BackgroundAutomatic measurement of respiratory rate in general hospital patients is difficult. Patient movement degrades the signal, and variation of the breathing cycle means that accurate observation for at least 60 s is needed for adequate precision.MethodsWe studied acutely ill patients recently admitted to a teaching hospital. Breath duration was measured from a tri-axial accelerometer attached to the chest wall, and compared with a signal from a nasal cannula. We randomly divided the patient records into a training (n=54) and a test set (n=7). We used machine learning to train a neural network to select reliable signals, automatically identifying signal features associated with accurate measurement of respiratory rate. We used the test records to assess the accuracy of the device, indicated by the median absolute difference between respiratory rates, provided by the accelerometer and by the nasal cannula.ResultsIn the test set of patients, machine classification of the respiratory signal reduced the absolute difference from 1.25 (0.56 to 2.18) to 0.48 (0.30 to 0.78) breaths/min (median, interquartile range). 50% of the recording periods were rejected as unreliable, and in one patient, only 10% of the signal time was classified as reliable. However, even only 10% of observation time would allow accurate measurement for 6 min in an hour of recording, giving greater reliability than nurse charting, which is based on much less observation time.ConclusionSignals from a body-mounted accelerometer yield accurate measures of respiratory rate, which could improve automatic illness scoring in adult hospital patients.