AI in Dentistry: 7 Basics to Protect Your Practice

AI in Dentistry: 7 Basics to Protect Your Practice

Maxwell’s demon is a term coined by computer scientist James Clerk Maxwell in 1867. The term helped him illustrate a thermodynamic experiment in which a demon controls a small massless doorway between two gas chambers. Some molecules go through the gate and some don’t because the demon uses its tail to sort them. In this theory, after being sorted, similar gases are then sorted into respective chambers by the demon’s tail swipe.

Do we need a Maxwell’s demon to help us decide which artificial intelligence (AI) walks through the door of our practices and which doesn’t? Maybe there’s a rational decision-making process that doesn’t involve a demon.

The best use of humans in dentistry with AI

In 1951, Norbert Wiener paved the way for machine learning (ML) and AI.1 Postulating that ML and AI could free people from repetitive tasks, he recognized the inherent dangers of computers that outweigh the human experience. ML and AI in dentistry are becoming the norm; they intersect between IT and repetitive clinical and administrative tasks.

I have no fear of AI taking over our roles as dental professionals. In a 2018 paper, artificial intelligence experts predicted that “human-level artificial intelligence (HLMI) has a 50% chance of occurring within 45 years, and only a 10% chance by 2027” .2 Phew!

Maybe ML and AI are like the Chinese symbol of crisis, both a threat and an opportunity. Let’s define the components of Maxwell’s demon door to assess your opportunity with AI.

More by Dr. Margaret Scarlett

Your most strategic capital investment write-offs are in the cloud
Teledentistry: virtual visits save time and PPE

7 building blocks to protect your practice

1. Ethics, including transparency. For now, you’ll have to decide your own ethics for using AI. The World Health Organization (WHO) has defined ethical benchmarks on which to build your practice. They detail six principles: autonomy, security, transparency, responsibility, fairness and sustainability.

With transparency, you balance the commercial interests of AI to ensure that patient rights are not subordinated. You need to decide if the AI ​​is trained with images of the diversity of populations and settings where you provide care. Basically, you need to know what the AI ​​does and doesn’t do in an easily accessible way. This means proper labeling on how a product should be used. Be sure to read labels.

2. Regulatory Matters: The Food and Drug Administration (FDA) has the authority to regulate marketing claims for different AI products in the United States. The FDA classifies different classes of software for ML and AI by risk regarding what they call software as a medical device (SaMD). Class I SaMD is zero or very low risk, Class II is moderate risk, and Class III is the highest risk if SaMD is inaccurate. However, the FDA has not decided what to do about change algorithms and transparency.

3. Marketing claims: FDA clears AI SaMD claims for marketing. Visit the FDA website to learn more about AI companies’ claims submissions (see 510 submissions) and how much data (how many people) was used to train the computers and test their learning. Currently they are diagnostic aids, but they could be actual diagnostics in the future.

4. Use image cases now, with more in the future: Use cases are currently being designed for common oral diseases, caries, periodontal disease, and oral pathology. X-ray images are commonly used, but as smartphones, high-definition cameras, and scanners become more accessible, a lot of information is captured that could be used for AI enhancements in the future. For now, human factors, such as caries risk assessments, are included.

5. What does an algorithm have to do with AI? An algorithm is the formula used by the machine to perform a specific repetitive task from training data. It uses multiple x-ray images of patients with demographic information regarding where the images were taken of which patients. You will need to know this to ensure that the algorithm is relevant for your patient population.

6. Labelling: The FDA requires labeling for Class II and Class III SaMDs. Class I devices are not labelled. Many of us think we need simple food-like labels that can easily compare different products, use cases, and demographics used to form the SaMD.

Figure 1 is a view of what an ideal AI tag for dentistry might look like. Since most dentists do not save diagnostic codes, key medical history results, or period risk assessments like our physician colleagues do, more innovation will occur with AI to take into other factors, such as the impact of the latest perio diagnostic definitions. For now, labeling images with patient name, exposure date, and image type can be useful to collect to analyze what makes sense for our practices.

7. Patient-centred care: In the absence of a clear understanding of the science and the chemical and biological underpinnings of common oral diseases by the FDA, practitioners must continue to focus on patient-centered care. I could imagine a research study comparing the results we make today to AI-generated decisions to treat or not to treat, but we don’t have the data yet. This means that for now, dental professionals will be in the driver’s seat of treatment decisions.

For now, we must listen to the “better angels of our nature” to guide our practice gate guard, Maxwell’s Demon. However, in the absence of this demon, dentistry will have to look to the benchmarks described here to design our own path for AI. Promising developments in ML and AI are here, with much work to be done to determine how and if humans are better than machines.

Editor’s note: This article originally appeared in the December 2022 print edition of Dental economy magazine. Dentists in North America can take advantage of a free print subscription. Register here.


  1. Vienna N. The human use of human beings. Houghton Mifflin. Published in 1950. Revised in 1954.
  2. Grace K, Salvatier J, Dafoe A, Zhang B, Evans O. When will AI surpass human performance? Testimonials from AI experts. J Artificial Intelligence Res. 2018;62(5):729-754.
  3. Ethics and governance of artificial intelligence for health. World Health Organization. June 28, 2021.

#Dentistry #Basics #Protect #Practice

Leave a Comment

Your email address will not be published. Required fields are marked *