COVID-19: A New AHRQ R21 Award will Study When is it Safe to Discharge a COVID-19 Patient from the Emergency Department
Find care now
If you are experiencing a medical emergency, please call 911 or seek care at an emergency room.
In her first federal award (AHRQ R21), Jessica E. Galarraga, MD, MPH will study, “An EHR-Based Screening Tool to Support Safe Discharges of COVID-19 Patients in the Emergency Department”. This study will develop a screening tool with electronic health record data using artificial intelligence/machine learning techniques to predict the risk of emergency department return and associated morbidity or mortality for COVID-19 patients. By developing a health IT solution that combines the use of natural language processing with a decision support tool, Dr. Galarraga seeks to turn unstructured clinical data into knowledge that can be applied to practice.
Oftentimes emergency clinicians must make rapid clinical decisions with limited information, which has heightened due to the challenges of COVID-19. Using predictive modeling with natural language processing and machine learning techniques can leverage the data-rich environment of the emergency department to improve the quality of care delivered to patients with COVID-19. This study has three aims: 1) Iteratively develop a concept map using mixed methods which will serve as the ontology categorizing predictive factors for COVID-19 emergency department returns and inform machine learning model development; 2) Develop and evaluate machine learning algorithms predictive of emergency department return risk for COVID-19 patients; 3) Prospectively validate a COVID-19 emergency department return screening tool (CERST) using real-time data.
This study will generate findings to improve the quality of care for COVID-19 patients in the emergency department. Findings will also be used to further optimize machine learning model, operationalize CERST as an EHR-integrated tool to support COVID-19 emergency department disposition decisions, and evaluate CERST’s performance on patient outcomes. Future studies will also employ mixed methods to develop guidelines on interventions by clinical and care transition staff using the tool to prevent emergency department returns and adverse outcomes among COVID-19 patients.
The study team hypothesizes that developing and operationalizing the proposed COVID-19- emergency department return screening tool (CERST) can help emergency department clinicians avoid premature discharges and engage in evidence-based discussions with COVID-19 patients regarding discharge plans. It may also reduce strain on hospital capacity by identifying patients safe for discharge and reserving resources for higher-risk COVID-19 patients.
Oftentimes emergency clinicians must make rapid clinical decisions with limited information, which has heightened due to the challenges of COVID-19. Using predictive modeling with natural language processing and machine learning techniques can leverage the data-rich environment of the emergency department to improve the quality of care delivered to patients with COVID-19. This study has three aims: 1) Iteratively develop a concept map using mixed methods which will serve as the ontology categorizing predictive factors for COVID-19 emergency department returns and inform machine learning model development; 2) Develop and evaluate machine learning algorithms predictive of emergency department return risk for COVID-19 patients; 3) Prospectively validate a COVID-19 emergency department return screening tool (CERST) using real-time data.
This study will generate findings to improve the quality of care for COVID-19 patients in the emergency department. Findings will also be used to further optimize machine learning model, operationalize CERST as an EHR-integrated tool to support COVID-19 emergency department disposition decisions, and evaluate CERST’s performance on patient outcomes. Future studies will also employ mixed methods to develop guidelines on interventions by clinical and care transition staff using the tool to prevent emergency department returns and adverse outcomes among COVID-19 patients.
The study team hypothesizes that developing and operationalizing the proposed COVID-19- emergency department return screening tool (CERST) can help emergency department clinicians avoid premature discharges and engage in evidence-based discussions with COVID-19 patients regarding discharge plans. It may also reduce strain on hospital capacity by identifying patients safe for discharge and reserving resources for higher-risk COVID-19 patients.
