Detection and presentation of bleeding events in the electronic health record
Bleeding and venous thromboembolism are frequent complications with hospitalised patients. Clinicians should be able to easily identify high risk cases when assessing risk of bleeding prior to surgery, preventive treatment for blood clots etc.
The aim is to aid clinical decision making using artificial intelligence (AI) to find critical information in electronic health records.
The goal in this project is to develop AI algorithms based on Natural Language Processing to find bleeding episodes reported in electronic health records. It will be developed based on extraction of relevant text from more than 300,000 electronic health records (unstructured data). When implemented, the algorithm can extract information on bleeding episodes from the patient medical record and the results will be reported to the medical doctor and patient in an easily understandable and relevant way.
The first part of the project proved that an artificial neural network can detect 98% of the bleeding episodes, and the next part of the project will develop a viable solution which can become part of daily clinical practice. The solution should be able to find indications of bleeding episodes, present a summary for the clinician and suggest measures.
Department of Clinical Biochemistry and Pharmacology, Odense University Hospital (OUH)
The Maersk Mc-Kinney Moller Institute, University of Southern Denmark (SDU)
Start: April 2021
End: March 2022
This project is a subproject of the project The Intelligent Health Record, wich includes several other subproject on how to use AI to find information in the electronic health record.
Read more about the project The Intelligent Health Record at ipj.nu (website only available in Danish).