Text mining for clinical support

Abstract

Background: In 2013, the Dahlgren Memorial Library (DML) at the Georgetown University Medical Center began using text mining software to enable its clinical informationists to quickly retrieve specific, relevant information from MEDLINE abstracts while on patient rounds.Description: In 2013, DML licensed the use of the Linguamatics I2E text-mining program, and DML’s clinical informationist began using it to text mine MEDLINE abstracts on patient rounds. In 2015, DML installed I2E on a server at Georgetown and negotiated with Elsevier to obtain the right to download and text mine the full text of clinical journals in ScienceDirect to support clinical decision making. In 2016, the license agreements for the New England Journal of Medicine and the BMJ platform were modified to allow text mining. In 2018, PubMed Central open access content was added to the Linguamatics license.Results: DML’s informationists found that they were able to quickly find useful information that was not retrievable by traditional methods, and clinicians reported the information was valuable.Conclusion: The ability to text mine MEDLINE abstracts and selected journal articles on patient rounds has allowed DML’s clinical informationists to quickly search large amounts of medical literature that can be used to answer physicians’ clinical questions. DML plans to acquire additional journal articles from selected publishers in the future, which should increase the usefulness of the project.Virtual Projects are published on an annual basis in the Journal of the Medical Library Association (JMLA) following an annual call for virtual projects in MLAConnect and announcements to encourage submissions from all types of libraries. An advisory committee of recognized technology experts selects project entries based on their currency, innovation, and contribution to health sciences librarianship.

The Presentation, Pace, and Profile of Infection and Sepsis Patients Hospitalized Through the Emergency Department: An Exploratory Analysis

“…We focused on four clinical note types (“History and Physical,” “ED Provider,” “ED Progress,” and “Consult History and Physical”) and extracted unstructured text following five note header types (“History of Present Illness,” “Patient Presents With,” “HPI,” “HPI Comments,” and Summary”). We used existing signs and symptoms ontologies generated by Systematized Nomenclature of Medicine and National Cancer Institute to identify relevant terms, based on their implementation within the I2E natural language processing software (Linguamatics I2E 5.4.1R13, Cambridge, UK) ( 31 – 36 ). We iteratively developed documentation queries to account for symptom negation and common text patterns like comma-separated lists.…”

How Do Team-Level and Individual-Level Linguistic Styles Affect Patients’ Emotional Well-Being—Evidence from Online Doctor Teams

“…"Text mining" refers to the use of natural language processing (NLP) techniques to extract facts, relationships, and opinions from a text [32]. With the rise of social media, massive amounts of text data have emerged on the web, and the study of social media content based on text mining has received attention from scholars.…”

A Semiautonomous Approach for Strategic Decision-Making; an Application for Digital Transformation in Finance

“…According to Hartmann et al, 2019, text mining is divided into two classes of machine learning (ML) and lexicon-based methods [29]. In order to make the best at selecting either of these approaches, one should be equipped with the subjective knowledge over research objectives as well as computational and data analysis skills.…”