Exploring and Visualizing Plans, Events, and Effects Interactively

The effective visualization of the application of treatment plans and patient data is an interesting research topic. However, visualizing the effects of applying treatment plans as well as supporting the exploration of effects on a patient's condition are still largely unresolved tasks. To fill this gap, we have developed CareCruiser -- an interactive visualization of patient parameters in combination with applied treatments which provides means (1) to assess success or failure of previously applied treatment plans, (2) to explore the effects of each applied clinical action on the patient's condition, and (3) to identify sub-optimal treatment choices.

The logical view (in the upper left corner) communicates the logical structure of treatment plan execution by means of a flowchart-like representation. The lower left part displays a tree graph to visualize the hierarchical structure of treatment plans and sub-plans; the time-oriented view (on the right) focuses on the temporal-qualities of applied treatment plans, clinical actions, and patient parameters. This screenshot shows one treatment plan that has been applied on three different patients (aligned vertically for comparison). The charts and treatment plans are colored according to the color scheme of the parameter values' distance to the intended value. Selecting ranges with big distance to the intended value with the range slider draws attention to critical cases and brings out the differences between the conditions of the three patients.

Highlighting the progress of parameter values from the initial value toward the intended value, results in getting an immediate idea of success or failure of the applied treatments. The overall success of executing the selected treatment plan at a given point in time is determined by the minimum of the success value for stabilizing the patient's tcSO2 and the success value for stabilizing the patient's PCO2. The low success values for stabilizing the patient's tcSO2 lead to a low overall success for the selected treatment plan.

Revealing the delayed drop of the patient's tcSO2 when applying the clinical action 'reduce the FiO2 when tcSO2 rises above 92%'. All applications of this action were aligned vertically along the black line; the negative slopes of tcSO2 were highlighted. Dragging the focus window over the time span after applying the action reveals a vertical turquoise pattern (drops of the tcSO2 curve) with some delay to the application of the action.