Heart pulse demodulation from Emfit mattress sensor using spectral and source separation techniques.

Jose Maria Perez-Macias1, Alpo Värri1, Sari-Leena Himanen1, Mirja Tenhunen2, Jari Viik1
1Tampere University, 2Tampere University Hospital (TAYS) and Tampere University


Introduction: Unobtrusive bed mattress sensors such us the electromechanical film transducer (Emfit) records the activity of the heart, breathing, and body movements with clinical applications ranging from epilepsy to sleep disorders. The mechanical activity of the heart recorded using these films is known as ballistocardiogram (BCG). However, BCG shapes changes on position, patient, and mattress.

Aim: In this study, we isolate a position-independent heart signal designed to isolate the heart activity recorded using an Emfit mattress sensor using extended polysomnography (PSG) recordings as a reference.

Methods: We used spectral and source separation techniques to infer heart Emfit pulse (EP). We validated the resulting signal using representative 10-minute normal breathing epochs from 31 subjects extracted from the PSG by estimating heart rate (HR) from the EP and compared it against the electrocardiogram (ECG) using non-overlapping one-minute windows.

Results: results show a signal similar in shape to a photoplethysmogram (PPG) with different timings in relation to the ECG’s R-peak. Finally, we found good agreement between HR with a mean absolute error (MAE) of 2.4 beats per minute (bpm) with standard deviation of 4.9bpm.

Conclusions: A position independent heart pulse signal from the Emfit mattress sensor was obtained in a range of subjects and validated by means of HR analysis.