Medical Prescription

This section describes how to build your custom OCR API to extract data from Medical Prescription using the API Builder. A Medical Prescription is an order for medicine from your doctor.

Prerequisites

You’ll need at least 20 different medical prescription images or pdfs to train your OCR model

Define your medical prescription use case

First, we’re going to define what fields we want to extract from your medical prescription.

Here is the list of fields we are going to extract using our OCR API:

  • Date
  • Doctor's name
  • Patient's name
  • Address: Of the medical center
  • Phone number: Of the medical center

That’s it for our use case. Feel free to add any other relevant data to fit your requirements.

Deploy your API

Once you have defined the list of fields you want to extract from your Medical Prescription, head over to the platform and follow these steps:

  1. Click on the Create a new API button on the right.

  2. Next, fill in the basic information about the API you want to create as seen below.

Set up your API

  1. Click on the Next button. The following page allows you to define and add your data model.

Define Your Model

There are two ways to add fields to your data model.

  • Upload a JSON config file
  • Manually add data

Data Model

Upload a JSON Config

To add data fields using JSON config upload.

  1. Copy the following JSON into a file.
{
  "problem_type": {
    "classificator": { "features": [], "features_name": [] },
    "selector": {
      "features": [
        {
          "cfg": { "filter": { "convention": "FR" } },
          "handwritten": false,
          "name": "date",
          "public_name": "Date",
          "semantics": "date"
        },
        {
          "cfg": { "filter": { "alpha": -1, "numeric": 0 } },
          "handwritten": false,
          "name": "doctor_s_name",
          "public_name": "Doctor's name",
          "semantics": "word"
        },
        {
          "cfg": { "filter": { "alpha": -1, "numeric": 0 } },
          "handwritten": false,
          "name": "patient_s_name",
          "public_name": "Patient's name",
          "semantics": "word"
        },
        {
          "cfg": { "filter": { "alpha": -1, "numeric": -1 } },
          "handwritten": false,
          "name": "medical_center_s_address",
          "public_name": "Medical center's address",
          "semantics": "word"
        },
        {
          "handwritten": false,
          "name": "medical_center_s_phone_number",
          "public_name": "Medical center's phone number",
          "semantics": "phone"
        }
      ],
      "features_name": [
        "date",
        "doctor_s_name",
        "patient_s_name",
        "medical_center_s_address",
        "medical_center_s_phone_number"
      ]
    }
  }
}
  1. Click on Upload a JSON config.
  2. The data model will be automatically filled.
  3. Click on Create API at the bottom of the screen.

Document Data Model filled

Manually Add Data

Using the interface, you can manually add each field for the data you are extracting. For this example, here are the different field configurations used:

  • Date: type Date in European format
  • Doctor's name: type String that never contains numeric characters
  • Patient's name: type String that never contains numeric characters
  • Medical center's address: type String that may contain both numeric and alpha characters
  • Medical center's phone number: type Phone

Once you’re done setting up your data model, click the Create API button at the bottom of the screen.

Document Data Model filled

Train Your Medical Prescription OCR

You’re all set! Now it's time to train your Medical Prescription deep learning model in the Training section of our API.

Train your model

  1. Upload one file at a time or a zip bundle of many files.
  2. Click on the field input on the right, and the blue box on the left highlights all the corresponding field candidates in the document.
  3. Next, click on the validate arrow for all the field inputs.
  4. Once you have selected the proper box(es) for each of your fields as displayed on the right-hand side, click on the validate button located at the right-side bottom to send an annotation for the model you have created.
  5. Repeat this process until you have trained 20 documents to create a trained model.

To get more information about the training phase, please refer to the Getting Started tutorial.

 

Questions?
Slack Logo Icon  Join our Slack