- Overview
- Medical Record Summarization
Healthcare Solutions user guide
Medical Record Summarization (MRS) output data
After a summarization run completes and a reviewer approves or rejects a summary, Medical Record Summarization writes the results to a Data Fabric entity called MRS_Output. Each record in this entity corresponds to one processed medical record and contains the generated summary, reviewer decisions, citations, and supporting metadata.
Downstream automations read from this entity to route outputs to systems of record, trigger additional processing, or archive clinical summaries.
The MRS_Output entity
The MRS_Output entity is automatically provisioned in your Data Fabric tenant when Medical Record Summarization is deployed. Each record is created when a summarization run completes for a document, and updated as the record moves through the clinical review workflow.
Output files
The four fields most relevant to downstream integration contain the actual deliverables produced by the summarization process.
| Field | Type | Description |
|---|---|---|
MRSDeepRagSummary | File | The AI-generated clinical summary produced by DeepRAG. This is the primary output of the summarization process. |
packetFile | File | A bundled archive containing all output files for the summarization run. |
MRSOutputOverrideFile | File | The reviewer-edited version of the summary. Populated only when a reviewer used the Override action to modify AI-generated content before approving. If no override occurred, this field is empty. |
MRSCitationsFile | File | A file containing citation mappings that link each finding in the summary to its source page in the original medical record document. |
Status and workflow fields
These fields track where a record is in the review lifecycle.
| Field | Type | Description |
|---|---|---|
OutputStatus | Text | The current review status. Values: Ready, Review started, Approved, Rejected. |
CurrentAssigneeName | Text | Display name of the reviewer currently assigned to this record. |
CurrentAssigneeId | Text | User ID of the assigned reviewer. |
AssignedAt | Date-Time | When the record was assigned for review. |
StartedWorkingAt | Date-Time | When a reviewer opened the record, transitioning status to Review started. |
CompletedAt | Date-Time | When summarization processing completed. |
Identity and source fields
These fields identify the source document and the template used.
| Field | Type | Description |
|---|---|---|
MRS_PDF_GUID | Text | Unique identifier for the source PDF document. |
OutputTemplateId | Text | ID of the template version used to generate this summary. |
ManualBatchId | Text | Identifies the summarization batch that produced this record. |
OutputNumPages | Number | Page count of the source document. |
Downstream automation patterns
After a reviewer completes their review, downstream processes typically need to retrieve the approved summary and deliver it to a system of record, handle rejected records by routing them for reprocessing, or archive the citation file for audit purposes.
The recommended approach is to configure a Data Fabric trigger on the MRS_Output
entity that fires when OutputStatus is updated to Approved or Rejected.
For general guidance on Data Fabric triggers, refer to About triggers in the Data Fabric documentation.