Author Archives: worobey

Final weeks!  I finished up the results regarding the number of discrepancies in our corpus and created some visualizations of the data using R. These graphs and charts were used on the poster that we created for the Simmons Undergraduate Research Symposium. The poster was well received and I am grateful that I had the opportunity to present our project. It was really exciting to show all that we had learned this year.

This week I met again with BJ, a professor at Simmons, to discuss my code for the remaining Tags. I had encountered a problem where the code used to find the total number of discrepancies (vs the total number of patients with discrepancies) was producing a value that did not make sense. With his help I was able to debug the program and it is now working!


I've been working on primarily the same project throughout this time. Trying to find the total number of discrepancies in smoking status was pretty tricky, but I was able to find this number after doing some research and much perseverence (yay!). I also took some time to learn how to use knitr, a package in R that allows me to create html documents so I can easily share my code and results and reduce risk of error. As a group we also submitted a proposal  to the undergraduate research conference at our university.

This week I will begin to work on the problem of finding discrepancies of smoking statuses. In our weekly meeting we discussed some of the challenges that will come with this - primarily that smoking status can change in a much more complicated way than diabetes status. In the case of diabetes the patient must have had diabetes, so if they did not we knew there was a discrepancy. Smoking status, on the other hand, can switch back and forth many times However, if a patient is listed as a smoker in the first visit, and then as never having smoked in any later visits then there is a discrepancy. This is definitely going to be an interesting project.

This week we collaborated to finish a poster presentation for the 2016 Tapia conference. We also read journal articles from the journal of biomedical informatics. The articles were pertaining to the 2014 i2b2/UTHealth NLP shared task, which is where we are getting the information for our research.