Penn Medicine Healthcare Predictive Team

Advancing Healthcare With Predictive Analytics

Predictive Healthcare is focused on deploying predictive healthcare applications with re-designed healthcare pathways that greatly improve patient health and wellness.


Projects

Early Warning System (EWS)

Reduce sepsis impact to patients through early intervention and patient management.

Learn more >

Team
  • Clinical Leader: Craig Umscheid
  • Clinical Champion: Patrick Donnelly
  • PMC Champion: Kim Pavan
  • HUP Champion: Mike Lynch / Laurie Meadows
  • Data Science Lead: Corey Chivers
Vent ABC

The Vent ABC project is to reduce ICU LOS through total time on mechanical ventilation by providing real-time notifications and patient insight of readiness for weaning the ventilator and sedation that is integrated into a standardized protocol that coordinates care between Respiratory Therapist, Nursing, and Covering provider.

Team
  • Clinical Leader: Barry Fuchs
  • Project Lead: Steven Gudowski
  • Data Science: Corey Chivers
  • Innovation: Eugene Gitelman, David Do
  • E-Lert: Ann Huffenberger
  • PMC Champion: Huey Pigford
Lung Connect

Reduce ED visits for lung cancer patients. If we can predict ED utilization, we can intervene in the high-risk population, and prevent ED visits

Team
  • Clinical Leads: Tracey Evans, Abigail Berman
  • Project Lead: Jennifer Braun
  • Data Scientist: Asaf Hanish
  • Cancer Informatics: Peter Gabriel
  • Human Factors: Susan Regli
CHF Wired

Optimize coordination of care across the continuum for heart failure patients. The effort, referred to as “WIRED” is an acronym for the pathway of care developed by our multidisciplinary team with a goal of identifying heart failure patients in the Hospital and deploying targeted interventions based on risk. WIRED represents five vital pieces for HF care regardless of location.

Learn more >
Team
  • Project Lead: J. Fante-Gallagher
  • Clinical Lead: Lee Goldberg
  • Data Scientist: Asaf Hanish
  • Human Factors: Susan Regli
Obstetrics - Early Warning System (OB-EWS)

Reduce a women's risk of hemorrhage or infection during and after labor and delivery. If we can detect hemorrhage and infection earlier than we can improve patient outcomes, shorten LOS lower ED utilization.

Team
  • Clinical Leader: Corrina Oxford-Horrey
  • Project Lead: Stephanie Ewing
  • Data Science Lead: Mike Becker