Are posttraumatic stress disorder mental health terms found in SNOMED‐CT medical terminology

Abstract

The authors sought to evaluate how well the Systematized Nomenclature of Medicine-Clinical Terms (SNOMED-CT) controlled vocabulary represents terms commonly used clinically when documenting posttraumatic stress disorder (PTSD). A list was constructed based on the PTSD criteria in the Diagnostic and Statistical Manual of Mental Disorders, Fourth Edition (DSM-IV; American Psychiatric Association, 1994), symptom assessment instruments, and publications. Although two teams mapping the terms to SNOMED-CT differed in their approach, the consensus mapping accounted for 91% of the 153 PTSD terms. They found that the words used by clinicians in describing PTSD symptoms are represented in SNOMED-CT. These results can be used to codify mental health text reports for health information technology applications such as automated chart abstraction, algorithms for identifying documentation of symptoms representing PTSD in clinical notes, and clinical decision support.

Automated Assessment of Patients’ Self-Narratives for Posttraumatic Stress Disorder Screening Using Natural Language Processing and Text Mining

“…The rapid advance of information technology over the past decade has led to breakthroughs in quality, continuity, and efficiency of e-health and e-psychology care (Drigas, Koukianakis, & Papagerasimou, 2011). One promising application is the use of natural language processing (NLP) and text mining techniques to identify clinical information contained in unstructured free text documents and to codify this information into structuralized data (Trusko et al, 2010). For instance, Pakhomov, Chacon, Wicklund, and Gundel (2011) extracted clear patterns of decline in grammatical complexity in language production affected by neurodegenerative disorders.…”

“…First, due to different backgrounds such as educational level, social status, living conditions, and so on, people often use various words to express the same concept. The openness and diversity of words may cause difficulties in mapping synonyms into a standardized reference terminology and extracting robust information that represents an identical domain (Trusko et al, 2010). Second, unlike the numeric data collected from questionnaires, textual data are often unstructured, neither having a predefined data model nor fitting well into relational patterns.…”

Characterization of near death experiences using text mining analyses: A preliminary study

“…Moreover, the text mining approach permitted to highlight a higher range of important features among the NDE narratives. We believe that the use of language processing via text mining techniques is a promising application to identify clinical and phenomenological information contained in unstructured freely expressed NDE testimonials [52]. For instance, automated speech analyses could further help in accurately discriminated between NDEs, NDEs-like (i.e., NDE phenomenology that is not associated with a life-threatening context; [4]).…”

Text mining and IRT for psychiatric and psychological assessment

“…One promising application is the use of natural language processing (NLP) and text mining techniques to identify the clinical information contained in unstructured free text documents and to codify this information into structuralized data (Trusko et al, 2010). For instance, Pakhomov and his colleagues (2011) extracted clear patterns of decline in grammatical complexity in language production affected by neurodegenerative disorders.…”

“…The challenges mainly exist from two aspects: First, due to different backgrounds, e.g., educational level, social status and living conditions, people often use various words to express the same concept. The openness and diversity of words may cause difficulties in mapping synonyms into a standardized reference terminology and extracting robust information that represents an identical domain (Trusko et al, 2010). Secondly, unlike the numeric data collected from questionnaires, textual data is often unstructured, neither having a pre-defined data model nor fitting well into relational patterns.…”