This research will develop and validate machine learning enhanced predictive models improving the allocation of critical care pharmacists to intensive care units to reduce adverse drug events.
This research will use artificial intelligence and machine learning to create prediction tools integrated into visualization dashboards to guide critical care pharmacists in preventing adverse drug events.
This research evaluates an artificial intelligence risk predictive tool called CoMET that uses visual outputs of patient data to serve as an early warning system for patients at risk of cardiac decompensation to allow for earlier intervention and reduction in morbidity and mortality.
This research implemented a clinical decision support tool to identify patients at risk for a life-threatening, uncommon cardiac arrhythmia.
This research study addressed the overuse of blood cultures to diagnose sepsis by developing an electronic health record-embedded clinical decision support tool that draws upon the strengths of analytical and naturalistic decision making.
This project evaluated the use of an in-room interactive monitor to improve patient-centered care and family engagement within a pediatric intensive care unit.
This research identified the data domains at greatest risk of communication errors during intensive care unit (ICU) patient rounds, developed the ability to conduct simulated ICU rounds for research and training, and found that there is a need for real-time simultaneous reviewing of data by all members of the rounding team to reduce communication errors.
This study defined a knowledge base for a clinical decision support (CDS) tool and identified technology requirements for CDS design to optimize adoption of necrotizing enterocolitis prevention practices to support clinician decision making with the overall goal to improve the use of evidence-based practices for prevention and early recognition of NEC among premature infants.
Examines the effect of tele-ICU monitoring on mortality, complications, length of stay, cost-effectiveness, provider attitudes, and human factors issues in ICUs and 7 community hospitals.
Developed, implemented, and evaluated a cooperative effort for using health IT to facilitate a continuum of appropriate medical and developmental care, from the time infants are admitted to Neonatal Intensive Care Units (NICUs), through the transition process to community-based health care services for infants most at-risk for long-term neurodevelopmental problems.
