Continuous Determination of Respiratory Rate in Hospitalized Patients using Machine Learning Applied to Electrocardiogram Telemetry
It addresses the need for automated, scalable patient monitoring for hospitalized patients at risk of clinical deterioration, particularly on standard medical wards where such monitoring is often absent, representing an incremental improvement by applying existing AI methods to pre-existing telemetry systems.
This work tackles the problem of inaccurate and time-consuming manual respiration rate (RR) monitoring in hospitalized patients by training a neural network to label RR from electrocardiogram telemetry waveforms, achieving mean absolute errors less than 1.78 breaths per minute in validation sets and demonstrating clinical utility through retrospective analysis linking RR dynamics to adverse events like intubation.
Respiration rate (RR) is an important vital sign for clinical monitoring of hospitalized patients, with changes in RR being strongly tied to changes in clinical status leading to adverse events. Human labels for RR, based on counting breaths, are known to be inaccurate and time consuming for medical staff. Automated monitoring of RR is in place for some patients, typically those in intensive care units (ICUs), but is absent for the majority of inpatients on standard medical wards who are still at risk for clinical deterioration. This work trains a neural network (NN) to label RR from electrocardiogram (ECG) telemetry waveforms, which like many biosignals, carry multiple signs of respiratory variation. The NN shows high accuracy on multiple validation sets (internal and external, same and different sources of RR labels), with mean absolute errors less than 1.78 breaths per minute (bpm) in the worst case. The clinical utility of such a technology is exemplified by performing a retrospective analysis of two patient cohorts that suffered adverse events including respiratory failure, showing that continuous RR monitoring could reveal dynamics that strongly tracked with intubation events. This work exemplifies the method of combining pre-existing telemetry monitoring systems and artificial intelligence (AI) to provide accurate, automated and scalable patient monitoring, all of which builds towards an AI-based hospital-wide early warning system (EWS).