My thinking about how artificial intelligence (AI) technologies will improve dentistry, if not fundamentally revolutionize it, has broadened considerably over the past few years.
As Lou Shuman, DMD, CAGS, explained in his February 2019 report Dental economy opinion piece, “How Artificial Intelligence Is Shaping Dentistry,” we’re a far cry from Hollywood’s vision of AI-powered humanoid robots.1 However, a range of AI technologies are already in use today in the form of computer software. AI-powered software automates routine tasks that are typically performed by humans. Sophisticated AI technology platforms can learn to learn insights and find patterns in complex systems and large amounts of data. Computer vision AI, in particular, holds promise for healthcare because it can analyze image content with superhuman speed and precision.
As a dentist looking for the potential of cutting-edge technology, my thoughts on AI initially tended to go through a narrow clinical lens: how will AI benefit me and dental clinicians like me? I would think about how AI could enable hyper-accurate, liability-free diagnoses and super-smart treatment plans. I would imagine perfectly fitting dentures and increased patient confidence, and I would see oral medicine finally integrated into systemic health care.
But it didn’t occur to me that AI could have a substantial impact on dental insurance beyond its obvious application to automating insurance claims submission.
Today, I would say that insurance is one area where AI will prove hugely beneficial to our industry, and sooner rather than later. From what I see, it’s clear that AI applications for dental insurance could have as big of an impact on the dental industry as a whole as it does on treatment delivery.
In fact, while AI applications for diagnosis and practice management are still under regulatory scrutiny, insurers in other industries are already benefiting from AI. According to the Center for Insurance Policy and Research, artificial intelligence “is currently used in claims processing, underwriting, fraud detection and customer service.”2 Auto insurers are using AI-powered virtual assistant chatbots to answer customer questions 24/7 with natural language, saving time and money. Machine learning and AI computer vision allow insurers to assess and predict costs faster and more accurately by analyzing data from historical information, sensors and loss images.
Why dental insurance needs AI
Dental insurance is the economic engine of our industry. Let’s face it, however loath to admit it, when dental insurance suffers, we all suffer.
First, dental insurance companies can take much of the credit for incorporating advances in science and technology into the practice of dentistry, thanks to the fact that they enable massive consumption of dental care. Certainly, every practicing dentist can attest to the fact that most patients will turn down advanced treatment options if their insurance doesn’t pay a significant portion of the bill.
Additionally, most practicing dentists can attest to the fact that as financial gatekeepers, insurance company claims-handling systems often mediate the quality and timeliness of patient care, since claims-handling determines patients’ willingness to accept treatment. In fact, it was this side of the insurance equation that I first considered when discussing the short-term benefits of AI for dentistry.
Previously, my considerations (and, yes, my frustrations) as a physician dealing with insurance companies overlooked the perspective of the insurer. As dentists, we look at claims handling and see a system that at best slows us down and at worst aims to trick us. If we step back and swap the optics, the bleak bureaucratic hassles we see in handling claims start to look like an unfortunate but essential industry save.
As things stand, fraud and overdiagnosis, along with waste and human error in the claims process, are creating a drag on insurers. Unfortunately, we know all too well that a few dishonest dentists can really skew the system for the worse. Atlantic The magazine recently covered a story of egregious dental insurance fraud and came to the conclusion that our profession is inherently susceptible to fraud.3 However, I know bad apples are the exception in our field, not the rule. It’s time to change history.
Consider that a large insurance company may receive around 40 million claims per year. No insurance company, no matter how large, has the manpower to review so many claims. In truth, only a fraction of claims are adjusted manually (I’ve heard estimates in the range of 3% to 5%), and the rest are decided by methods that seem downright arbitrary and random. In reality, most claims are not decided by a trained professional, but rather by informed mathematical models which, by their very nature, will statistically mark some good claims as groundless and some bad claims as valid.
It is on this last point that we – and our patients – are frustrated. But if insurance companies blindly accept every claim, then fraud, waste and abuse would bankrupt the financial backbone of our industry, and we would lose the only official doctor-patient intermediary that helps ensure proper alignment between diagnosis and treatment. Let’s not forget that fraud, waste and abuse do not only cost insured patients and dentists. This is costing taxpayers billions in Medicaid system costs. Everyone can agree that this is an issue worth addressing.
So how do you reconcile the problems doctors face when dealing with insurance companies and the problems insurance companies face when dealing with doctors?
The Truth: Oral Imaging, AI, and Precision in Dentistry
Oral imaging is both the primary diagnostic evidence on which we prescribe treatment and the primary evidence on which insurers assess claims. This is also the area of dentistry where AI can provide the most immediate results through computer vision. In fact, AI systems based on computer vision technology for oral imaging analysis are poised to surpass the diagnostic capabilities of humans.
Oral imaging diagnostic systems with AI computer vision will soon deliver super accurate results at superhuman speed and bring clarity of truth to dental insurance. They will ensure doctors are treated fairly by insurance companies, protect insurance companies from dishonest doctors, and give patients peace of mind when dealing with doctors and insurers.
What we can expect from AI for dental insurance
No claims left behind—Manpower will no longer limit the number of claims that are subject to a certain level of review, as the AI will assess everything oral imagery accompanying each claim. Assessment results can be used to assess the likelihood of a claim being approved, allowing insurance companies to quickly and intelligently determine which claims should be manually reviewed and which should be expedited for approval.
Prevent insurance fraud, waste, and abuse—When all images associated with claims are analyzed, fraud, waste and abuse in dental insurance claims will be largely eliminated. AI can detect cases of resubmission fraud in which dentists submit a single image depicting a particular pathology multiple times or submit the same image to multiple insurers.
AI can also flag potential instances of overdiagnosis and misdiagnosis. Diagnostic cleanup will reduce costs for everyone, reduce liability for insurers and physicians, and mitigate risk for patients. And, of course, the AI can instantly notify doctors when they submitted the wrong image by mistake.
Automatic pre-disaster assessment—AI will eventually enable full integration between dental practices and insurance imaging systems, providing real-time claims assessment and cost transparency before treatment.
The AI that assesses the images on the spot and communicates the results to the insurer will allow insurers to immediately inform doctors whether the insurance will cover the prescribed treatment and, if so, how much the insurance will pay.
Automatic pre-claim assessment is truly the holy grail of AI for dental insurance. It will bring initial financial clarity and diagnostic validation to a field of medicine that has often been criticized for its lack of both. Clarity of costs and validation of diagnoses will also provide an ancillary benefit to patients, as they are more likely to receive the appropriate treatment when diagnoses and treatment finances are discussed openly, in real time.
For fairly obvious (but not always correct) reasons, insurance companies tend to hold a place of dishonor in the hearts of dentists and patients alike. But like it or not, insurance is the financial engine of the dental industry. Anything that makes this engine more efficient will benefit dentistry as a whole. This is why insurance applications of AI will potentially revolutionize the dental industry as much as its therapeutic applications.
1. Shuman L. How artificial intelligence is shaping dentistry. Dental economy website. https://www.dentaleconomics.com/macro-op-ed/article/16386252/how-artificial-intelligence-is-shaping-dentistry. Published February 1, 2019.
2. Artificial Intelligence. National Association of Insurance Commissioners website. https://content.naic.org/cipr_topics/topic_artificial_intelligence.htm. Published September 13, 2019. Updated December 23, 2019.
3. Jabr F. The truth about dentistry: It’s a lot less scientific — and more prone to gratuitous procedures — than you might think. Atlantic magazine. https://www.theatlantic.com/magazine/archive/2019/05/the-trouble-with-dentistry/586039/. Published in May 2019.