Skip to Content

AI-102: How to Automate Patient Data Entry with Azure Document Intelligence?

By: Author Alex Lim

Posted on

Categories Exam

Struggling with the AI-102 exam and custom document intelligence? Learn how to automate patient registration data entry for merged medical centers using Azure AI Document Intelligence Studio. Step-by-step guide for creating custom extraction models, uploading documents, creating fields, assigning values, and training with Neural mode. Ace the AI-102 certification!

Table of Contents

Question

You work for NutexCare, a chain of medical care centers in the southeastern United States. Your company has recently purchased a competitor, Xerigon. You need to implement a custom document intelligent model to automate the data entry of the patient registration form used by both medical centers. Since NutexCare and Xerigon medical centers are in different states, the patient registration forms require different information in some sections and have different formats. You want to pull the required information from each state to be included in a Power App flow.

Which steps should you choose in Azure AI Document Intelligence Studio?

Choose the appropriate steps and place them in the correct order.

Unordered Choices:

  • Upload documents.
  • Select Custom classification model under the Custom models file.
  • Assign values.
  • Create the fields.
  • Train the model by choosing Template as the build mode.
  • Enter project details, configure the service resource, and connect to the training data source.
  • Select Custom extraction model under the Custom models tile.
  • Train the model by choosing Neural as the build mode.

Answer

Correct Order:

  1. Select Custom extraction model under the Custom models tile.
  2. Enter project details, configure the service resource, and connect to the training data source.
  3. Upload documents.
  4. Create the fields.
  5. Assign values.
  6. Train the model by choosing Neural as the build mode.

Explanation

  1. You would first select Custom extraction model under the Custom models tile.
  2. You would then enter the project details.
  3. You would configure the service resource, specifying the subscription, resource group, and form recognizer resource.
  4. You would then connect to the training data source, the path of the folder of Azure Blob storage to store the project.
  5. You would then upload at least five documents for labeling and training your custom extraction model.
  6. Click the plus (+) button in the top right of the screen to add fields from the dataset.
  7. You would then label the fields by assigning a value to them by choosing a word or words in the document. Continue this process until all the fields have been labeled.
  8. Once all the documents have had their fields added and labeled, you would start training the model. In this scenario, you would set the build mode to Neural instead of Template, since there are documents from two different medical centers that use different formats. If the documents were of the same format, then you would choose Template.
  9. You would not select Custom classification model under the Custom models tile. In this scenario, you are extracting data from forms, not classifying the data.

Microsoft Azure AI Engineer Associate AI-102 certification exam practice question and answer (Q&A) dump with detail explanation and reference available free, helpful to pass the Microsoft Azure AI Engineer Associate AI-102 exam and earn Microsoft Azure AI Engineer Associate AI-102 certification.