Health timeline: An insight-based study of a timeline visualization of clinical data

Andres Ledesma (Corresponding Author), Niranjan Bidargaddi, Jörg Strobel, Geoffrey Schrader, Hannu Nieminen, Ilkka Korhonen, Miikka Ermes

    Research output: Contribution to journalArticleScientificpeer-review

    1 Citation (Scopus)

    Abstract

    BACKGROUND: The increasing complexity and volume of clinical data poses a challenge in the decision-making process. Data visualizations can assist in this process by speeding up the time required to analyze and understand clinical data. Even though empirical experiments show that visualizations facilitate clinical data understanding, a consistent method to assess their effectiveness is still missing.

    METHODS: The insight-based methodology determines the quality of insights a user acquires from the visualization. Insights receive a value from one to five points based on a domain-specific criteria. Five professional psychiatrists took part in the study using real de-identified clinical data spanning 4 years of medical history.

    RESULTS: A total of 50 assessments were transcribed and analyzed. Comparing a total of 558 insights using Health Timeline and 576 without, the mean value using the Timeline (1.7) was higher than without (1.26; p<0.01), similarly the cumulative value with the Timeline (11.87) was higher than without (10.96: p<0.01). The average time required to formulate the first insight with the Timeline was higher (13.16 s) than without (7 s; p<0.01). Seven insights achieved the highest possible value using Health Timeline while none were obtained without it.

    CONCLUSIONS: The Health Timeline effectively improved understanding of clinical data and helped participants recognize complex patterns from the data. By applying the insight-based methodology, the effectiveness of the Health Timeline was quantified, documented and demonstrated. As an outcome of this exercise, we propose the use of such methodologies to measure the effectiveness of visualizations that assist the clinical decision-making process.

    Original languageEnglish
    Article number170
    Pages (from-to)170
    Number of pages14
    JournalBMC Medical Informatics and Decision Making
    Volume19
    Issue number1
    DOIs
    Publication statusPublished - 22 Aug 2019
    MoE publication typeA1 Journal article-refereed

    Keywords

    • Clinical data
    • Data visualization
    • Electronic health record
    • Health informatics
    • Insight-based methodology

    Fingerprint Dive into the research topics of 'Health timeline: An insight-based study of a timeline visualization of clinical data'. Together they form a unique fingerprint.

    Cite this