Inspiration
We were struck by how many mistakes happen due to mix-ups in medical abbreviations, so we wanted to create something to fix this issue. For example, someone was given morphine sulfate because MS was seen on their record when it meant multiple sclerosis.
What it does
We added implementation to the EHR which automatically highlights abbreviations in medical records and provides the definition that fits given the context and history provided. Abbreviations deemed “Do Not Use” by The Joint Commission are highlighted in red, while other abbreviations are highlighted in yellow.
How we built it
We compiled a database from multiple sources, gathering over 1600 medical abbreviations. We created sample medical records after contacting professionals to simulate a real-life implementation into an Electronic Health Record. We used Flask to connect the front-end and back-end of our web model and facilitate the upload of the text file of abbreviations. We then maintained records of the Joint Commission's No Use Abbreviations, our database of universal abbreviations, and the patient's medical records to cross reference all 3 sources to provide an accurate translation of the Patient notes.
Challenges we ran into
We ran into many problems when creating this project. It started with the connection of the front and back end using Flask, as that was something none of us were familiar with. We also had to deal with many issues in maintaining our 4 separate files as it was a complicated process to cross-reference everything accurately.
Accomplishments that we're proud of
We are most proud of how we were able to create and filter our own data set and utilize this unfamiliar framework to create something that we believe can change the way medical staff communicate.
What we learned
We learned about how powerful collaboration during code is. If we were missing even one member in our group, we would have had no hope of completing this daunting task. But we managed to complete it by working together and communicating with each other.
What's next for Abbrev EZ
We want to connect with Oracle and Epic to implement Abbrev EZ so that it can be used in hospitals. We also want to contact EHR vendors to get a better understanding of how a system like this could be implemented in the system directly and transcend a simple web demo.
Log in or sign up for Devpost to join the conversation.