One of the key areas on the administrative side of healthcare is prior authorization. This is when clinicians need to get an approval from the insurance company to perform a service like an MRI for the patient. Insurance companies use prior authorization to control costs by preventing unnecessary procedures. This is always a point of contention since doctors think they should be the ones to make decisions about what’s appropriate for their patients. However, insurance companies argue that testing and procedures are often ordered by doctors when medical guidelines don’t support them. Most recently, doctors have used ChatGPT to generate these letters to the insurance companies. Although a great time-saver, ChatGPT has shown an ability to provide false scientific references in these letters or fabricate patient data.
This underlines the fact that although we’re heading for exciting days, the road to get there is not fully paved yet. However, one of the early use cases for generative AI is that of generating prior authorization letters that summarize key information from the EHR and explain why procedures are necessary.
Let’s use the example of someone who’s presenting with back pain for the first time. The overwhelming majority of patients with back pain improve spontaneously without the use of expensive medical procedures like MRIs. However, some clinicians go straight to ordering an MRI as their preferred diagnostic tool. I can see both sides of the argument, but being a physician, I tend to agree that clinicians know best. There are often circumstances that mean the clinician will deviate from the guidelines for good reason. But they need to do a better job of documentation so that insurance companies agree to pay for it. AI can help with the documentation, ensuring that these extenuating circumstances are included on the forms that will be filed with the insurance company. It would also take care of a lot of annoying and time-consuming tasks for the medical staff.
AI can be used to harvest the appropriate information for prior authorizations and RPA can populate the insurance forms with that information to allow for automatic submission with a higher likelihood of approval. This is good news for providers and their employees because it means they don’t have to manually complete forms or set up rules for prior authorization. For example, companies like Epic, Olive and UIPATH use RPA and workflow software to automate important administrative processes such as eligibility checks, insurance claims, prior authorizations, appointment reminders, billing, data reporting and analytics.