Estimation of Clinical Workload and Patient Activity using Deep Learning and Optical Flow
This work addresses the need for automated, contactless monitoring of patient conditions and clinical workload in healthcare, particularly in intensive care units, though it appears incremental by combining existing object detection and optical flow methods.
The paper tackled the problem of estimating patient agitation and caregiver workload in a hospital setting by analyzing patient and worker motion from thermal video frames, achieving performance illustrated through comparison with clinical agitation scores on over 32,000 frames from ICU recordings.
Contactless monitoring using thermal imaging has become increasingly proposed to monitor patient deterioration in hospital, most recently to detect fevers and infections during the COVID-19 pandemic. In this letter, we propose a novel method to estimate patient motion and observe clinical workload using a similar technical setup but combined with open source object detection algorithms (YOLOv4) and optical flow. Patient motion estimation was used to approximate patient agitation and sedation, while worker motion was used as a surrogate for caregiver workload. Performance was illustrated by comparing over 32000 frames from videos of patients recorded in an Intensive Care Unit, to clinical agitation scores recorded by clinical workers.