Standard Data Mining Runs

To assemble data mining counts and statistics that can be compared over time, Argus Signal Management includes 23 data mining runs. All runs are refreshed as part of preparing a monthly signal management update.

The following types of runs are included:

• Data mining runs to produce disproportionality scores and report counts for the Argus data set. These runs are incorporated into the drug-event combinations table.
• Data mining runs to determine new or follow-up cases relative to prior time periods.
• Data mining runs to produce disproportionality scores for the HLT and SOC levels of the MedDRA hierarchy.
• A 3D data mining run that is used to identify Drug-Drug-Event interactions that may merit further investigation.

All of the standard data mining runs for Signal Management are MGPS runs that are limited to the set of monitored drugs. These runs are assigned to the project referenced in the Signal Management Configuration. This project is named Argus Signal Mgmt by default.

If your user role includes access to the Data Mining Results tab in Oracle Empirica Signal, you can view complete run details for any run. Click the Data Mining Results tab, select the data mining run from the drop-down list, then click View Run Details.

If custom terms are identified for Signal Management, the run details provide information on the custom terms.

In the descriptions that follow, values in angle brackets come from your organization’s Argus Signal Configuration.

• Data Mining Runs Producing Disproportionality Scores
  Data mining runs are performed to produce the disproportionality scores for drug-event terms. This process includes one run computed using all reports in Argus, another for spontaneous reports, and another for study reports.
• Data Mining Runs to Determine “New” Cases
  The cumulative subset runs are performed to determine "new" cases relative to prior time periods.
• Data Mining Runs Producing SOC, HLT Disproportionality Scores
  A pair of data mining runs is performed to compute disproportionality scores at the SOC and HLT levels of the MedDRA hierarchy using spontaneous reports in Oracle Argus Mart.
• Data Mining Runs for Viewing Interactions
  A 3D data mining run is used to investigate Drug-Drug-Event interactions.