Researchers at the University of Alberta's Faculty of Medicine & Dentistry are using artificial intelligence to help dentists identify and manage dental anxiety in children, according to a university news article published November 12. The approach adapts an existing psychological assessment tool — the Child Drawing: Hospital (CD:H) Scale — for use in dental settings, then trains machine learning models to score the drawings automatically.
The project began with Silvia Ortiz, a former master's student supervised by Dr. Hollis Lai, professor and associate chair at the Mike Petryk School of Dentistry. Ortiz adapted the CD:H Scale, which was originally developed and validated to evaluate the emotional status of school-aged children in hospitals. The method is straightforward: children receive a blank sheet of paper and eight crayons in specific colours, with no pencil or eraser, allowing them to draw freely. Their drawings are then assessed across 23 criteria, each scored from one to 10, with 10 indicating the highest level of anxiety. Criteria include the position and size of the person drawn, as well as the number and predominance of colours used.
Lai told the university that the project addresses a common challenge: young children may struggle to communicate their feelings through traditional Likert scale surveys, which ask respondents to rate their experiences on a scale of five or seven levels. The drawing-based approach offers an alternative that does not rely on verbal or numerical self-reporting.
Building on Ortiz's work, another master's student, Rojin Adabdokht, developed and tested machine learning algorithms to automate the anxiety screening process. The goal was to explore how AI could replicate human scoring in a busy dental office, giving dentists insights into their young patients while saving time. Lai clarified that the project focused on comparing AI-generated scores with those scored by human professionals to determine whether the process could be automated.
The team encountered constraints in training models with a limited sample of images, Lai said. This led them to consider how generative samples could be used to train detection models — an innovative augmentation approach that helped highlight what made the training data unique.
For university students considering careers in dentistry, oral health, or AI in healthcare, the research illustrates a growing intersection between clinical practice and machine learning. The ability to automate routine assessments could reshape how dental offices operate, potentially reducing the time dentists spend on screening tasks and allowing more focus on patient care.
Beyond the anxiety project, Lai's group within the Oral Health Analytics and Informatics Unit (OHAI-U) is applying image-based classification to other dental challenges. One project, in collaboration with oral pathologist Dr. Pallavi Parashar and graduate students, uses the Segment Anything Model (SAM) — an AI vision learning model — to identify and quantify cells, helping oral pathologists analyze samples more efficiently without having to examine details manually under a microscope. A separate use case involves teaching AI to assess images of the palatal suture — the roof-of-the-mouth growth line — to determine if a patient's jaw is still maturing. Additional AI tools look at cervical vertebral maturation to forecast the amount of remaining facial development in a patient.
Lai emphasized that putting AI to work effectively requires more than access to the latest tools. Researchers must first understand the programming and methodology behind them, he said, adding: "If you don't understand programming, you won't understand AI. That's why we went down the pathway of methodological training."
This methodological training is offered through the Online Graduate Certificate in AI and Health, taught across the College of Health Sciences, where Lai leads a course on AI integration and transformation in health. For flexible, hands-on learning, faculty, staff and students can join a monthly Dental AI Literacy Virtual Series, which provides interactive discussions, hands-on tool demonstrations and guided literature reviews. The Applied AI in Oral Health Summer Institute also brings together participants from across Canada for AI literacy and methodology training.
"With oral health research, the commercial sector is moving quickly," Lai told the university. "There are tools available, but training is not readily available, and it's getting harder to adapt to AI research opportunities."
The university article noted that the work is part of a broader series showcasing how faculty and staff are using AI to enhance student learning, improve efficiencies and model critically informed use of the technology.