Notice
We and selected third parties use cookies or similar technologies for technical purposes and, with your consent, for other purposes as specified in the cookie policy. Denying consent may make related features unavailable.
You can consent to the use of such technologies by using the “Accept” button, by closing this notice, by scrolling this page, by interacting with any link or button outside of this notice or by continuing to browse otherwise.
No items found.

AI Use Case: Claims Document Intake and Data Extraction

October 8, 2024

Claims, IT and underwriting leaders are constantly pressured to improve efficiency, increase productivity and reduce costs. The ability to extract the greatest quantity of actionable decision data from the massive volume of documents pouring into underwriting and claims management systems is essential to meeting these demands.

This is the first in a series that frames data management within specific process challenges to illuminate key differences among the most prevalent document processing options:  

  • Traditional tech RPA (Robotic Processing Automation)/IDP (Intelligent Document Processing)
  • Human power, including in-house SME (Subject Matter Experts), claims assistants and BPO (Business Process Outsourcing)
  • Insurance-specific Generative AI document processing systems.

To introduce the topic, we’ll focus on critical initial steps of the insurance claims process that yield valuable decision data – claims document intake, data entry and setup.

People Power for a People Business

Human power has been the go-to solution for insurance, even since the first alternatives entered the picture nearly 75 years ago. Inarguably, nothing beats human ingenuity—and, after all, insurance is a people business.  

The most common steps taken by claims managers, claims assistants and BPO staff generally follow a common pattern:

  1. Receive claims via multiple channels (email, mail and fax)
  2. Sort and categorize documents by claim type  
  3. Scan physical documents into digital format  
  4. Perform data entry, inputting relevant information into the insurer's system  
  5. Verify data accuracy against existing records  
  6. Set up new claim files in the system.  

This process relies heavily on judgment and attention to detail—all areas in which human ingenuity excels. However, it’s time-intensive and error-prone, and can consume up to 40% of insurance professionals’ work time, which could be directed toward higher-value core tasks.  

The only way to scale up human capacity in underwriting to accommodate spikes in demand is to add more people, whether by expanding staff or increasing dependence on outside BPO.

People alone cannot keep up with the explosion of data pouring into underwriting and claims departments, which has driven function leaders to find faster alternatives.

Robotic Process Automation (RPA) – Not Quite The Silver Bullet You Hoped For

By 2025, experts predict global businesses will generate more than 181 Zettabytes (one ZB = 1021 bytes) of data annually, a figure that is expected to grow 7% annually.  

One approach insurance businesses are taking to speed up document intake and processing through setup is simple automation, either RPA (Robotic Process Automation) or IDP (Intelligent Document Processing).  

These tools have become staples for their ability to automate repetitive, manual tasks using software (“bots”) to replicate human actions across claim document processing:  

Intake => Classification => Extraction => Validation => Data entry => Exception handling => Setup

Sometimes referred to as “hyper-automation, RPA has been around since the turn of the 21st century. It offers solutions that effectively address a select group of claims document processing challenges. As this technology is rule-based, it requires human instruction for every action. For example, it cannot pre-process and classify documents without training or configuration. Also, most notably, RPA struggles with complex documents, significant variations in document formats and unstructured data, often requiring additional tools or human intervention.  

Beyond incomplete capabilities vis-à-vis those necessary for complex document processing solutions, RPA and similar techniques have had high TCO (Total Cost of Ownership). Respondents to a 2022 study reported broken bots at least once weekly, causing significant downtime – between five and 24 hours per incident. As a result (per Deloitte), 96 percent of RPA customers never get to value.  

New Kid on the Block: Generative AI

A relatively new technology, generative AI's suitability for insurance document processing stems from its adaptive learning capabilities and contextual understanding. Gen AI-powered solutions surpass simple automation while working autonomously and far faster and more accurately than human power.  

Managing the process functions listed above, AI-powered solutions ingest documents in various formats (printed forms, digital, structured and unstructured).

In classification, AI automatically categorizes claims forms, medical reports, invoices and other document types.

AI-powered systems then extract relevant data points using natural language processing and validates them by cross-referencing the extracted data against policy details and claim history for accuracy.

Data entry flows directly into claims management systems with extracted and validated information.

Exception handling flags anomalies or incomplete data for human review, learning from the resolutions to these problems.

Setup configures claim file based on extracted data to initiate appropriate claims management workflow.

Unlike people-power, GenAI is highly scalable and ready to accommodate spikes in demand to increase capacity at critical times. Compared to rules-based RPA-based systems, Generative AI functions as a cognitive system to interpret complex, unstructured documents, adapting to variations in format and language.

But not all GenAI is insurance GenAI.  

Public AI solutions have tremendous cognitive capabilities, but general Large Language Models (LLMs) are not trained on insurance data, nor do they consider the security, data privacy or heavily regulated nature of the insurance space. Document processing in underwriting or claims demands systems trained on insurance data.  

Selecting the best document processing solution for your business’s needs is a complex decision, but it doesn’t need to be complicated.

Roots Automation has created The Buyer’s Guide to AI-Powered Document Processing in Underwriting and Claims to help you evaluate the options available for your business.  

We invite you to download this brief manual for quick access to essential facts and figures about the insurance document processing lifecycle. It also includes a comprehensive chart of available options and other resources to aid your research into insurance document processing solutions.  

What’s a Rich Text element?

The rich text element allows you to create and format headings, paragraphs, blockquotes, images, and video all in one place instead of having to add and format them individually. Just double-click and easily create content.

Static and dynamic content editing

A rich text element can be used with static or dynamic content. For static content, just drop it into any page and begin editing. For dynamic content, add a rich text field to any collection and then connect a rich text element to that field in the settings panel. Voila!

How to customize formatting for each rich text

Headings, paragraphs, blockquotes, figures, images, and figure captions can all be styled after a class is added to the rich text element using the "When inside of" nested selector system.

Fusce non convallis mi. Curabitur nec rutrum orci. Etiam vitae diam ut tellus venenatis ultricies. Fusce vitae ipsum sed urna tempor tempor et vitae dui.
Fusce vulputate molestie est

Fusce non convallis mi. Curabitur nec rutrum orci. Etiam vitae diam ut tellus venenatis ultricies. Fusce vitae ipsum sed urna tempor tempor et vitae dui. Aliquam nibh ante, tempus vel ultricies nec, tempus sed felis. Nullam et efficitur velit. Aenean odio nulla, facilisis a commodo eu, suscipit at augue.

Aliquam rutrum dui sapien. Aliquam pulvinar lectus accumsan est dictum, et faucibus justo ornare. Mauris placerat placerat consequat. Donec commodo consectetur nunc, et posuere orci lacinia sed. Duis mollis, eros quis porta laoreet, mi est euismod lectus, vitae volutpat quam enim congue tellus. Lorem ipsum dolor sit amet, consectetur adipiscing elit. Proin ornare laoreet consequat. Integer at accumsan lacus, eget ultricies augue. Vestibulum semper sapien at venenatis pretium. Integer nec iaculis lacus. Sed elit nisi, luctus sit amet vehicula nec, mattis nec purus. Nulla facilisi. Nam ornare in justo eget facilisis.

  • Praesent sit amet lectus quis metus sagittis tempor.
  • Sed mattis ipsum vitae turpis laoreet condimentum
  • Sed orci erat, rhoncus efficitur eros a, sollicitudin commodo tortor
  • Sed accumsan ex viverra est tincidunt bibendum a non nulla curabitur eget ligula mauris
  • Nam ut sagittis velit suspendisse ullamcorper quis lorem vitae hendrerit
  • Vivamus diam orci, dignissim ac nulla hendrerit, porttitor posuere risus

Cras vel leo mattis viverra tellus eget vestibulum est

  1. Praesent sit amet lectus quis metus sagittis tempor.
  2. Sed mattis ipsum vitae turpis laoreet condimentum.
  3. Sed orci erat, rhoncus efficitur eros a, sollicitudin commodo tortor.
  4. Sed accumsan ex viverra est tincidunt bibendum a non nulla curabitur eget ligula mauris.
  5. Curabitur sit amet auctor tellus, at scelerisque sem. In sit amet convallis arcu, id vulputate velit. Proin feugiat interdum nulla, eu malesuada massa commodo quis.
  6. Vivamus diam orci, dignissim ac nulla hendrerit, porttitor posuere risus.

Cras vel leo mattis viverra tellus eget vestibulum est

  • Etiam arcu metus, vestibulum et consequat sit amet, imperdiet at augue donec condimentum risus at consequat sollicitudin.
  • In sit amet nisi vitae odio tristique posuere integer vel magna dignissim, sodales mauris a, tempus odio nullam orci sapien, posuere non posuere et, laoreet vel velit.
  • Quisque eleifend tempor eros aenean et tempus neque nam ut porttitor velit maecenas consectetur, lacus at commodo efficitur, est neque tincidunt leo, et dictum nunc lorem a est.
  • Maecenas viverra turpis vitae eros tempus porttitor nulla tempor nunc eros, eu elementum arcu dapibus a etiam a tristique metus.

Share this post

GET IN TOUCH

Let's make work more human, together.
Contact Us