1
|
Yang L, Ding Z, Zhou J, Zhang S, Wang Q, Zheng K, Wang X, Chen L. Algorithmic detection of sleep-disordered breathing using respiratory signals: a systematic review. Physiol Meas 2024; 45:03TR02. [PMID: 38387048 DOI: 10.1088/1361-6579/ad2c13] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/10/2023] [Accepted: 02/22/2024] [Indexed: 02/24/2024]
Abstract
Background and Objective. Sleep-disordered breathing (SDB) poses health risks linked to hypertension, cardiovascular disease, and diabetes. However, the time-consuming and costly standard diagnostic method, polysomnography (PSG), limits its wide adoption and leads to underdiagnosis. To tackle this, cost-effective algorithms using single-lead signals (like respiratory, blood oxygen, and electrocardiogram) have emerged. Despite respiratory signals being preferred for SDB assessment, a lack of comprehensive reviews addressing their algorithmic scope and performance persists. This paper systematically reviews 2012-2022 literature, covering signal sources, processing, feature extraction, classification, and application, aiming to bridge this gap and provide future research references.Methods. This systematic review followed the registered PROSPERO protocol (CRD42022385130), initially screening 342 papers, with 32 studies meeting data extraction criteria.Results. Respiratory signal sources include nasal airflow (NAF), oronasal airflow (OAF), and respiratory movement-related signals such as thoracic respiratory effort (TRE) and abdominal respiratory effort (ARE). Classification techniques include threshold rule-based methods (8), machine learning models (13), and deep learning models (11). The NAF-based algorithm achieved the highest average accuracy at 94.11%, surpassing 78.19% for other signals. Hypopnea detection sensitivity with single-source respiratory signals remained modest, peaking at 73.34%. The TRE and ARE signals proved to be reliable in identifying different types of SDB because distinct respiratory disorders exhibited different patterns of chest and abdominal motion.Conclusions. Multiple detection algorithms have been widely applied for SDB detection, and their accuracy is closely related to factors such as signal source, signal processing, feature selection, and model selection.
Collapse
Affiliation(s)
- Liqing Yang
- Key Laboratory of Biorheological Science and Technology of Ministry of Education, Chongqing University, Chongqing, People's Republic of China
- Chongqing Medical Electronics Engineering Technology Research Center, Chongqing University, Chongqing, People's Republic of China
| | - Zhimei Ding
- Key Laboratory of Biorheological Science and Technology of Ministry of Education, Chongqing University, Chongqing, People's Republic of China
- Chongqing Medical Electronics Engineering Technology Research Center, Chongqing University, Chongqing, People's Republic of China
| | - Jiangjie Zhou
- Chongqing Medical Electronics Engineering Technology Research Center, Chongqing University, Chongqing, People's Republic of China
- Chongqing Key Laboratory of Artificial Intelligence and Service Robot Control Technology, Chongqing, People's Republic of China
| | - Siyuan Zhang
- Key Laboratory of Biorheological Science and Technology of Ministry of Education, Chongqing University, Chongqing, People's Republic of China
- Chongqing Medical Electronics Engineering Technology Research Center, Chongqing University, Chongqing, People's Republic of China
| | - Qi Wang
- Chongqing Medical Electronics Engineering Technology Research Center, Chongqing University, Chongqing, People's Republic of China
- Chongqing Key Laboratory of Artificial Intelligence and Service Robot Control Technology, Chongqing, People's Republic of China
| | - Kaige Zheng
- Chongqing Medical Electronics Engineering Technology Research Center, Chongqing University, Chongqing, People's Republic of China
- Chongqing Key Laboratory of Artificial Intelligence and Service Robot Control Technology, Chongqing, People's Republic of China
| | - Xing Wang
- Key Laboratory of Biorheological Science and Technology of Ministry of Education, Chongqing University, Chongqing, People's Republic of China
- Chongqing Key Laboratory of Artificial Intelligence and Service Robot Control Technology, Chongqing, People's Republic of China
| | - Lin Chen
- Key Laboratory of Biorheological Science and Technology of Ministry of Education, Chongqing University, Chongqing, People's Republic of China
- Chongqing Key Laboratory of Artificial Intelligence and Service Robot Control Technology, Chongqing, People's Republic of China
| |
Collapse
|
2
|
Oppersma E, Ganglberger W, Sun H, Thomas RJ, Westover MB. Algorithm for automatic detection of self-similarity and prediction of residual central respiratory events during continuous positive airway pressure. Sleep 2021; 44:5924368. [PMID: 33057718 PMCID: PMC8631077 DOI: 10.1093/sleep/zsaa215] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/24/2020] [Revised: 10/05/2020] [Indexed: 12/02/2022] Open
Abstract
Study Objectives Sleep-disordered breathing is a significant risk factor for cardiometabolic and neurodegenerative diseases. High loop gain (HLG) is a driving mechanism of central sleep apnea or periodic breathing. This study presents a computational approach that identifies “expressed/manifest” HLG via a cyclical self-similarity feature in effort-based respiration signals. Methods Working under the assumption that HLG increases the risk of residual central respiratory events during continuous positive airway pressure (CPAP), the full night similarity, computed during diagnostic non-CPAP polysomnography (PSG), was used to predict residual central events during CPAP (REC), which we defined as central apnea index (CAI) higher than 10. Central apnea labels are obtained both from manual scoring by sleep technologists and from an automated algorithm developed for this study. The Massachusetts General Hospital sleep database was used, including 2466 PSG pairs of diagnostic and CPAP titration PSG recordings. Results Diagnostic CAI based on technologist labels predicted REC with an area under the curve (AUC) of 0.82 ± 0.03. Based on automatically generated labels, the combination of full night similarity and automatically generated CAI resulted in an AUC of 0.85 ± 0.02. A subanalysis was performed on a population with technologist-labeled diagnostic CAI higher than 5. Full night similarity predicted REC with an AUC of 0.57 ± 0.07 for manual and 0.65 ± 0.06 for automated labels. Conclusions The proposed self-similarity feature, as a surrogate estimate of expressed respiratory HLG and computed from easily accessible effort signals, can detect periodic breathing regardless of admixed obstructive features such as flow limitation and can aid the prediction of REC.
Collapse
Affiliation(s)
- Eline Oppersma
- Cardiovascular and Respiratory Physiology Group, TechMed Centre, University of Twente, The Netherlands
| | | | - Haoqi Sun
- Department of Neurology, Massachusetts General Hospital, Boston, MA
| | - Robert J Thomas
- Department of Medicine, Beth Israel Deaconess Medical Center, Division of Pulmonary, Critical Care & Sleep Medicine, Harvard Medical School, Boston, MA
| | | |
Collapse
|
3
|
Pizarro C, van Essen F, Linnhoff F, Schueler R, Hammerstingl C, Nickenig G, Skowasch D, Weber M. Speckle tracking echocardiography in chronic obstructive pulmonary disease and overlapping obstructive sleep apnea. Int J Chron Obstruct Pulmon Dis 2016; 11:1823-34. [PMID: 27536094 PMCID: PMC4976816 DOI: 10.2147/copd.s108742] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/23/2022] Open
Abstract
Background COPD and congestive heart failure represent two disease entities of growing global burden that share common etiological features. Therefore, we aimed to identify the degree of left ventricular (LV) dysfunction in COPD as a function of COPD severity stages and concurrently placed particular emphasis on the presence of overlapping obstructive sleep apnea (OSA). Methods A total of 85 COPD outpatients (64.1±10.4 years, 54.1% males) and 20 controls, matched for age, sex, and smoking habits, underwent speckle tracking echocardiography for LV longitudinal strain imaging. Complementary 12-lead electrocardiography, laboratory testing, and overnight screening for sleep-disordered breathing using the SOMNOcheck micro® device were performed. Results Contrary to conventional echocardiographic parameters, speckle tracking echocardiography revealed significant impairment in global LV strain among COPD patients compared to control smokers (−13.3%±5.4% vs −17.1%±1.8%, P=0.04). On a regional level, the apical septal LV strain was reduced in COPD (P=0.003) and associated with the degree of COPD severity (P=0.02). With regard to electrocardiographic findings, COPD patients exhibited a significantly higher mean heart rate than controls (71.4±13.0 beats per minute vs 60.3±7.7 beats per minute, P=0.001) that additionally increased over Global Initiative for Chronic Obstructive Lung Disease stages (P=0.01). Albeit not statistically significant, COPD led to elevated N-terminal pro-brain natriuretic peptide levels (453.2±909.0 pg/mL vs 96.8±70.0 pg/mL, P=0.08). As to somnological testing, the portion of COPD patients exhibiting overlapping OSA accounted for 5.9% and did not significantly vary either in comparison to controls (P=0.07) or throughout the COPD Global Initiative for Chronic Obstructive Lung Disease stages (P=0.49). COPD-OSA overlap solely correlated with nocturnal hypoxemic events, whereas LV performance status was unrelated to coexisting OSA. Conclusion To conclude, COPD itself seems to be accompanied with decreased LV deformation properties that worsen over COPD severity stages, but do not vary in case of overlapping OSA.
Collapse
Affiliation(s)
- Carmen Pizarro
- Department of Internal Medicine II, Cardiology, Pneumology and Angiology, University Hospital Bonn, Bonn, Germany
| | - Fabian van Essen
- Department of Internal Medicine II, Cardiology, Pneumology and Angiology, University Hospital Bonn, Bonn, Germany
| | - Fabian Linnhoff
- Department of Internal Medicine II, Cardiology, Pneumology and Angiology, University Hospital Bonn, Bonn, Germany
| | - Robert Schueler
- Department of Internal Medicine II, Cardiology, Pneumology and Angiology, University Hospital Bonn, Bonn, Germany
| | - Christoph Hammerstingl
- Department of Internal Medicine II, Cardiology, Pneumology and Angiology, University Hospital Bonn, Bonn, Germany
| | - Georg Nickenig
- Department of Internal Medicine II, Cardiology, Pneumology and Angiology, University Hospital Bonn, Bonn, Germany
| | - Dirk Skowasch
- Department of Internal Medicine II, Cardiology, Pneumology and Angiology, University Hospital Bonn, Bonn, Germany
| | - Marcel Weber
- Department of Internal Medicine II, Cardiology, Pneumology and Angiology, University Hospital Bonn, Bonn, Germany
| |
Collapse
|
4
|
Pizarro C, Schaefer C, Kimeu I, Pingel S, Horlbeck F, Tuleta I, Nickenig G, Skowasch D. Underdiagnosis of Obstructive Sleep Apnoea in Peripheral Arterial Disease. Respiration 2015; 89:000371355. [PMID: 25720463 DOI: 10.1159/000371355] [Citation(s) in RCA: 22] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/07/2014] [Accepted: 11/18/2014] [Indexed: 02/28/2024] Open
Abstract
Background: Obstructive sleep apnoea (OSA) has interdependently been related to the onset and progression of a large portion of atherosclerotic cardiovascular disorders. In due consideration of OSA-mediated endothelial dysfunction, its impact on peripheral artery disease is conceivable, but undefined. Objectives: The aim of this study was to identify the prevalence of OSA in a lower extremity artery disease (LEAD) study population. Methods: A total of 91 patients receiving in- and outpatient treatment for LEAD were included in this prospectively conducted trial. In addition to an angiological examination, all patients underwent nocturnal screening for sleep-disordered breathing by use of SOMNOcheck micro® (SC micro) and - depending on the results obtained - polysomnography. Results: Patients were principally late middle-aged (69.3 ± 10.8 years), male (71.4%) and slightly overweight (BMI 26.8 ± 3.9). Overnight screening determined a sleep apnoea prevalence of 78.0%, of which 90.1% exhibited a predominantly obstructive genesis. The mean apnoea-hypopnoea index (AHI; events/h) and oxygen desaturation index (events/h) averaged 11.8 ± 13.4 and 8.9 ± 14.2, respectively. The individual AHI categories of non-pathological (<5), mild (5 to <15), moderate (15 to <30) and severe sleep apnoea (≥30) accounted for 22.0, 59.3, 13.2 and 5.5%, respectively. A distributive examination of AHI within LEAD severity groups evinced a significant association (p = 0.047). In cases of at least moderate sleep apnoea (AHI ≥15) polysomnography was performed (n = 17, 18.7% of the whole collective). Correlative analysis revealed a significant correlation between values obtained by SC micro recording and polysomnography, establishing the diagnostic accuracy of the screening results. Conclusions: OSA exhibits an important prevalence of 70.3% in LEAD patients with prior undiagnosed sleep-disordered breathing, indicating major OSA unawareness in this cardiovascular cohort. However, the impact of OSA treatment on LEAD propagation remains to be determined. © 2015 S. Karger AG, Basel.
Collapse
Affiliation(s)
- Carmen Pizarro
- Department of Internal Medicine II, Cardiology, Pneumology and Angiology, University Hospital Bonn, Bonn, Germany
| | | | | | | | | | | | | | | |
Collapse
|