Apnea-hypopnea index estimation using overnight chest-wall accelerometry
Abstract
Rationale and study objectives: To develop a method for apnea-hypopnea index (AHI) estimation using a chest-worn accelerometer, as an approach to obstructive sleep apnea diagnosis and long-term monitoring of treatment, for example through positional therapy. Methods: We developed a method for AHI estimation by combining a cardiorespiratory sleep staging algorithm with an adapted neural network for detecting respiratory events. Originally based on electrocardiography and respiratory impedance plethysmography, the network was retrained using chest-wall accelerometry-based instantaneous heart rate and respiratory effort. Training and validation utilized accelerometer data from 413 participants across two centers, recorded during diagnostic overnight polysomnography (PSG), in absence of any therapy. The dataset was split equally: half was used to train the neural network, and the remaining half to evaluate its performance. This evaluation compared the accelerometry-derived overnight AHI against the reference from PSG, both overall and separately for supine and non-supine sleeping positions. Results: Sleep staging reached substantial agreement with polysomnography, achieving a Cohen's kappa coefficient of agreement of 0.67 for four-class sleep staging (Wake/REM/N1-N2/N3). AHI was estimated with highly reliable, showing an intraclass correlation coefficient of 0.90 (95% CI: 0.86-0.92) when compared to polysomnography-derived values. Performances were consistent in both supine and non-supine sleeping positions. Positive likelihood ratios were high (7.1, 16.0, and 165.7 for the mild, moderate, and severe OSA severity classes, using near-boundary double labeling). Negative likelihood ratios were low (0.095, 0.153, and 0.069 for the same cases). Conclusion: AHI can be reliably estimated using chest-wall accelerometry. This approach may be used in diagnostic tests for OSA but also to assess residual AHI during positional therapy.
Related
- Respiratory event duration reveals novel phenotypes beyond the apnea–hypopnea index in obstructive sleep apnea
- Beyond the Apnea-Hypopnea Index: Cardiovascular and Metabolic Phenotyping of Hypertensive Patients with Obstructive Sleep Apnea—A Narrative Review
- Craniofacial Load Modifies the Interaction of Obesity and Apnea Hypopnea Index Severity in Adult Males.
- Unilateral nonarteritic anterior ischemic optic neuropathy associated with obstructive sleep apnea-hypopnea syndrome: a case report.
- Accelerometry-Based and Gyroscope-Based Detection of Sleep Apnea Events: Systematic Review of Technical and Clinical Evidence.
BibTeX
@article{schipper2026apneahypopnea,
title = {{Apnea-hypopnea index estimation using overnight chest-wall accelerometry}},
author = {Fons Schipper and Pedro Fonseca and Angela Grassi and Marco Ross and Fokke van Meulen and Merel van Gilst and Pien Bosschieter and Emily Schoustra and Ruud van Sloun and Fayçal Abdenbi and Nico de Vries and Raphael Heinzer and Jean-Louis Pépin and Sebastiaan Overeem},
journal = {Frontiers in Sleep},
year = {2026},
month = jul,
doi = {10.3389/frsle.2026.1858267},
url = {https://hal.science/hal-05743857v1},
note = {CC BY},
}
RIS
TY - JOUR
TI - Apnea-hypopnea index estimation using overnight chest-wall accelerometry
AU - Fons Schipper
AU - Pedro Fonseca
AU - Angela Grassi
AU - Marco Ross
AU - Fokke van Meulen
AU - Merel van Gilst
AU - Pien Bosschieter
AU - Emily Schoustra
AU - Ruud van Sloun
AU - Fayçal Abdenbi
AU - Nico de Vries
AU - Raphael Heinzer
AU - Jean-Louis Pépin
AU - Sebastiaan Overeem
PY - 2026
DA - 2026/07/20
JO - Frontiers in Sleep
DO - 10.3389/frsle.2026.1858267
UR - https://hal.science/hal-05743857v1
AB - Rationale and study objectives: To develop a method for apnea-hypopnea index (AHI) estimation using a chest-worn accelerometer, as an approach to obstructive sleep apnea diagnosis and long-term monitoring of treatment, for example through positional therapy. Methods: We developed a method for AHI estimation by combining a cardiorespiratory sleep staging algorithm with an adapted neural network for detecting respiratory events. Originally based on electrocardiography and respiratory impedance plethysmography, the network was retrained using chest-wall accelerometry-based instantaneous heart rate and respiratory effort. Training and validation utilized accelerometer data from 413 participants across two centers, recorded during diagnostic overnight polysomnography (PSG), in absence of any therapy. The dataset was split equally: half was used to train the neural network, and the remaining half to evaluate its performance. This evaluation compared the accelerometry-derived overnight AHI against the reference from PSG, both overall and separately for supine and non-supine sleeping positions. Results: Sleep staging reached substantial agreement with polysomnography, achieving a Cohen's kappa coefficient of agreement of 0.67 for four-class sleep staging (Wake/REM/N1-N2/N3). AHI was estimated with highly reliable, showing an intraclass correlation coefficient of 0.90 (95% CI: 0.86-0.92) when compared to polysomnography-derived values. Performances were consistent in both supine and non-supine sleeping positions. Positive likelihood ratios were high (7.1, 16.0, and 165.7 for the mild, moderate, and severe OSA severity classes, using near-boundary double labeling). Negative likelihood ratios were low (0.095, 0.153, and 0.069 for the same cases). Conclusion: AHI can be reliably estimated using chest-wall accelerometry. This approach may be used in diagnostic tests for OSA but also to assess residual AHI during positional therapy.
SN - 2813-2890
SN - 2813-2890
ER -