Respiratory cycle related EEG changes: Modified respiratory cycle segmentation

Evaluation of the agreement of tidal breathing parameters measured simultaneously using pneumotachography and structured light plethysmography

Structured light plethysmography (SLP) is a noncontact, noninvasive, respiratory measurement technique, which uses a structured pattern of light and two cameras to track displacement of the thoraco–abdominal wall during tidal breathing. The primary objective of this study was to examine agreement between tidal breathing parameters measured simultaneously for 45 sec using pneumotachography and SLP in a group of 20 participants with a range of respiratory patterns (“primary cohort”). To examine repeatability of the agreement, an additional 21 healthy subjects (“repeatability cohort”) were measured twice during resting breathing and once during increased respiratory rate (RR). Breath‐by‐breath and averaged RR, inspiratory time (tI), expiratory time (tE), total breath time (tTot), tI/tE, tI/tTot, and IE50 (inspiratory to expiratory flow measured at 50% of tidal volume) were calculated. Bland–Altman plots were used to assess the agreement. In the primary cohort, breath‐by‐breath agreement for RR was ±1.44 breaths per minute (brpm). tI, tE, and tTot agreed to ±0.22, ±0.29, and ±0.32 sec, respectively, and tI/tE, tI/tTot, and IE50/IE50_SLP to ±0.16, ±0.05, and ±0.55, respectively. When averaged, agreement for RR was ±0.19 brpm. tI, tE, and tTot were within ±0.16, ±0.16, and ±0.07 sec, respectively, and tI/tE, tI/tTot, and IE50 were within ±0.09, ±0.03, and ±0.25, respectively. A comparison of resting breathing demonstrated that breath‐by‐breath and averaged agreements for all seven parameters were repeatable (P > 0.05). With increased RR, agreement improved for tI, tE, and tTot (P ≤ 0.01), did not differ for tI/tE, tI/tTot, and IE50 (P > 0.05) and reduced for breath‐by‐breath (P < 0.05) but not averaged RR (P > 0.05).

Automatic Diagnosis of Obstructive Sleep Apnea/Hypopnea Events Using Respiratory Signals

Obstructive sleep apnea is a sleep disorder which may lead to various results. While some studies used real-time systems, there are also numerous studies which focus on diagnosing Obstructive Sleep Apnea via signals obtained by polysomnography from apnea patients who spend the night in sleep laboratory. The mean, frequency and power of signals obtained from patients are frequently used. Obstructive Sleep Apnea of 74 patients were scored in this study. A visual-scoring based algorithm and a morphological filter via Artificial Neural Networks were used in order to diagnose Obstructive Sleep Apnea. After total accuracy of scoring was calculated via both methods, it was compared with visual scoring performed by the doctor. The algorithm used in the diagnosis of obstructive sleep apnea reached an average accuracy of 88.33 %, while Artificial Neural Networks and morphological filter method reached a success of 87.28 %. Scoring success was analyzed after it was grouped based on apnea/hypopnea. It is considered that both methods enable doctors to reduce time and costs in the diagnosis of Obstructive Sleep Apnea as well as ease of use.