Clinical Research Directory

Cognitive Outcomes After Dexmedetomidine Sedation in Cardiac Surgery Patients

Anesthesia is a drug induced, reversible, comatose state that facilitates surgery and it is widely assumed that cognition returns to baseline after anesthetics have been eliminated. However, many patients have persistent memory impairment for weeks to months after surgery. Cardiac surgery appears to carry the highest risk of postoperative cognitive dysfunction (POCD). These cognitive deficits are associated with increased mortality, prolonged hospital stay and loss of independence. The investigators propose to investigate the role of Dexmedetomidine (DEX) in preventing long-term POCD after cardiac surgery and enhancing early postoperative recovery. It is anticipated that DEX will be the first effective preventative therapy for POCD, improve patient outcomes, and reduce length of stay and healthcare costs.

Intelligent Intensive Care Unit

Delirium, as a common complication of hospitalization, poses significant health problems in hospitalized patients. Though about a third of delirium cases can benefit from intervention, detecting and predicting delirium is still very limited in practice. A common characterization of delirium is change in activity level, causing patients to become hyperactive or hypoactive which is manifested in facial expressions and total body movements. This pilot study is designed to test the feasibility of a delirium detection system using movement data obtained from 3-axis wearable accelerometers and commercially available camera with facial recognition video system in conjunction with electronics medical record (EMR) data to analyze the relation of whole-body movement and facial expressions with delirium.

Pervasive Sensing and AI in Intelligent ICU

Important information related to the visual assessment of patients, such as facial expressions, head and extremity movements, posture, and mobility are captured sporadically by overburdened nurses, or are not captured at all. Consequently, these important visual cues, although associated with critical indices such as physical functioning, pain, delirious state, and impending clinical deterioration, often cannot be incorporated into clinical status. The overall objectives of this project are to sense, quantify, and communicate patients' clinical conditions in an autonomous and precise manner, and develop a pervasive intelligent sensing system that combines deep learning algorithms with continuous data from inertial, color, and depth image sensors for autonomous visual assessment of critically ill patients. The central hypothesis is that deep learning models will be superior to existing acuity clinical scores by predicting acuity in a dynamic, precise, and interpretable manner, using autonomous assessment of pain, emotional distress, and physical function, together with clinical and physiologic data.