The cost of care in the Neonatal Intensive Care Unit (NICU) is extremely high. Care coordination has been recognized to reduce costs and improve care quality in the NICU. Challenges in quantifying coordination and measuring its effectiveness, however, have hindered its optimization in healthcare institutions. Existing studies address this issue by using observations to study coordination structure, which requires substantial manual effort and is restricted to a limited number of provider types. We represent care coordination through provider interaction networks composed of all NICU provider types that are automatically learned from electronic health records. We further quantify effectiveness of the coordination by measuring the relationship between the provider network structures and patient length of stay.

Describe the new knowledge and additional skills the participant will gain after attending your presentation.: Based on our research in the Neonatal Intensive Care Unit, we found that active dissemination of patient information to team members may be associated with reduced patient’s length of stay. Attendees are encouraged to take our electronic health records (EHR) data-driven approach to representing care coordination and quantifying it via network analysis.


Cindy Kim (Presenter)
Vanderbilt University

Christoph Lehmann, Vanderbilt University Medical Center
Jonathan Schildcrout, Vanderbilt University Medical Center
Dupree Hatch, Vanderbilt University Medical Center
Dan France, Vanderbilt University Medical Center
You Chen, Vanderbilt University Medical Center

Presentation Materials: