An estimated 95% of hospitals in the United States use electronic medical records (EMRs) to manage and report on patient medical history. Yet, despite the widespread adoption of EMRs, they have not realized their full potential for conducting routine surveillance of quality measures, for measuring hospital performance, or for surveillance of patient safety. The use of EMR data for patient safety surveillance and predictive analytics has been especially underutilized for acute myocardial infarction (AMI—commonly known as heart attacks. A research team led by Dartmouth Institute Associate Professor Jeremiah Brown is developing a robust automated surveillance toolkit for 30-day re-admissions. The toolkit can be used to predict the risk of hospital re-admission, especially for those at highest risk of returning to the hospital.
An estimated 95% of hospitals in the U.S. use EMRs to manage & report on patient medical history.
The toolkit will focus on extracting complex information about patient health and health care factors, including social risk factors such as living status and social support at home. In particular, the research team will work with natural language processing to turn narrative notes entered by doctors, nurses, and other health care professionals into health measures that can be used to help identify risk of re-admission. The methods used to develop the toolkit will be translated into other reasons (in addition to AMIs) for hospital stays, potentially helping health care workers to maximize patient safety, while at the same time reducing health care costs by preventing unnecessary hospital stays. This work is supported by an R01 grant from the National Heart, Lung, and Blood Institute of the National Institutes of Health.
GET IN TOUCH