Let the Chart Spark: Embedding Semantic Context into Chart with Text-to-Image Generative Model.

Pictorial visualization seamlessly integrates data and semantic context into visual representation, conveying complex information in an engaging and informative manner. Extensive studies have been devoted to developing authoring tools to simplify the creation of pictorial visualizations. However, mainstream works follow a retrieving-and-editing pipeline that heavily relies on retrieved visual elements from a dedicated corpus, which often compromise data integrity. Text-guided generation methods are emerging, but may have limited applicability due to their predefined entities. In this work, we propose ChartSpark, a novel system that embeds semantic context into chart based on text-to-image generative models. ChartSpark generates pictorial visualizations conditioned on both semantic context conveyed in textual inputs and data information embedded in plain charts. The method is generic for both foreground and background pictorial generation, satisfying the design practices identified from empirical research into existing pictorial visualizations. We further develop an interactive visual interface that integrates a text analyzer, editing module, and evaluation module to enable users to generate, modify, and assess pictorial visualizations. We experimentally demonstrate the usability of our tool, and conclude with a discussion of the potential of using text-to-image generative models combined with an interactive interface for visualization design.

Validation of the PROMIS sleep disturbance item bank computer adaptive test (CAT) in patients on renal replacement therapy.

OBJECTIVE: To examine the validity and reliability of the PROMIS Sleep Disturbance Item Bank Computer Adaptive Test (PROMIS-SD CAT) in patients on renal replacement therapy, using the Insomnia Severity Index as the primary legacy instrument. METHODS: Cross-sectional sample of adults on renal replacement therapy completed PROMIS-SD CAT, Insomnia Severity Index, General Anxiety Disorder-7, Edmonton Symptom Assessment System-revised Renal, SF-12 questionnaires. Construct validity was confirmed by associations with legacy instrument scores and measures of emotional wellbeing. Test-retest and scale reliability were assessed using intraclass correlation coefficient and standard errors of measurement, respectively. Discrimination was assessed using receiver-operating characteristic curve analysis. RESULTS: Among 217 participants (133 kidney transplant recipients, 84 on dialysis), 15% had moderate/severe sleep disturbance (Insomnia Severity Index ≥15). PROMIS-SD CAT exhibited good test-retest (intraclass correlation coefficient = 0.89, 95% confidence interval (0.83-0.93)) and scale (>0.9 for T-scores 34-73) reliability. PROMIS-SD CAT T-scores were strongly correlated with Insomnia Severity Index (rho = 0.85, 95% confidence interval (0.81-0.88)), Edmonton Symptom Assessment System-revised Renal Sleep Item (rho = 0.75, 95% confidence interval (0.69-0.81)) and moderately with General Anxiety Disorder-7 scores and SF-12 Mental Component Summary scores (p < 0.001 for all). PROMIS-SD CAT demonstrated outstanding discrimination for moderate/severe insomnia (defined as Insomnia Severity Index ≥15) (AUROC 0.93, 95% confidence interval (0.88, 0.98)). PROMIS-SD CAT and Insomnia Severity Index measurement characteristics were qualitatively similar between patients on dialysis and kidney transplant recipients. CONCLUSIONS: These results support PROMIS-SD CAT's validity and reliability for research and as potential screening tool among patients on renal replacement therapy.