Fig 1.
Graphical user interface in the web browser.
The screen is divided in two parts: the sidebar (left part, used to for inputs) and the main panel (right part, used for outputs). The outputs are accessible through various tabs on top of the main panel part of the screen.
Fig 2.
Data for first two patients of the demo data set.
Data for two Erythema migrans patients are displayed. It spans eight rows, as each of them was evaluated on four occasions. Not all recorded variables are displayed.
Table 1.
Main panel: tabs with statistical output.
Fig 3.
Summary tab output for binary variables.
The table displays the descriptive statistics for the presence of each symptom; the plot shows the observed proportions of patients that report the presence of the symptom, along with their 95% confidence intervals.
Fig 4.
Summary: grouping variable tab output for binary variables.
The table displays the summary statistics for the presence of symptoms at baseline for groups defined by the response to treatment at last evaluation. The proportions are compared, unadjusted and adjusted P values and Q values are provided (see text for details).
Fig 5.
Graphical exploration tab output for numerical variables—lasagna plot.
The heat map displays graphically the intensity of arthralgia for each patient (horizontal axis) and evaluation occasion (vertical axis). A dendrogram showing patient similarity is plotted on the vertical axis.
Fig 6.
Clustering tab output—heat map displaying the similarities of reported symptoms and of patients.
The colors represent the intensity of the symptoms at baseline (rows) for each patient (columns). Hierarchical clustering is used to group symptoms and patients.
Fig 7.
Regression model: one evaluation time tab output—estimation of non-linear associations.
The graphs display the estimated associations between the age of the patients and selected symptom intensities at baseline evaluation. Restricted cubic splines are used for modeling. See text for details.