Search

We examine a 12-min video-recorded interaction among a patient (KN) in a disordered state of consciousness (DOC) and a speech language pathologist clinician (CL) that takes place in a medical rehabilitation setting. The video is a demonstration of how caregivers could use a clinical assessment to observe their loved one's behavior to communicate potential behavioral changes to healthcare professionals. The purpose of this paper is to make visible the communication practices used by participants that may not be obvious to researchers, medical rehabilitation practitioners, and clinical assessment developers. We use phenomenological, linguistic and conversation analytic approaches to analyze the interaction. We found that KN demonstrates multiple conversational competencies, some (but not all) of which are acknowledged by CL, and most of which are not directly addressed by the assessment scoring criteria. For example, KN demonstrates conversational competency by responding non-verbally to CL's prompts from the assessment protocol and following along with the unspoken rules of discourse. He does this primarily through gaze, which broadcasts the focus of his attention and actively signals his participation in the conversation. Though KN does not always respond correctly to CL's questions, he nevertheless demonstrates implicit conversational competencies during turns of talk such as returning to 'neutral' position which signals the completion of a turn of talk. KN's conversational competencies may be missed by CL and the assessment protocol but we argue that they are important in understanding KN's capacity. Our analyses show that competency is not simply a performance by one person who appropriately and correctly responds to a series of questions in a prescribed time frame. Competence is a collaborative achievement among participants, co-produced in situ , and influenced by linguistic and cultural habits of talk and epistemic norms that privilege clinical knowledge and expertise. • Competency is a collaborative achievement grounded on participants' conversational strategies. • Analytic pluralism allows for analyses using multiple perspectives. • Clinical assessments have unacknowledged epistemic privilege. [ABSTRACT FROM AUTHOR]

Background: Two years into the COVID-19 pandemic and with more than five million deaths worldwide, the healthcare establishment continues to struggle with every new wave of the pandemic resulting from a new coronavirus variant. Research has demonstrated that there are variations in the symptoms, and even in the order of symptom presentations, in COVID-19 patients infected by different SARS-CoV-2 variants (e.g., Alpha and Omicron). Textual data in the form of admission notes and physician notes in the Electronic Health Records (EHRs) is rich in information regarding the symptoms and their orders of presentation. Unstructured EHR data is often underutilized in research due to the lack of annotations that enable automatic extraction of useful information from the available extensive volumes of textual data. Methods: We present the design of a COVID Interface Terminology (CIT), not just a generic COVID-19 terminology, but one serving a specific purpose of enabling automatic annotation of EHRs of COVID-19 patients. CIT was constructed by integrating existing COVID-related ontologies and mining additional fine granularity concepts from clinical notes. The iterative mining approach utilized the techniques of 'anchoring' and 'concatenation' to identify potential fine granularity concepts to be added to the CIT. We also tested the generalizability of our approach on a hold-out dataset and compared the annotation coverage to the coverage obtained for the dataset used to build the CIT. Results: Our experiments demonstrate that this approach results in higher annotation coverage compared to existing ontologies such as SNOMED CT and Coronavirus Infectious Disease Ontology (CIDO). The final version of CIT achieved about 20% more coverage than SNOMED CT and 50% more coverage than CIDO. In the future, the concepts mined and added into CIT could be used as training data for machine learning models for mining even more concepts into CIT and further increasing the annotation coverage. Conclusion: In this paper, we demonstrated the construction of a COVID interface terminology that can be utilized for automatically annotating EHRs of COVID-19 patients. The techniques presented can identify frequently documented fine granularity concepts that are missing in other ontologies thereby increasing the annotation coverage. [ABSTRACT FROM AUTHOR]