SHARP

System for Hospital Adaptive Readmission Prediction and Management (SHARP) A real-time decision support system that estimates individual risk of hospital readmission within 30 days.

C-WIN

Tsui Laboratory and Children’s Hospital of Pittsburgh of UPMC have announced a research partnership to develop a software analytics tool, called the Cardiac ICU Warning Index (C-WIN), which will enable early prediction of catastrophic events such as cardiac arrest or emergency endotracheal tube intubation in patients with congenital heart disease. (http://insideupmc.upmc.com/cardiac-arrest-early-detection-system/)

NLP

In Tsui laboratory, we employ three NLP tools to process clinical free-text reports such as progress notes and discharge summary from electronic health records (EHR) systems.

  • TOPAZ: A homegrown NLP tool developed in the Department of Biomedical Informatics, University of Pittsburgh that employs the Unstructured Information Management Architecture (UIMA) pipeline framework and analytic engines to efficiently extract medical concepts from clinical free-text eports and outputs medical concepts in Unified Medical Language System (UMLS) concept unique identifier (CUI) codes. TOPAZ is written in JAVA programming language.
  • cTAKES: An open source Apache natural language processing tool originally developed at Mayo Clinics that employs UIMA pipeline framework and analytic engines to extract medical concepts from clinical free-text reports and outputs medical concepts in UMLS CUI codes. cTAKES is written in JAVA programming language.
  • MedLEE: A proprietary NLP tool originally developed by Dr. Carol Friedman at Columbia University that extracts medical concepts from clinical free-text reports and outputs medical concepts in UMLS CUI codes.