MedProcNER Subtasks

The MedProcNER Shared Task is made up of three different subtasks, each with its own aim:

Subtask 1: Clinical Procedure Recognition

In this subtask, participants are challenged to automatically detect mentions of clinical procedures in published clinical reports in Spanish. Using the MedProcNER corpus as training data, they must create systems that are able to read the text and retrieve the start and end position of clinical procedures mentioned in the text.

Subtask 2: Clinical Procedure Normalization

In this subtask, participants are challenged to automatically normalize mentions of clinical procedures in published clinical reports in Spanish. Using the MedProcNER corpus as training data, they must create systems that are able to assign SNOMED CT codes to the mentions retrieved in Subtask 1.

Subtask 3: Clinical Procedure-based Document Indexing

In this subtask, participants are challenged to automatically assign clinical procedure codes to the full clinical case report texts. Using the MedProcNER corpus as training data, they must create systems that are able to assign SNOMED CT codes to the full case report so that they can be indexed.