Automated extraction and normalization of findings from cancer-related free-text radiology reports

We describe the performance of a particular natural language processing system that uses knowledge vectors to extract findings from radiology reports. LifeCode® (A-Life Medical, Inc.) has been successfully coding reports for billing purposes for several years. In this study, we describe the use of LifeCode® to code all findings within a set of 500 cancer-related radiology reports against a test set in which all findings were manually tagged. The system was trained with 1400 reports prior to running the test set. Results: LifeCode® had a recall of 84.5% and precision of 95.7% in the coding of cancer-related radiology report findings. Conclusion: Despite the use of a modest sized training set and minimal training iterations, when applied to cancer-related reports the system achieved recall and precision measures comparable to other reputable natural language processors in this domain.