Create and Run a Pipeline

Running a pipeline refers to the use of a set of NLP components to identify the specified information , including sentence segmentation, tokenization, part of speech tagging, abbreviations, etc. The NLP components are executed in a sequence based on the functional dependency amongst them.
In order to recognize clinical concepts within clinical text:

  1. You need to create a project
  2. You need to configure the pipeline
  3. You need to import the files that you want to be analyzed
  4. You need to process the imported files by running them through the pipeline.

Follow the steps below to build a pipeline:

  1. Create a new project:
    1. Click on the plus (+) sign at the top left corner of the screen as shown in the Figure below.
      Create a new project
      Create a new project
    2. On the pop-up window (Figure below), enter a name for your project, for example: "Clinical_concept_recognition".
      Creating a new NLP pipeline project
      Creating a new NLP pipeline project
    3. Select NLP Pipeline as the project type.
    4. Click the Finish button.
      A project with the specified name is created
      A project with the specified name is created and is placed under Mypipeline folder

Double click the pipeline name to view its content. As you can see, it contains two folders "Components", and "Data". The Components folder contains the pipeline configuration file. The Data folder includes two folders: Input, and Output. The Input folder holds the files that are processed by the pipeline. The results obtained by running the pipeline are saved in the output folder.