Following a highly successful first Healthcare Hackathon last year, Linguamatics will be hosting another Hackathon at the 2016 Text Mining Summit in Cape Cod. This half-day event utilizing Linguamatics I2E platform will allow teams to solve real-life challenges. Sign up for the 2016 Hackathon and benefit from a greater understanding of query strategies and learn new skills from colleagues and Linguamatics NLP text mining experts.
There is significant interest and scope for the application of NLP to improve clinical trials. Identification of patient populations is difficult to scale due to complex eligibility criteria and medical records, which make manual chart review a long and laborious process. Many trials suffer from slow accrual and may miss target numbers because of these issues.
The 2016 Hackathon will focus on a Diabetes clinical trial definition that the Linguamatics Health Science Center (LHSC) wish to run.
The first part of the challenge will be to assess diabetes-related criteria from funded clinical trials. Writing a successful grant is challenging, competition for funds increases yearly. It’s beneficial to see what trials are receiving funding to compare to your grant application. This process will involve mining clinical trial.gov to ensure your success.
The second part of the challenge will be to mine a patient population for matches to the LHSC clinical trial and to export values associated with the eligibility criteria of the trial. The resulting data set will enable a much faster identification of potential trial subjects to ensure successful recruitment. An unannotated set of medical transcripts will be provided to participants to evaluate and build queries against.
Both sets of data will have been pre-indexed with appropriate disease and medication ontologies and any region detection preprocessing that the data set requires. In addition, a small set of example medical transcripts and clinical trials will be provided with annotations, a “gold standard”, to demonstrate how results should appear.
At the end of the session we will present some hints and tips for getting good results.
Unseen annotated test data set will be used to assess each team’s efforts, and the best results will be presented during the next day.
Who should attend?
The I2E Query Hackathon is for existing I2E users rather than new users. Participation for the Hackathon is free but registration is required and spaces are limited so please sign up early. If you plan to stay on to attend the rest of the Text Mining Summit you will need to sign up to that.
Entries will be submitted at the end of the day and judged by Linguamatics CTO, David Milward and Elizabeth Marshall, Director, Clinical Analytics