A generic rule-based system for clinical trial patient selection
arXiv:1907.06860v15 citations
Originality Synthesis-oriented
AI Analysis
This work addresses patient selection for clinical trials, but it is incremental as it applies an existing rule-based method to a specific challenge.
The authors tackled the problem of identifying patients meeting clinical trial criteria using a generic rule-based NLP pipeline, achieving an average F1 score of 0.89 on a test set and ranking 8th out of 45 teams.
The n2c2 2018 Challenge task 1 aimed to identify patients who meet lists of heterogeneous inclusion/exclusion criteria for a hypothetical clinical trial. We demonstrate a generic rule-based natural language pipeline can support this task with decent performance (the average F1 score on the test set is 0.89, ranked the 8th out of 45 teams ).