Research
Print page Print page
Switch language
Rigshospitalet - a part of Copenhagen University Hospital
E-pub ahead of print

Robust, ECG-based algorithm for Sleep Disordered Breathing detection in large population-based cohorts using an automatic, data-driven approach

Research output: Contribution to journalJournal articleResearchpeer-review

DOI

  1. Cerebral blood flow, oxygen metabolism, and lactate during hypoxia in patients with obstructive sleep apnea

    Research output: Contribution to journalJournal articleResearchpeer-review

  2. Comparison of computerized methods for rapid eye movement sleep without atonia detection

    Research output: Contribution to journalJournal articleResearchpeer-review

  1. Long-term health and socioeconomic consequences of childhood and adolescent-onset of narcolepsy

    Research output: Contribution to journalJournal articleResearchpeer-review

  2. The role of sleep in the pathophysiology of nocturnal enuresis

    Research output: Contribution to journalReviewResearchpeer-review

  3. CD8+ T cells from patients with narcolepsy and healthy controls recognize hypocretin neuron-specific antigens

    Research output: Contribution to journalJournal articleResearchpeer-review

  4. External validation of a data-driven algorithm for muscular activity identification during sleep

    Research output: Contribution to journalJournal articleResearchpeer-review

  5. Rapid eye movements are reduced in blind individuals

    Research output: Contribution to journalJournal articleResearchpeer-review

  • Mads Olsen
  • Emmanuel Mignot
  • Poul J Jennum
  • Helge Bjarup Dissing Sorensen
View graph of relations

STUDY OBJECTIVES: Up to 5% of adults in Western countries have undiagnosed sleep disordered breathing (SDB). Studies have shown that electrocardiogram (ECG)-based algorithms can identify SDB and may provide alternative screening. Most studies however have limited generalizability as they have been conducted using the Apnea-ECG database, a small sample database that lacks complex SDB cases.

METHODS: Here, we developed a fully automatic, data-driven algorithm that classifies apnea and hypopnea events based on the ECG using almost 10.000 polysomnographic sleep recordings from two large population-based samples, the Sleep Heart Health Study (SHHS) and the Multi-Ethnic Study of Atherosclerosis (MESA), which contain subjects with a broad range of sleep and cardiovascular diseases (CVD) to ensure heterogeneity.

RESULTS: Performances on average were Se=68.7%, Pr=69.1%, F1=66.6% per subject, and accuracy of correctly classifying AHI severity score was Acc=84.9%. Target apnea-hypopnea index (AHI) and predicted AHI were highly correlated (R2=0.828) across subjects, indicating validatity in predicting SDB severity. Our algorithm proved to be statistically robust between databases, between different Periodic Leg Movement Index (PLMI) severity groups, and for subjects with previous CVD incidents. Further, our algorithm achieved state-of-the-art performance of Se=87.8%, Sp=91.1%, Acc=89.9% using independent comparisons and Se=90.7%, Sp=95.7%, Acc=93.8% using a transfer learning comparison on the Apnea-ECG database.

CONCLUSION: Our robust and automatic algorithm constitutes a minimally intrusive and inexpensive screening system for the detection of SDB event using the ECG to alleviate the current problems and costs associated with diagnosing SDB cases and to provide a system capable of identifying undiagnosed SDB cases.

Original languageEnglish
JournalSleep (Online)
ISSN1550-9109
DOIs
Publication statusE-pub ahead of print - 2020

ID: 59152572