Smartphone Movement Sensors for Remote Monitoring of Respiratory Rate: Observational Study

Abstract

AbstractBackgroundMobile health offers potential benefits to patients and healthcare systems alike. Existing remote technologies to measure respiratory rate (RR) have limitations, such as cost, accessibility and reliability. Using smartphone sensors to measure RR may offer a potential solution.ObjectiveThe aim of this study was to conduct a comprehensive assessment of a novel mHealth smartphone application designed to measure RR using movement sensors.MethodsIn Study 1, 15 participants simultaneously measured their RR with the app, and an FDA cleared reference device. A novel reference method to allow the app to be evaluated ‘in the wild’ was also developed. In Study 2, 165 participants measured their RR using the app, and these measures were compared to the novel reference. Usability of the app was also assessed in both studies.ResultsThe app, when compared to the FDA-cleared and novel references, respectively, showed a mean absolute error (MAE) of 1.65 (SD=1.49) and 1.14 (1.44), relative MAE of 12.2 (9.23) and 9.5 (18.70) and bias of 0.81 (limits of agreement (LoA) =-3.27-4.89) and 0.08 (−3.68-3.51). Pearson correlation coefficients were 0.700 and 0.885. 93% of participants successfully operated the app on their first use.ConclusionsThe accuracy and usability of the app demonstrated here show promise for the use of mHealth solutions employing smartphone sensors to remotely monitor RR. Further research should validate the benefits that this technology may offer patients and healthcare systems.