Temporal relation discovery between events and temporal expressions identified in clinical narrative.

The automatic detection of temporal relations between events in electronic medical records has the potential to greatly augment the value of such records for understanding disease progression and patients' responses to treatments. We present a three-step methodology for labeling temporal relations using machine learning and deterministic rules over an annotated corpus provided by the 2012 i2b2 Shared Challenge. We first create an expanded training network of relations by computing the transitive closure over the annotated data; we then apply hand-written rules and machine learning with a feature set that casts a wide net across potentially relevant lexical and syntactic information; finally, we employ a voting mechanism to resolve global contradictions between the local predictions made by the learned classifier. Results over the testing data illustrate the contributions of initial prediction and conflict resolution.

A corpus of full-text journal articles is a robust evaluation tool for revealing differences in performance of biomedical natural language processing tools.

BACKGROUND: We introduce the linguistic annotation of a corpus of 97 full-text biomedical publications, known as the Colorado Richly Annotated Full Text (CRAFT) corpus. We further assess the performance of existing tools for performing sentence splitting, tokenization, syntactic parsing, and named entity recognition on this corpus. RESULTS: Many biomedical natural language processing systems demonstrated large differences between their previously published results and their performance on the CRAFT corpus when tested with the publicly available models or rule sets. Trainable systems differed widely with respect to their ability to build high-performing models based on this data. CONCLUSIONS: The finding that some systems were able to train high-performing models based on this corpus is additional evidence, beyond high inter-annotator agreement, that the quality of the CRAFT corpus is high. The overall poor performance of various systems indicates that considerable work needs to be done to enable natural language processing systems to work well when the input is full-text journal articles. The CRAFT corpus provides a valuable resource to the biomedical natural language processing community for evaluation and training of new models for biomedical full text publications.

Natural language processing and the oncologic history: is there a match?

PURPOSE: The widespread adoption of electronic health records (EHRs) is creating rich databases documenting the cancer patient's care continuum. However, much of this data, especially narrative "oncologic histories," are "locked" within free text (unstructured) portions of notes. Nationwide incentives, ranging from certification (Quality Oncology Practice Initiative) to monetary reimbursement (the Health Information Technology for Economic and Clinical Health Act), increasingly require the translation of these histories into treatment summaries for patient use and into tools to assist in transitions of care. Unfortunately, formulation of treatment summaries from these data is difficult and time-consuming. The rapidly developing field of automated natural language processing may offer a solution to this communication problem. METHODS: We surveyed a cross section of providers at Beth Israel Deaconess Medical Center regarding the importance of treatment summaries and whether these were being formulated on a regular basis. We also developed a program for the Informatics for Integrating Biology and the Bedside challenge, which was designed to extract meaningful information from EHRs. The program was then applied to a sample of narrative oncologic histories. RESULTS: The majority of providers (86%) felt that treatment summaries were important, but only 11% actually implemented them. The most common obstacles identified were lack of time and lack of EHR tools. We demonstrated that relevant medical concepts can be automatically extracted from oncologic histories with reasonable accuracy and precision. CONCLUSION: Natural language processing technology offers a promising method for structuring a free-text oncologic history into a compact treatment summary, creating a robust and accurate means of communication between providers and between provider and patient.