Exploring Dental Health Detection Using a Sonic Toothbrush

Dental hygiene is an important part of a person’s overall health. Early detection of dental diseases is crucial to prevent unwanted consequences. Although x-rays are currently the most accurate gold standard for detecting dental disease, they are not available to many people around the world.

Carnegie Mellon College of Engineering researchers teamed up with the University of Pittsburgh School of Dentistry to create a dental health detection system that uses commercially available electric toothbrushes for dental health detection. dental condition. The work is published in the journal ACM Proceedings on Interactive, Mobile, Wearable, and Ubiquitous Technologies.

According to the Centers for Disease Control, in 2024, approximately 57 million Americans lived in a dental health professional shortage area and approximately 67% of these shortage areas were in rural communities. By offering an electric toothbrush capable of performing dental self-exams at home, the hope is to provide dental care to millions of people who would not otherwise receive it.

The ToMoBrush (Tooth Monitoring Brush / Tomorrow’s Brosse de Tooth) explores the potential of using a commercially available electric toothbrush with minimal hardware modification for dental health detection to enable dental self-examinations regularly at home.

Rather than considering a toothbrush solely as a cleaning instrument, ToMoBrush exploits the fact that an electric toothbrush emits acoustic signals generated by the rapid automatic vibrations of the bristles. When the brush is in contact with a tooth, the tooth also vibrates with the toothbrush and produces distinct acoustic signals depending on the condition of each tooth.

“Dental diseases are a major public health challenge that can cause pain and infections, potentially leading to problems with eating, speech and even social interaction,” says Kuang Yuan, a Ph.D. student in electrical and computer engineering. “We explored an inexpensive solution for dental health monitoring that patients can use regularly from the comfort of their home.”

The team then developed a data-driven signal processing pipeline to detect and discriminate different dental conditions, such as cavities, plaque, and food impaction, as well as variations in electric toothbrushes, such as brand, battery charge and hair formation. To address these variables, the team modeled the vibration system including the toothbrush, dental resonance, and the force and movement of brushing.

In their article, the researchers propose an algorithm to separate these different factors and extract clean dental resonance signatures based on a key observation. Although these factors share the same frequency band, their rates of variation across frequencies are different. By adapting a technique widely used in speech processing to separate glottal excitation and vocal tract resonances, the team proposes to convert the signal into the cepstrum domain where these distinct behaviors are easily separable.

“After obtaining the dental resonance signature, we developed a feature selection algorithm to select specific signature regions specialized in detecting three different dental conditions,” says Yuan. “We can perform health detection by comparing signatures with previous healthy baseline measurements.”

The team believes that such a system can complement the dental health care system, even for those who have access to professional dental care, by providing early warnings about potential problems between visits to the dentist.

Yuan will present the team’s findings at the 2024 International Symposium on Ubiquitous and Ubiquitous Computing on Wearable Computing (UbiComp/ISWC) in Melbourne, Australia.