Using Natural Language Processing to Understand Unstructured Healthcare Data

Parker, R. David; Abram, Marissa D.; Mancini, Karen

doi:10.2139/ssrn.4092364

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…12 Approximately 80% of medical data collected in electronic health records are unstructured because they cannot be easily managed using predefined data models. 13 Therefore, clinicians use multiple data collection tools, leading to poor oversight, waste of time, and can ultimately result in poorer decision-making for the patients’ sake. Clinicians additionally collect information on patients’ schedules and ward transfers during their hospital stay.…”

Section: Introductionmentioning

confidence: 99%

Triptychon: Usability evaluation and implementation of a web-based application for patients’ lab and vital parameters

Kittel,

Moorthy,

Rao

et al. 2023

DIGITAL HEALTH

View full text Add to dashboard Cite

Background A major challenge in healthcare is the interpretation of the constantly increasing amount of clinical data of interest to inpatients for diagnosis and therapy. It is vital to accurately structure and represent data from different sources to help clinicians make informed decisions. Objective We evaluated the usability of our tool ‘Triptychon’ – a three-part visualisation dashboard of essential patients’ medical data provided by a direct overview of their hospitalisation information, laboratory, and vital parameters over time. Methods The study followed a cohort of 20 participants using the mixed-methods approach, including interviews and the usability questionnaires, Health Information Technology Usability Evaluation Scale (Health-ITUES), and User Experience Questionnaire (UEQ). The participant's interactions with the dashboard were also observed. A thematic analysis approach was applied to analyse qualitative data and the quantitative data's task completion time and success rates. Results The usability evaluation of the visualisation dashboard revealed issues relating to the terminology used in the user interface and colour coding in its left and middle panels. The Health-ITUES score was 3.72 (standard deviation (SD) = 1.0), and the UEQ score was 1.6 (SD = 0.74). The study demonstrated improvements in intuitive dashboard use and overall satisfaction with using the dashboard daily. Conclusion The Triptychon dashboard is a promising new tool for medical data presentation. We identified design and layout issues of the dashboard for improving its usability in routine clinical practice. According to users’ feedback, the three panels on the dashboard provided a holistic view of a patient's hospital stay.

show abstract

Section: Introductionmentioning

confidence: 99%