Prediction of low pulse oxygen saturation in COVID-19 using remote monitoring post hospital discharge

Background: Monitoring systems have been developed during the COVID-19 pandemic enabling clinicians to remotely monitor physiological measures including pulse oxygen saturation (SpO(2)), heart rate (HR), and breathlessness in patients after discharge from hospital. These data may be leveraged to understand how symptoms vary over time in COVID-19 patients. There is also potential to use remote monitoring systems to predict clinical deterioration allowing early identification of patients in need of intervention.Methods: A remote monitoring system was used to monitor 209 patients diagnosed with COVID-19 in the period following hospital discharge. This system consisted of a patient-facing app paired with a Bluetooth-enabled pulse oximeter (measuring SpO(2) and HR) linked to a secure portal where data were available for clinical review. Breathlessness score was entered manually to the app. Clinical teams were alerted automatically when SpO(2) < 94 %. In this study, data recorded during the initial ten days of monitoring were retrospectively examined, and a random forest model was developed to predict SpO(2) < 94 % on a given day using SpO(2) and HR data from the two previous days and day of discharge.Results: Over the 10-day monitoring period, mean SpO(2) and HR increased significantly, while breathlessness decreased. The coefficient of variation in SpO2, HR and breathlessness also decreased over the monitoring period. The model predicted SpO(2) alerts (SpO(2 )< 94 %) with a mean cross-validated. sensitivity of 66 & PLUSMN; 18.57 %, specificity of 88.31 +/- 10.97 % and area under the receiver operating characteristic of 0.80 +/- 0.11. Patient age and sex were not significantly associated with the occurrence of asymptomatic SpO(2) alerts.Conclusion: Results indicate that SpO(2) alerts (SpO(2) < 94 %) on a given day can be predicted using SpO(2) and heart rate data captured on the two preceding days via remote monitoring. The methods presented may help early identification of patients with COVID-19 at risk of clinical deterioration using remote monitoring.