Reports | Create Cross Domain Data

Create Cross Domain Data
This report adds data for various domains to the adsl.sas7bdat table corresponding to incidence of variables in the AE , CM , LB , and MH domains and a summary statistic for LB , EG , and VS domain values. The report converts all character variables with values N and Y to numeric variables with values 0 and 1 , respectively. The resulting output data set is suitable for pattern discovery and predictive modeling. A transposed version of the data set is also produced. Both versions are useful for clustering .
Report Results Description
Running this report with the Nicardipine sample setting generates the Results shown below. Output from the report is organized into sections. Each section contains one or more plots, data panels, data filters, or other elements that facilitate your analysis.
The Create Cross Domain Data report initially shows two sections Indicators and Statistics . Use the available options in each section to drill-down into the data.
Hierarchically clusters all binary indicator variables . A separate section is created for each domain ( ADSL ( AD ), Concomitant Medications ( CM ), Adverse Events ( AE ), Disposition ( DS ), Medical History ( MH ), and Laboratory Test Results ( LB )) that has binary variables , depending on the options selected. The binary variables are converted to 0s and 1s and clustered.
The AD Indicators section is shown below:
An Indicator section contains the following elements:
A two-way hierarchical clustering analysis of the 0-1 variables , with subjects as rows and indicator variables as columns.
You can study the Heat Map and Dendrogram to see both subjects that have similar values of the binary variables as well as binary variables that are similar across subjects.
See the JMP Hierarchical Clustering platform for more information.
Hierarchically clusters a statistic computed on continuous variables. A separate section is created for each domain (ECG Test Results ( EG ), Laboratory Test Results ( LB ), and Vital Signs ( VS )) that has continuous variables.
The EG Max section is shown below:
Statistics sections contains the following elements:
This shows a Parallel Plot of the computed statistic for each variable in the domain. Each line in the plot corresponds to a subject. In the example above, the max statistic is plotted for four variables. The coloring of the lines comes from the hierarchical clustering analysis of the first numeric domain.
You can study this plot to determine trends across variables as well as outlying subjects.
See the JMP Parallel Plot platform for more information.
This displays a two-way clustering analysis of the statistic across all variables and subjects.
You can study this plot to determine numeric measurements that are similar across subjects and/or subjects that are similar across numeric measurements.
See the JMP Hierarchical Clustering platform for more information.
Output Data
This pane provides links to the following output data sets:
Transposed Subject Data ( adsl_cddt.sas7bdat ): This data set is the transpose of the main output table. The transposed table has domain data identifiers as rows and subjects as columns.
Action Buttons
Action buttons, provide you with an easy way to drill down into your data. The following action buttons are generated by this report:
Profile Subjects : Select subjects and click to generate the patient profiles. See Profile Subjects for additional information.
Show Subjects : Select subjects and click to open the ADSL (or DM if ADSL is unavailable) of selected subjects.
Cluster Subjects : Select subjects and click to cluster them using data from available covariates . See Cluster Subjects for additional information.
Demographic Counts : Select subjects and click to create a data set of USUBJID s, which subsets all subsequently run reports to those selected subjects. The currently available filter data set can be applied by selecting Apply Subject Filter in any report dialog .
Click to generate a standardized pdf - or rtf -formatted report containing the plots and charts of selected sections.
Click the Options arrow to reopen the completed report dialog used to generate this output.
Click the gray border to the left of the Options tab to open a dynamic report navigator that lists all of the reports in the review. Refer to Report Navigator for more information.
Report Options
Report Option Descriptions
Specific documentation for each of the options can be viewed by clicking on the following links:
General Options
Interventions , Events , Binary Variables in ADSL , Character Findings , and High and Low Labs
Cluster subjects
Subject Filter 1
Additional Filters
Additional Filter to Include Subjects 2
Merge supplemental domain
Select the population to include in the analysis
Time Windows
Time Scale
Trial Time Windows
Term Level
Create summary statistic variables for numeric findings and Summary Statistic for Findings Data
Normalization of Lab Measurements and log Transformation of Lab Measurements
Multiplier for Upper Normal Limit and Divisor for Lower Normal Limit

Subject-specific filters must be created using the Create Subject Filter report prior to your analysis.

For more information about how to specify a filter using this option, see The SAS WHERE Expression .