Emory researchers received a four-year $930,000 grant from the National Library of Medicine (NLM) to create an open-source suite of tools for advancing patient safety and quality in acute care settings.

Vicki Hertzberg PhD, FASA, from the School of Nursing is the primary investigator on the award along with Joyce Ho, PhD, from the Emory College of Arts and Sciences and Roy Simpson, DNP, RN, DPNAP, FAAN, FACMI. Hertzberg is an internationally recognized expert on “big data” and its impact on health care.

Despite a large body of evidence that nursing quality is directly related to patient outcomes in the acute care setting, nurses often lack timely information to improve individual patient outcomes. The Chart-assessment for Real-time Investigation of Nursing and Guidance (CARING) study aims to develop an automated machine learning system to report and predict adverse outcomes for hospitalized patients to assist nurses in care planning.

The widespread use of electronic health records (EHR) in hospitals now makes it possible to get timely health data for patients. However, outcome quality indicators can often only be determined by piecing together other information that are often buried in nursing notes.

“Due to the way the data are processed, it often takes six to nine months to get results,” says Simpson, a nurse informatician.

Ho, an expert on data mining and machine learning with a focus on healthcare applications, says the goal is to use machine learning tools with existing data in the EHR to determine the indicators in real-time and also use the data for predictive purposes.

The NLM is the world’s largest biomedical library, and maintains a vast print collection. It also produces electronic information resources on a wide range of topics and conducts and supports research, development, and training in biomedical informatics and health information technology.