The utility of neural network in the diagnosis of Cheyne-Stokes respiration

Clinical applications of artificial intelligence in sleep medicine: a sleep clinician's perspective

BACKGROUND

The past few years have seen a rapid emergence of artificial intelligence (AI)-enabled technology in the field of sleep medicine. AI refers to the capability of computer systems to perform tasks conventionally considered to require human intelligence, such as speech recognition, decision-making, and visual recognition of patterns and objects. The practice of sleep tracking and measuring physiological signals in sleep is widely practiced. Therefore, sleep monitoring in both the laboratory and ambulatory environments results in the accrual of massive amounts of data that uniquely positions the field of sleep medicine to gain from AI.

METHOD

The purpose of this article is to provide a concise overview of relevant terminology, definitions, and use cases of AI in sleep medicine. This was supplemented by a thorough review of relevant published literature.

RESULTS

Artificial intelligence has several applications in sleep medicine including sleep and respiratory event scoring in the sleep laboratory, diagnosing and managing sleep disorders, and population health. While still in its nascent stage, there are several challenges which preclude AI's generalizability and wide-reaching clinical applications. Overcoming these challenges will help integrate AI seamlessly within sleep medicine and augment clinical practice.

CONCLUSION

Artificial intelligence is a powerful tool in healthcare that may improve patient care, enhance diagnostic abilities, and augment the management of sleep disorders. However, there is a need to regulate and standardize existing machine learning algorithms prior to its inclusion in the sleep clinic.

Detection of Cheyne-Stokes Breathing using a transformer-based neural network

Annotation of sleep disordered breathing, including Cheyne-Stokes Breathing (CSB), is an expensive and time-consuming process for the clinician. To solve the problem, this paper presents a deep learning-based algorithm for automatic sample-wise detection of CSB in nocturnal polysomnographic (PSG) recordings. 523 PSG recordings were retrieved from four different sleep cohorts and subsequently scored for CSB by three certified sleep technicians. The data was pre-processed and 16 time domain features were extracted and passed into a neural network inspired by the transformer unit. Finally, the network output was post-processed to achieve physiologically meaningful predictions. The algorithm reached a F1-score of 0.76, close to the certified sleep technicians showing that it is possible to automatically detect CSB with the proposed model. The algorithm had difficulties distinguishing between severe obstructive sleep apnea and CSB but this was not dissimilar to technician performance. In conclusion, the proposed algorithm showed promising results and a confirmation of the performance could make it relevant as a screening tool in a clinical setting.

Diagnosis of Obstructive Sleep Apnea in Patients with Associated Comorbidity

Obstructive sleep apnea (OSA) is a heterogeneous disease with many physiological implications. OSA is associated with a great diversity of diseases, with which it shares common and very often bidirectional pathophysiological mechanisms, leading to significantly negative implications on morbidity and mortality. In these patients, underdiagnosis of OSA is high. Concerning cardiorespiratory comorbidities, several studies have assessed the usefulness of simplified screening tests for OSA in patients with hypertension, COPD, heart failure, atrial fibrillation, stroke, morbid obesity, and in hospitalized elders.The key question is whether there is any benefit in the screening for the existence of OSA in patients with comorbidities. In this regard, there are few studies evaluating the performance of the various diagnostic procedures in patients at high risk for OSA. The purpose of this chapter is to review the existing literature about diagnosis in those diseases with a high risk for OSA, with special reference to artificial intelligence-related methods.

ResCSRF: Algorithm to Automatically Extract Cheyne-Stokes Respiration Features From Respiratory Signals

OBJECTIVE

Cheyne-Stokes respiration (CSR) related features are significantly associated with cardiac dysfunction. Scoring of these features is labor intensive and time-consuming. To automate the scoring process, an algorithm (ResCSRF) has been developed to extract these features from nocturnal measurement of respiratory signals.

METHODS

ResCSRF takes four signals (nasal flow, thorax, abdomen, and finger oxygen saturation) as input. It first detects CSR cycles and then calculates the respiratory features (cycle length, lung-to-periphery circulation time, and time to peak flow). It outputs nightly statistics (mean, median, standard deviation, and percentiles) of these features. It was developed and blindly tested on a group of 49 chronic heart failure patients undergoing overnight in-home unattended respiratory polygraphy recordings.

RESULTS

The performance of ResCSRF was evaluated against manual expert scoring (ES) (consensus between two independent sleep scorers). In terms of percentage of CSR per recording, the mean difference [reproducibility coefficient (RPC)] between ResCSRF and ES was 0.5(6.4) and 0.5(8.1) for development and test set, respectively. The nightly statistics of CSR-related features output by ResCSRF showed high correlation with ES on the blind test set with the mean difference of less than 3 s and RPC of less than 7 s.

CONCLUSIONS

These results indicate that ResCSRF is capable of automating the scoring of CSR-related features and could potentially be implemented into a remote monitoring system to regularly monitor patients' cardiac function.

Computer-Assisted Diagnosis of the Sleep Apnea-Hypopnea Syndrome: A Review

Automatic diagnosis of the Sleep Apnea-Hypopnea Syndrome (SAHS) has become an important area of research due to the growing interest in the field of sleep medicine and the costs associated with its manual diagnosis. The increment and heterogeneity of the different techniques, however, make it somewhat difficult to adequately follow the recent developments. A literature review within the area of computer-assisted diagnosis of SAHS has been performed comprising the last 15 years of research in the field. Screening approaches, methods for the detection and classification of respiratory events, comprehensive diagnostic systems, and an outline of current commercial approaches are reviewed. An overview of the different methods is presented together with validation analysis and critical discussion of the current state of the art.

Validation of ApneaLink as screening device for Cheyne-Stokes respiration

STUDY OBJECTIVES

Polysomnography (PSG) is the gold standard in diagnosing sleep disordered breathing (SDB). Diagnostic analysis of SDB is time-consuming and labor-intensive and entails long waiting lists for patients. The aim of this study was to assess the validity of a flow-based screening classifier as an automated diagnostic test for Cheyne-Stokes respiration (CSR).

SETTING

Sleep laboratory.

PARTICIPANTS

70 study subjects (28 with obstructive sleep apnea [OSA], 20 with CSR, 11 with CSR+OSA and 11 without SDB).

MEASUREMENTS

The nasal cannula flow signal was analyzed by ApneaLink (ResMed, Sydney, Australia), based on a classifier algorithm using pattern recognition. In a simultaneous PSG, results were compared with manual scoring of respiratory events by certified sleep experts.

RESULTS

For detecting CSR we obtained a sensitivity of 87.1% (95% confidence interval 75.3% to 98.9%), a specificity of 94.9% (95% confidence interval 87.9% to 100%), a positive likelihood ratio of 17.0, and a negative likelihood ratio of 0.14. The area under the curve (AUC) of the according receiver operating characteristic (ROC) curve was 93.4%. This resulted in an accuracy of 91.4% for identifying CSR.

CONCLUSION

In this study we demonstrated that the screening classifier was able to detect CSR with high diagnostic accuracy. Hence, ApneaLink equipped with CSR classifier is an appropriate screening tool which may help to prioritize patients with CSR for PSG.

Pattern recognition of obstructive sleep apnoea and Cheyne-Stokes respiration

The aim of this study was to assess the validity of an artificial neural network based on flow-related spectral entropy as a diagnostic test for obstructive sleep apnoea and Cheyne-Stokes respiration. A data set of 37 subjects was used for spectral analysis of the airflow by performing a fast Fourier transform. The examined intervals were divided into epochs of 3 min. Spectral entropy S was applied as a measure for the spread of the related power spectrum. The spectrum was divided into several frequency areas with various subsets of spectral entropy. We studied 11 subjects with obstructive apnoeas (n = 267 epochs), 10 subjects with obstructive hypopnoeas (n = 80 epochs), 11 subjects with Cheyne-Stokes respiration (n = 253 epochs) and 5 subjects with normal breathing in non-REM sleep (n = 174 epochs). Based on spectral entropy an artificial neural network was built, and we obtained a sensitivity of 90.2% and a specificity of 90.9% for distinguishing between obstructive apnoeas and Cheyne-Stokes respiration, and a sensitivity of 91.3% and a specificity of 94.6% for discriminating between obstructive hypopnoeas and normal breathing in non-REM sleep. This resulted in an accuracy of 91.5% for identifying flow patterns of obstructive sleep apnoea, Cheyne-Stokes respiration and normal breathing in non-REM sleep. It is concluded that the use of an artificial neural network relying on spectral analysis of the airflow could be a useful method as a diagnostic test for obstructive sleep apnoea and Cheyne-Stokes respiration.