Using Natural Language Processing to Enable In-depth Analysis of Clinical Messages Posted to an Internet Mailing List: A Feasibility Study

Abstract

BackgroundAn Internet mailing list may be characterized as a virtual community of practice that serves as an information hub with easy access to expert advice and opportunities for social networking. We are interested in mining messages posted to a list for dental practitioners to identify clinical topics. Once we understand the topical domain, we can study dentists’ real information needs and the nature of their shared expertise, and can avoid delivering useless content at the point of care in future informatics applications. However, a necessary first step involves developing procedures to identify messages that are worth studying given our resources for planned, labor-intensive research.ObjectivesThe primary objective of this study was to develop a workflow for finding a manageable number of clinically relevant messages from a much larger corpus of messages posted to an Internet mailing list, and to demonstrate the potential usefulness of our procedures for investigators by retrieving a set of messages tailored to the research question of a qualitative research team.MethodsWe mined 14,576 messages posted to an Internet mailing list from April 2008 to May 2009. The list has about 450 subscribers, mostly dentists from North America interested in clinical practice. After extensive preprocessing, we used the Natural Language Toolkit to identify clinical phrases and keywords in the messages. Two academic dentists classified collocated phrases in an iterative, consensus-based process to describe the topics discussed by dental practitioners who subscribe to the list. We then consulted with qualitative researchers regarding their research question to develop a plan for targeted retrieval. We used selected phrases and keywords as search strings to identify clinically relevant messages and delivered the messages in a reusable database.ResultsAbout half of the subscribers (245/450, 54.4%) posted messages. Natural language processing (NLP) yielded 279,193 clinically relevant tokens or processed words (19% of all tokens). Of these, 2.02% (5634 unique tokens) represent the vocabulary for dental practitioners. Based on pointwise mutual information score and clinical relevance, 325 collocated phrases (eg, fistula filled obturation and herpes zoster) with 108 keywords (eg, mercury) were classified into 13 broad categories with subcategories. In the demonstration, we identified 305 relevant messages (2.1% of all messages) over 10 selected categories with instances of collocated phrases, and 299 messages (2.1%) with instances of phrases or keywords for the category systemic disease. ConclusionsA workflow with a sequence of machine-based steps and human classification of NLP-discovered phrases can support researchers who need to identify relevant messages in a much larger corpus. Discovered phrases and keywords are useful search strings to aid targeted retrieval. We demonstrate the potential value of our procedures for qualitative researchers by retrieving a manageable set of messages concerning systemic and oral disease.

Dental Blogs, Podcasts, and Associated Social Media: Descriptive Mapping and Analysis

“…Future research may include the development of topic dictionaries that allow for finer coding and categorization of clinical content in dentistry. For example, natural language processing has been helpful in other studies and may have application here as well [ 38 ]. In terms of scope, our study did not address how dental clinicians locate, select, or make use of information that is available on these blogs, podcasts, and other social media.…”

Online Information Exchanges for Parents of Children With a Rare Health Condition: Key Findings From an Online Support Community

“…The online environment appears to offer excellent opportunities for health care professionals and health communication professionals to provide high-quality medical information to caregivers who are in information-seeking mode [57]. The online environment also offers opportunities for innovative interdisciplinary research that can use information technology to bridge gaps between nursing, medicine, and health communication among others [43,45,57,60]. …”

“…Future studies may need to explore and compare information-exchange processes in online communities dedicated to other conditions. Current advances in online content research such as natural language processing may be appropriate for analysis and comparison of large datasets across health conditions and disciplines [60]. …”

Interactive Cohort Identification of Sleep Disorder Patients Using Natural Language Processing and i2b2

“…Natural language processing (NLP) techniques have been widely used to quickly analyze a large amount of texts in support of humans [12]. Techniques such as part-of-speech tagging, parsing, and named entity recognition (NER) may speed up the process of identifying diagnoses, procedures and medications in clinical notes with satisfactory accuracy [13][14][15]. Syntactic structures obtained from parse trees provide useful indicators for extracting concepts and values from natural language sentences as well as for building queries [16].…”