Computer vision technologies are uniquely poised to accelerate the mental health evaluation process. Modern computer vision applications focus on video understanding tasks such as object classification, detection, and segmentation. In the context of healthcare, deep learning algorithms have become the de-facto standard for many medical imaging tasks. In the context of mental health, 3D imaging sensors can accurately capture facial expressions at high resolution. From these facial scans, we can build algorithms for detecting depression. We are striving to develop a low-cost AI-driven platform to screen for behavioral health symptoms within a primary care setting.
Reliable use of hand hygiene is associated with large reductions in hospital-acquired infections, which account for a significant fraction of hospital complications, mortality and healthcare expenditures. We are designing and demonstrating privacy-protective depth sensors and refining computer vision technology to make it easier for all clinicians and staff to perfect hand hygiene.
ICU patient monitoring by trained personnel is costly and time-consuming. Working with colleagues at Stanford's adult hospital and Intermountain Healthcare, we will apply and refine computer vision technology in the ICU to make it easier for clinicians to continuously identify opportunities to detect and respond to changes in patients' health status.
We are designing an integrated solution for the remote monitoring, assessment and support of seniors living independently at home. Our goal is to allow seniors to extend their capacity to live at home, improve their quality of life and avoid unnecessary and costly relocations into institutional care.