AI Detects Body Position and Movement of Patients to Improve at Home Treatment
AI Detects Body Position and Movement of Patients to Improve at Home Treatment
1 PagesWakayama Medical University Hospital is researching a system that uses the Intel® Distribution of OpenVINO™ toolkit and 2D human pose estimation models to monitor patient movements during home blood transfusions. A smartphone captures video, sent via Zoom to a hospital PC where OpenVINO™ detects risky motions like getting up or bending an elbow. These are flagged for physician review, enabling timely responses such as contacting a caregiver or making a house call. With a 90% accuracy rate in matching body positions, the system supports safer home treatment without requiring deep learning expertise, thanks to OpenVINO’s user-friendly, pre-trained models.
