.9), the average duration of CPAP use was 7.5 ± 4.0 years. The median PB% in stable patients was low at 0.32%, and only 149 patients (24%) had a PB% above 1%. Multiple regression analysis of factors for the development of PB showed that the most important factor was atrial fibrillation (Af) with a coefficient of 0.693 (95% CI; 0.536 to 0.851), followed by QRS duration with a coefficient of 0.445 (95% CI; 0.304 to 0.586), followed by history of heart failure, male sex, comorbid hypertension, obesity, and age. The average PB% for paroxysmal Af was significantly lower than that for persistent and permanent Af.

CONCLUSIONS

The median PB% in stable patients on CPAP treatment was low at 0.32%, with only 24% of patients having PB% ≥ 1%. Persistent Af and an increase in QRS duration were found to be important predictors of increased PB%.

CLINICAL TRIAL REGISTRATION

UMIN000042555 2021/01/01.

Artificial intelligence in sleep medicine: an American Academy of Sleep Medicine position statement

None

Sleep medicine is well positioned to benefit from advances that use big data to create artificially intelligent computer programs. One obvious initial application in the sleep disorders center is the assisted (or enhanced) scoring of sleep and associated events during polysomnography (PSG). This position statement outlines the potential opportunities and limitations of integrating artificial intelligence (AI) into the practice of sleep medicine. Additionally, although the most apparent and immediate application of AI in our field is the assisted scoring of PSG, we propose potential clinical use cases that transcend the sleep laboratory and are expected to deepen our understanding of sleep disorders, improve patient-centered sleep care, augment day-to-day clinical operations, and increase our knowledge of the role of sleep in health at a population level.

Interrelated atrial fibrillation and leaks triggering and maintaining central sleep apnoea and periodic breathing in a CPAP-treated patient

We report the case of a 71-year-old obese continuous positive airway pressure (CPAP)-treated man who developed an acute cardiac failure (ACF) triggered by atrial fibrillation. CPAP data downloaded from the CPAP software (Rescan®) retrospectively demonstrated the progressive development of a high residual central apnoea-hypopnoea index (AHI) with Cheyne-Stokes respiration (CSR). The AHI decreased after cardioversion allowing normalization of cardiac rhythm and function. Raw data extracted from CPAP software showed a gradual decrease in the periodic breathing cycle length related to a simultaneous improvement in left ventricular ejection fraction (LVEF) after cardioversion. During this clinical period of respiratory instability in the presence of cardiac failure, CSR episodes were exacerbated by ventilation overshoots followed by micro-arousals induced by leaks. This might explain the high night to night variability of CSR occurrence in susceptible patients with impaired cardiac function. Beyond attempts to improve cardiac function, leak reduction might represent an important target for CSR management.

[Telemonitoring in continuous positive airway pressure-treated patients with obstructive sleep apnoea syndrome: An algorithm proposal]

Most of the continuous positive airway pressure (CPAP) devices currently in use allow telemonitoring of observance, leaks and the apnoea-hypopnoea index (AHI). La Société française de recherche et de médecine du sommeil (SFRMS) and La Société de pneumologie de langue française (SPLF) workgroup offer to CPAP prescribers and to home care providers a scientific document which has the following purposes: to underline the relevance of the telemonitoring of leaks and the AHI, to define alert thresholds, to describe the principal mechanisms generating excessive leaks and high AHI, and to propose a diagnostic algorithm.