ED LOS: Predictive analytics to reduce emergency department length of stay for youth with behavioral health disorders
Reducing Emergency Department length of stay through population-based predictive modeling.
In-Patient/Acute Care Settings
Rational coronary care unit triage for stable patients with NSTEMI
Predicting the development of in-hospital complications requiring ICU care in initially stable patients with NSTEMI.
Improving inpatient goals of care conversations
Increasing and improving how hospitalists discuss goals of care with their patients and their families.
Comprehensive Cardiac Device Safety System
Creation of a “single source of truth” for device information in Cardiology.
Mobile Complex Care Plans for Children with Medical Complexity
Implementing a mobile complex care plan for provider and patient’s guardians to coordinate care approaches.
Project CALM: Personalized Music for Delirium Prevention
Development and implementation of a personalized music program that targets patients who are at high-risk for developing delirium and seen in the Perioperative Optimization for Senior Health (POSH) clinic at Duke.
CALYPSO: Machine Learning for Assessing & Managing Surgical Outcomes
Building statistical models and using machine learning principles to predict the absolute and relative risks of surgical complications for specific patients.
Duke Connected Care Chronic Kidney Disease Care Improvement Project
Use of validated statistical models on Duke data to predict the rate of decompensation for patients with Chronic Kidney Disease (CKD) while also creating a novel model of team-based care, Population Rounding TM.
Breast Cancer Caremaps
Create a customized Caremap driven by EHR data and presented in an infographic format to support an ‘at-a-glance’ reference to complex treatment options, decision points and timelines upon diagnosis.