March 26, 2021
Order processing and fulfillment workflows are everywhere; however, many industries are struggling with rapid digital transformation and still process orders by paper or fax. Now is the time to transform your order form intake process using Optical Character Recognition (OCR) and Automated Machine Learning (AutoML) from Impira.
Despite an increasing consumer demand to provide more convenient experiences, healthcare and insurance are two example industries that remain heavily reliant on paper workflows. According to a recent survey a whopping 90% of healthcare providers still use paper. Eliminating that much paper is quite the undertaking, let alone the hundreds of thousands of hours of manual data entry that is highly error prone and slow to process.
Paper is everywhere. From insurance claims to pharmacy prescriptions and medical equipment order forms, there is no shortage of paper-based workflows that can benefit from automation. The burden of manual data entry is real.
Better than OCR technology, Impira AutoML reduces the amount of time and effort required to process order forms for any order processing or fulfillment teams. Impira gives you instant access to high quality data, allowing your teams to more efficiently process an increased volume of complex, high priority orders, with much greater accuracy. The result? Order forms can be addressed with greater care, driving higher customer satisfaction, greater retention, and increased revenue.
Impira AutoML can be applied to a wide variety of use cases across the enterprise.
Many companies have turned to traditional OCR solutions in an effort to diminish the time consuming workloads involved in manually entering in details from paper forms. When legacy OCR technology is not supercharged by artificial intelligence (AI), it doesn’t learn from mistakes, is extremely limited when deployed in an enterprise, and doesn’t provide the structured output that businesses require to successfully convert a piece of paper into meaningful and useful information.
Impira AutoML technology combines OCR with artificial intelligence and machine learning to fully automate this effort, enabling smarter access to information in your documents. Impira continuously learns from your interactions to improve results, provide instant access to better quality data, and ultimately get your workflows moving at lightning speed. Whether it be a document, a scan, or a photograph, Impira supports them all, affording you complete flexibility in how you receive your order forms. And our simple APIs can be used to integrate with your order and fulfillment processes, allowing you to support a drastically higher volume of orders and increase your customer satisfaction.
Want to see it in action? Follow along with your own custom order forms, or you can download some sample Durable Medical Equipment Order Forms from the link on the left.
If you haven’t already done so, head on over to impira.com/signup to create your free account. There’s no credit card or personal information needed to get started beyond an email address. Our free plan includes OCR processing on up to 200 file units (pages), so there’s no cost to follow along with this tutorial.
Once you’ve created your account, start by creating a new “collection”. A collection is the main feature within Impira for organizing and grouping files together. Collections are a lot like folders on your computer. Click on the ‘plus’ symbol next to the word “collections” in the left-hand sidebar.
In the dialogue box that appears, give your collection a meaningful name of your choice, such as “Order Forms”.
Click on the name of your newly created collection.
Next, select your sample order forms and drag them into the browser area where it says “Upload 5+ files”. Alternatively you can click on the “Upload files” button and choose “From computer”, selecting from the location you saved the sample files. Set aside one sample file to be used at the end of this tutorial.
Once your file(s) are uploaded they are immediately processed and made available in a spreadsheet style table as seen below.
You’re now ready to extract the requisite information from your order forms. To begin, double-click on the first file to open the Impira mark-up interface. From here you can click or highlight the data you need from the forms and give the value a name.
Let’s start by extracting the Member’s name. You can do this by clicking on the member’s first name and dragging your mouse to highlight their full name. On the right-hand side bar, label this field as “Member’s name”. If you close the mark-up interface by clicking the “X” in the top-right corner, you’ll see that we’ve added a new column to our table for this field.
Impira AutoML now analyzes all the files in your “Order forms” collection and updates a model based on your selection. In just a few seconds you have created and trained an ML model, and run it across all of your forms to automatically fill-in your table - a process that, when done manually, takes hours!
Now that you have your results, you can also review or confirm their predictions. Within each cell you will see a quick visual indication of the underlying numerical confidence score for the prediction. Different colors represent confidence levels: Green indicates a highly confident result, red suggests that a review is recommended, and black denotes a field you have confirmed or added manually. At a glance you can easily ascertain areas that need a review, or others that have higher quality results.
By double-clicking on any cell, Impira will take you to the exact location of the ML prediction. Go ahead and double-click on one of the red cells, indicating that a review is recommended for this record. Impira has drawn a box around the predicted text on the page and, if the value is correct, you can simply click the “Confirm value” button on the right-hand sidebar. This simple interaction also provides training input to your model.
If you find that adjustments are necessary, you can easily remove the predicted value by clicking the “X” on the field name in the right-hand sidebar and redraw a box around the correct value. If the prediction only needs some minor adjustments, you can also move and resize the box that is overlaid on top of the field.
Each time you make a validation or correction, that information is fed back into the AutoML model for immediate re-training. Validate a few more predictions, and you will start to see the confidence flags change from red to green, indicating high-confidence.
Now that you’re familiar with the simple process to add new fields and confirm their results, you can go ahead and add a few more. Try it yourself with fields such as Effective Date of Prescription, the Member’s ID number, or even the Member’s Address fields.
Here’s a few additional tips to help you:
As you add these additional fields, the number of columns in your table will grow and, in a matter of a few minutes you have created a complete set of records without typing in any of the information yourself.
Once you are satisfied with your quality of the results you might choose to download your data as a CSV file. To do that, click the Download button in the top right corner.
Alternatively, you may want to programmatically access your extracted data. Impira provides a robust set of RESTful APIs for both reading and writing data. Now that your AutoML model has been trained, any new order forms that are sent to the Impira platform will be automatically categorized and extracted.
Remember the one sample file we set aside in Step 2? Let’s imagine that you receive this file for intake at a future point in time. As part of your workflow, this file can be ingested into Impira through various means (e.g. Dropbox sync, S3 sync, etc.). To simulate this, drag and drop this remaining file onto the collection. Going forward, new order forms sent to Impira will be appended to this collection as a new row. Impira AutoML will then automatically be applied to this new document, and the information made available to download or access via APIs.