We are excited about our current body of work and want to share project insights. For more information, questions about our work, or to share ideas, please contact us.
We are excited about our current body of work and want to share project insights. For more information, questions about our work, or to share ideas, please contact us.
By developing a composite score algorithm based on wearable collected data, this project assesses the functional status of patients with lumbar degenerative spine disease.
Project Lead: Camilo Molina
active
The team is working to determine the feasibility and effectiveness of using an iPad within BJC hospitals to allow a video conversation among patients, their caregivers, their PCP, and the hospitalist involved in their inpatient care.
Project Lead: Mark Williams
active
This project investigates the feasibility of a simulation-free workflow to enhance clinical decision-making with up-front planning on diagnostic images.
Project Lead: Tianyu Zhao
active
In an effort to reduce postoperative pulmonary complications, the team is working to determine the efficacy of perioperative incentive spirometry to improve forced expiratory volume (FEV1).
Project Lead: Chet W. Hammill and Chenyang Lu
completed
The team worked to detect intraoperative hypoxemia within the Epic electronic medical records and assess the clinical meaningfulness of the Deep Intraoperative Alert system.
Project Lead: Michael C. Montana and Thomas Kannampallil
completed
This project uses intensive psychometric and biometric data to define how different disease domains impact patient recovery from lumbar fusion surgery.
Project Lead: Wilson Z. Ray and Jacob Greenberg
completed
By conducting user evaluations of the current ENVISION prototype, the team is working to create a functional version of the ENVISION tool to assist caregivers in the assessment and management of advanced cancer patients.
Project Lead: Karla T. Washington
completed
This project demonstrates the feasibility of a pressure sensor device to record skin pressure and prevent pressure injuries in ICU patients.
Project Lead: Amanda Westman and Justin M. Sacks
completed
By developing a machine learning, predictive-analytics model, this COVID-19 Big Ideas team identified variables associated with the need for ECMO in pediatric COVID-19 patients.
Project Lead: Ahmed Said
completed
In an effort to predict and reduce physician burnout, the team used advanced machine learning to measure physician workload and its association with burnout and medication errors.
Project Lead: Sunny Lou
completed
Using AI-based Cognitive Behavioral Therapy, this project generated an effective point-of-contact electronic medical records notification to alert clinicians when a patient shows concerning anxiety or depression symptoms.
Project Lead: Abby Cheng
completed
Focusing on youth with Type 1 diabetes, the team optimized an existing smartphone app that will test dynamic cognition of these patients.
Project Lead: Tamara Hershey and Mary Katherine Ray
completed