Outlier detection of vital sign trajectories from COVID-19 patients

TL;DR

This paper introduces a new trajectory comparison algorithm using dynamic time warp distance to detect abnormal vital sign trends in COVID-19 patients, aiding early deterioration detection from wearable sensor data.

Contribution

The paper presents a novel trajectory comparison method based on dynamic time warp distance for identifying abnormal vital sign trends in patient monitoring.

Findings

Successfully identified abnormal epochs correlating with deteriorating health.

Detected patients at risk of readmission using outlier epoch analysis.

Validated method on real-world COVID-19 patient data.

Abstract

In this work, we present a novel trajectory comparison algorithm to identify abnormal vital sign trends, with the aim of improving recognition of deteriorating health. There is growing interest in continuous wearable vital sign sensors for monitoring patients remotely at home. These monitors are usually coupled to an alerting system, which is triggered when vital sign measurements fall outside a predefined normal range. Trends in vital signs, such as increasing heart rate, are often indicative of deteriorating health, but are rarely incorporated into alerting systems. We introduce a dynamic time warp distance-based measure to compare time series trajectories. We split each multi-variable sign time series into 180 minute, non-overlapping epochs. We then calculate the distance between all pairs of epochs. Each epoch is characterized by its mean pairwise distance (average link distance) to all other epochs, with clusters forming with nearby epochs. We demonstrate in synthetically generated data that this method can identify abnormal epochs and cluster epochs with similar trajectories. We then apply this method to a real-world data set of vital signs from 8 patients who had recently been discharged from hospital after contracting COVID-19. We show how outlier epochs correspond well with the abnormal vital signs and identify patients who were subsequently readmitted to hospital.