Eur Respir J 2007, doi:10.1183/09031936.00091206
Automatic detection of sleep-disordered breathing from a single channel airflow record
1 Dept of Pulmonology, Fukuoka National Hospital, Fukuoka, Japan
* To whom correspondence should be addressed. E-mail: nakano_h{at}palette.plala.or.jp.
Single channel airflow monitors developed for screening for sleep-disordered breathing (SDB) have conflicting results for their accuracy. We hypothesized that the analytic algorithm is crucial for the performance and tried to develop a novel computer algorithm. We employed 399 polysomnography records including a thermal sensor signal. The first 100 records were used in the development of the algorithm and the remainder for validation. In addition, 119 polysomnography records including a thermocouple signal and a nasal pressure signal were used for the validation. The algorithm was designed to obtain a time series (flow-power) using power spectral analysis that expresses fluctuation in the airflow signal amplitude. From the time series the algorithm detects transient falls of the flow-power and calculates flow-RDI defined as the number of the falls per hour. In the validation group, the areas under receiver operating characteristic curves for diagnosis of SDB (apnea-hypopnea index These results suggest that a single channel airflow monitor can be used to detect SDB automatically if the analytic algorithm is optimized. Keywords: Power spectral analysis, screening, sleep apnea, signal processing
This article has been cited by other articles:
| |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||