Estimation of respiratory information from the built-in pressure sensors of a dialysis machine

The purpose of the present study is to determine the feasibility of estimating respiratory information from the built-in pressure sensors of a dialysis machine. The study database consists of simultaneous recordings of pressure signals and capnographic signals from 6 patients during 7 hemodialysis treatment sessions. Respiration rates were estimated using respiratory induced variations in the beat-to-beat interval series of the cardiac component of the pressure signal and respiratory induced baseline variations in the pressure signal, respectively. The estimated respiration rates were compared to a reference respiration rate determined from the capnograhpic signal. The root-mean-square error of the estimated respiration rate from the baseline variations of the pressure signal was 2.10 breaths/min; the corresponding error of the estimated respiration rate from the beat-to-beat interval series of the cardiac component was 4.95 breaths/min. The results suggest that it is possible to estimate respiratory information from the pressure sensors.