ABSTRACT
We present and evaluate measurement fusion and decision fusion for recognizing apnea and periodic limb movement in sleep episodes. We used an in-bed sensor system composed of an array of strain gauges to detect pressure changes corresponding to respiration and body movement. The sensor system was placed under the bed mattress during sleep and continuously recorded pressure changes. We evaluated both fusion frameworks in a study with nine adult participants that had mixed occurrences of normal sleep, apnea, and periodic limb movement. Both frameworks yielded similar recognition accuracies of 72.1 ± â¼ 12% compared to 63.7 ± 17.4% for a rule-based detection reported in the literature. We concluded that the pattern recognition methods can outperform previous rule-based detection methods for classifying disordered breathing and period limb movements simultaneously.
Subject(s)
Beds , Movement/physiology , Polysomnography , Respiratory Mechanics/physiology , Sleep Apnea Syndromes , Actigraphy/instrumentation , Actigraphy/methods , Adult , Aged , Extremities/physiology , Female , Humans , Male , Middle Aged , Polysomnography/instrumentation , Polysomnography/methods , Sleep/physiology , Sleep Apnea Syndromes/diagnosis , Sleep Apnea Syndromes/physiopathologyABSTRACT
This paper presents a working prototype of a wearable patient monitoring device capable of recording the heart rate, blood oxygen saturation, surface temperature and humidity during an magnetic resonance imaging (MRI) experiment. The measured values are transmitted via Bluetooth low energy (LE) and displayed in real time on a smartphone on the outside of the MRI room. During 7 MRI image acquisitions of at least 1 min and a total duration of 25 min no Bluetooth data packets were lost. The raw measurements of the light intensity for the photoplethysmogram based heart rate measurement shows an increased noise floor by 50LSB (least significant bit) during the MRI operation, whereas the temperature and humidity readings are unaffected. The device itself creates a magnetic resonance (MR) signal loss with a radius of 14 mm around the device surface and shows no significant increase in image noise of an acquired MRI image due to its radio frequency activity. This enables continuous and unobtrusive patient monitoring during MRI scans.