Optimizing Health Insurance: The AI Effect
- By Claudio Caula, AIA
- May 15, 2023
The efficiency of health insurance claim approvals is important to insurers. When customers are financially and physically vulnerable, medical cost claim approvals need to be fast to reduce their anxieties. Driven by such needs, insurers have actively explored ways to accelerate the claim approval process.
Implementing AI into the claim approval process can be a challenging task. Claim approvals have been difficult to automate as it involves complex information - such as medical invoices and lab reports - to undergo a thorough assessment process which requires medical expertise. Employees involved in the claim approval process, such as assessors, have also expressed concerns over AI’s potential to redefine their job scopes.
There has been renewed interest in using AI to accelerate the claim approval process. With the suitable suite of AI and machine learning solutions supported by the right people, insurers can now automate the end-to-end claims process electronically without any manual intervention and still achieve high levels of accuracy.
What has changed to make this breakthrough?
- Improvement of the technical infrastructure
More insurers are adopting cloud applications, which has made AI solutions faster and more cost-effective to execute.
With cloud-hosted applications, Application Programming Interfaces (API) can be quickly integrated into current enterprise systems to automate processes. The cloud also allows the implementation of data analytics platforms and Machine Learning Operations (MLOps) to facilitate the smooth creation, maintenance and tracking of AI applications.
If done right, a cloud-based AI solution can seamlessly execute APIs and provide accurate results in seconds.
- Better image recognition solutions through AI
AI-enabled image recognition technology has also advanced to a point where accurate and usable text data can be processed from most images.
The first step in the claim approval process is to capture information, which is submitted as forms, medical reports, and receipts in image formats. This information is then input into digital systems for further assessment.
There have been attempts to automate the data-capturing step using image recognition solutions. However, inconsistent document layouts and tabular financial data formats have resulted in image recognition technologies producing dismal output results.
Thanks to advancements in AI and machine learning, image recognition technologies can now achieve impressively accurate results. For example, image recognition technologies used by major insurance players, such as AIA, have managed to achieve an output accuracy of above 90% for claim approvals.
- Digitizing Customer Interactions
The ability to digitally submit claims has also breathed new life into AI applications.
Not long ago, all forms and documents were submitted as physical documents that would be manually input into digital systems.
Today, customers can type in their information and upload photos of the required documents. With crucial information available digitally, AI solutions can capture this information and use it easily in an automated workflow.
- Leading change with organizational culture
Organizational cultural changes have led to more successful AI solution implementations.
Changing workflows can be a challenge, especially for processes like claim approvals which have been practiced a certain way for decades. Many organizations often fail in attempts to use AI for claim approvals due to human resistance towards new workflows and concerns over the accuracy of important decisions.
More insurers are educating employees on the reliability of data analytics, which has contributed to the broader acceptance of AI solutions. Such programs help employees to understand how AI solutions work and how to manage AI’s related risks. These programs also assure employees that AI is here to improve their work performance and not replace them.
Conclusion
AI is ready to make its mark on the insurance industry, with advancements in the people and technologies powering the technology.
For example, major insurance players like AIA have used AI to produce impressive time savings and customer experience improvements. AIA has managed to automate 90% of its claim approval processes while achieving an output accuracy of 99.7%. This has reduced the claims processing time from two days to two minutes, meaning that customers can submit a digital claim and expect a refund in their bank account in less than 20 minutes. New AI models (i.e., Transformers) and improvements in computer vision and natural language process (NLP) technologies have also spurred AIA to build more accurate AI solutions, which will further accelerate their claim approval processes.
AI’s potential to optimize the health insurance process is being realized, and this presents the industry with a good opportunity to drive AI adoption. By delivering accurate claim approval results at a fraction of the time and effort, AI is here to move the industry forward.
Claudio Caula, AIA’s director for group data analytics, wrote this article.
The views and opinions expressed in this article are those of the author and do not necessarily reflect those of CDOTrends. Image credit: iStockphoto/Epstudio20