In exploration,you are driving Quantum Leap Analyst’s analytical engine to obtain the specific information that may help shed light over the problem at hand. Some of Quantum Leap Analyst’s Exploration features are highlighted below:

Pattern List

Pattern List is a data grouping facility that enables you to select one or more attributes, slice the data into subsets defined by these attributes in their different states, and display how these data subsets align to a selected Target Attribute. In this example, you are examining how patients, grouped by Age Group, Ethnicity and Gender will align to Total Cost.

Group Data

Group Data is frequently used to get an “eagle’s eye” view of the data and to compare averages and totals, etc. for data subsets that have been defined and structured in a hierarchical order by the analyst. Group Data will enable you to easily compose reports that show e.g. key performance indicators such as Length of Stay, Total Cost, Number of procedures by patients segments, by primary diagnosis, or principal procedure etc.

Heat Map

Heat Maps reflect a dissection and grouping of the data along user defined dimensions or Patterns. Heat Maps may be characterized as cross-tabs or "pivot tables on steroids" in that they not only will present the assemblage of the data by user defined dimensions, but also the context and relevance of the details of the dissection method.


Correlation measures the degree to which two attributes vary in relation to each other. Correlations may substantiate something you already know, a theory or hypothesis. The fact that Length of Stay, Total Cost, Number of Diagnoses and Number of Procedures are correlated should not come as a big surprise. These four attributes specifically may also constitute key performance indicators that individually or in some derivative, combined format are monitored over time.

Data Comparison

Data Comparison will rank all the attributes in a dataset in terms of their ability to differentiate between two subsets of data. Data Comparison is especially useful when differentiating factors can be influenced or controlled by a decision maker.

Data Distribution

Data distribution for a continuous attribute illustrates the distribution, identifies outliers and shows the key statistics. You have a number of options to select outliers or non-outliers for the ensuing analysis. Statistics will be shown for the selection you made enabling you to compare statistics between All Data and the selection. At the same time, a filter (a simple pattern) was created based on the selection, enabling you to further explore the associated data subset.