SummaryIntroduction: This article is part of the Focus Theme of Methods of Information in Medicine on “Biosignal Interpretation: Advanced Methods for Studying Cardiovascular and Respiratory Systems”.Objectives: The aim of this study is to assess the reliability of the estimated Nocturnal Heart Rate (HR), recorded through a bed sensor, compared with the one obtained from standard electrocardiography (ECG).Methods: Twenty-eight sleep deprived patients were recorded for one night each through matrix of piezoelectric sensors, integrated into the mattress, through polysomnography (PSG) simultaneously. The two recording methods have been compared in terms of signal quality and differences in heart beat detection.Results: On average, coverage of 92.7% of the total sleep time was obtained for the bed sensor, testifying the good quality of the recordings. The average beat-to-beat error of the inter-beat intervals was 1.06%. These results suggest a good overall signal quality, however, considering fast heart rates (HR > 100 bpm), performances were worse: in fact, the sensitivity in the heart beat detection was 28.4% while the false positive rate was 3.8% which means that a large amount of fast beats were not detected.Conclusions: The accuracy of the measurements made using the bed sensor has less than 10% of failure rate especially in periods with HR lower than 70 bpm. For fast heart beats the uncertainty increases. This can be explained by the change in morphology of the bed sensor signal in correspondence of a higher HR.
Probabilistic data fusion model for heart beat detection from multimodal physiological data
