Surgical complications are associated with decreased quality of life, inferior survival, and significant cost increases to the health system. “Expert” opinion and population data currently drive guidelines that attempt to prevent or mitigate post-surgical complications. However, individualized risk profiles are not utilized in selecting specific prophylaxes or preventive therapies, such that preventable complications remain prevalent. Therefore, we constructed a Clinical AnaLYtical Platform for Surgical Outcomes (CALYPSO) as an integrated platform for personalized risk prediction and result delivery.

Our goal is to 1) accurately forecast the occurrence of complications, 2) deploy a burden-free interface to encourage adoption by providers, and 3) associate best-practice interventions with significant predictors of complications in order to impact patient outcomes.

Article: Journal of Biomedical Informatics - A comparison of models for predicting early hospital readmissions

Article: Using Machine Learning to Create New Models of Care

Presentation: Analytics Tools to Identify Patients with Chronic Kidney Disease

 

See a video of some of the work being done for this project:

Ouwen Huang's research for Calypso

http://dihi.org/news/ouwen-huang-s-research-calypso