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

Abstract

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.

Figure 1.

Example of data extraction. (A) The actual de-identified text from a progress note, representing the writer's oncologic treatment history. The text has been annotated: bold phrases are problems, italicized phrases are treatments, and underlined phrases are tests. (B) Natural language processing output. Phrases were identified and assigned concept type (problem/treatment/test). Overall precision for this case was 88%, and overall recall was 76%. Three problems that were partially identified were scored as positive identifications. (C) A manually constructed example of a possible reformulation of the text from (A) into a structured element sufficient for succinct communication between providers. EHR, electronic health record; CT, computed tomography; FNA, fine needle aspiration.