This research will develop and validate advanced statistical and machine learning methods to assess and improve representational semantic integrity of terminologies in large clinical databases.
This research will assess the validity of patient-level computable social factor phenotypes used to predict a patient’s risk of increased healthcare utilization and costs.
This research will adapt and implement a digital mental health intervention to improve care coordination of mental health services in ambulatory care settings.
This research will compare the use of predictive modeling versus traditional questionnaires to identify those with unmet social needs, use the superior method to inform the development of a clinical decision support tool, and evaluate the tool’s impact on referrals to social providers.
This study will integrate a previously piloted risk tool and clinical decision aid, MammoScreen, with an EHR to provide personalized decision support for both patients and clinicians to improve quality of care for women who are at increased risk for breast cancer.
This research will develop and evaluate an artificial intelligence-driven clinical decision support system to detect and manage acute kidney injury in the emergency department.
This research will implement a personalized and electronically integrated shared clinical decision support system for left ventricular assist devices in patients with advanced heart failure.
The research team will implement and evaluate an integration application that incorporates relevant health information exchange data directly into the electronic health record in the emergency department.
This research’s goal is to show that interoperability, including adoption of regional health information exchanges, improves mortality rates and care efficiency at the population and patient levels.
This project aims to refine and develop methods to address missing electronic health record data to improve data quality and research validity.
