AI system for single-tooth prediction of early childhood caries detection with over 90% accuracy

Email

 

image: 

HKU Dentistry developed Spatial-MiC, the world’s first AI system for early childhood caries detection at the single-tooth resolution.

view more 

Credit: The University of Hong Kong

Early childhood caries (ECC)—the world’s most prevalent chronic childhood disease—disproportionately targets specific teeth, a mystery that has remained unresolved until now. A collaborative research team from the Faculty of Dentistry of the University of Hong Kong (HKU), Chinese Academy of Sciences (CAS-QIBEBT), Qingdao Stomatological Hospital, and Qingdao Women and Children's Hospital has made a groundbreaking discovery that could revolutionise the prevention of childhood tooth decay. The team has developed the world’s first artificial intelligence (AI) system capable of predicting early childhood caries risk for individual teeth based on microbial characteristics, achieving an accuracy rate of over 90%. This pioneering study was published in Cell Host & Microbe.

The research was led by Professor Shi Huang, Assistant Professor in Microbiology from the Division of Applied Oral Sciences and Community Dental Care at the HKU Faculty of Dentistry. The team also includes Yufeng Zhang, a PhD student from the same faculty, Professor Jian Xu from CAS-QIBEBT, Dr Fei Teng from Qingdao Stomatological Hospital, and Dr Fang Yang from Qingdao Women and Children's Hospital.

The research team conducted the most comprehensive analysis to date of tooth-specific microbial communities in young children aged 3-5 years, using an innovative approach that combined cutting-edge 16S rRNA sequencing with shotgun metagenomics for microbial compositional and functional analysis. By tracking 2,504 individual tooth plaque samples from 89 preschoolers over nearly a year, they uncovered distinct patterns that foretell dental decay.

At the heart of the discovery is a remarkable anterior-to-posterior microbial gradient in healthy mouths. The study found that front teeth (incisors) naturally harbour different bacterial communities than back teeth (molars), creating a predictable spatial pattern across the mouth. This gradient, maintained by factors like saliva flow and tooth anatomy, becomes disrupted when cavities begin to form. The researchers identified specific bacterial shifts that occur well before visible decay, including the migration of incisor-associated microbes to molar sites and vice versa.

The team's most significant achievement was developing Spatial-MiC, the world’s first AI system that predicts cavity risks in individual teeth based on complex microbial communities. The system analyses these microbial patterns to assess cavity risk. By combining data from a tooth's microbial community with information from its neighbours, Spatial-MiC achieved 98% accuracy in detecting existing cavities and 93% accuracy in predicting cavities two months before they became clinically apparent. This represents a major improvement over current whole-mouth assessment methods, which often miss early warning signs.

The implications for children's dental health are profound. ECC affects over 70% of 5-year-olds in China and remains the most common chronic childhood disease worldwide. Current prevention strategies typically treat all teeth equally, despite clear differences in susceptibility. This research paves the way for precision dentistry approaches that could provide targeted preventive care to high-risk teeth before damage occurs.

“These findings fundamentally change how we understand tooth decay,” Professor Huang explained. “We've moved from seeing cavities as inevitable to being able to predict and prevent them at the microbial level, tooth by tooth.”

The team envisions a future where the system could be expanded to validate the approach in diverse populations. The ultimate goal is to develop clinical tests that bring the technology into dental offices worldwide. As Dr Yang, the first author noted, “This isn't just about better dental care. It's about giving children healthier starts in life by preventing pain, infections, and the developmental impacts of severe tooth decay in a more precise manner.”

Link to research: https://doi.org/10.1016/j.chom.2025.05.006

Smoking leaves lasting mark on teeth, research reveals

Researchers from Northumbria University have discovered that smokers have tell-tale signs of their smoking habits ingrained deep within their teeth, which remain even after a person has quit

Peer-Reviewed Publication

Northumbria University

FacebookXLinkedInWeChatBlueskyMessageWhatsAppEmail

 

image: 

Example of smoking damage in an archaeological tooth. The magnified image shows variations in the tooth's cementum rings caused by smoking

view more 

Credit: Dr Ed Schwalbe, Northumbria University

Evidence of the permanent impact of smoking on people’s teeth has been uncovered by researchers for the first time. 

Researchers from Northumbria University have discovered that smokers have tell-tale signs of their smoking habits ingrained deep within their teeth, which remain even after a person has quit. 

Their findings, which are now published in the scientific journal PLOS One, could help to shine new insights on forensic and historical investigations. 

Teeth consist of three main hard tissues: enamel, dentine and cementum. Cementum, which covers the tooth root, develops characteristic “rings” that grow each year as we age – much like tree rings. 

The research team had initially set out to see if these rings could be used to predict the age of an individual in a forensic setting, such as identifying disaster victims or for situations when an individual’s DNA is not on a DNA database. 

After examining a total of 88 teeth provided by both living dental patients and from archaeological remains, they were surprised to find signs of disruption in the cementum rings of some teeth, but not in others. 

The disruption appeared as variations in the thickness and regularity of the rings within the teeth. 

The researchers realised that these disruptions were associated with those who had identified as current or ex-smokers. 

Their study revealed evidence of smoking damage in the teeth of 70% of ex-smokers and 33% of current smokers, compared to just 3% of non-smokers. 

They also found that the cementum is thicker in ex-smokers. They believe this is a result of the cementum returning to its normal levels when smoking ceases, leaving ‘stronger’ deposits on top of the damaged rings which makes them thicker, whereas current smokers continue to have disruption to their cementum levels. 

“Our research shows that it’s possible to tell if someone was a smoker just by examining their teeth,” said Dr Ed Schwalbe, Associate Professor in Northumbria University’s Department of Applied Sciences. 

“We found that the regular annual deposition of rings was disrupted for some individuals and realised that these disruptions were associated with current or ex-smokers, but were very rare in non-smokers.” 

Forty-six individuals who were undergoing dental treatment requiring tooth extraction consented to take part in the study, providing 70 teeth between them along with their medical and smoking histories.  

Notably, the researchers found smoking damage in one of the teeth provided by a living donor which they estimated to have occurred between the ages of 22 and 41.  

On checking the information provided, they found that the donor, who was aged 58 at the time of tooth extraction, was a smoker during that period. They had begun smoking when they were 28 years old and stopped at the age of 38. 

Dr Schwalbe and Dr Valentina Perrone worked with Dr Sarah Inskip, UKRI Fellow at the University of Leicester’s School of Archaeology and Ancient History, to sample a further 18 teeth from archaeological remains dating from 1776-1890.

Evidence of the age, biological sex and date of death was available for 13 of the 18 teeth provided.  

Some of the archaeological teeth bore clear evidence of smoking activity, displaying staining and even notches from pipe smoking. 

Remarkably, cementum analysis of the archaeological samples revealed that the rings within the teeth of smokers who died in the 18th and 19th centuries displayed the same signs of disruption as those from living donors who were current or ex-smokers.  

The findings could prove to be especially important for forensic science and historical studies in future, added Dr Schwalbe. 

“This could help us learn more about people’s lifestyles in the past, especially in archaeological studies where patterns of tobacco use can reveal important cultural insights,” he said.

 “The identification of 'smoking damage' in archaeological teeth opens up further avenues to understand how the long-term consumption of tobacco in populations has affected our health through time,” added Dr Inskip, who leads the Tobacco, Health and History Project which looks at the long-term consequences of tobacco use on health between 1600-1900.

“By looking at growth rings in the teeth, we can also estimate a person’s age when the tooth was removed, or when they died,” said Dr Schwalbe. “Together, this information could help identify unknown individuals – such as disaster victims or those buried in mass graves – and offer new tools for forensic and historical investigations.” 

Cementochronology – the study of what is more formally known as acellular extrinsic fibre cementum (AEFC) – has been widely used to estimate age at death and conditions such as pregnancy or disease, but this is believed to be the first time it has been used to predict tobacco use. 

Dr Valentina Perrone, who is now working as a Research Assistant at Leicester University, added: “We compared the cemental deposition of smokers, ex-smokers and non-smokers visually and statistically to identify irregularities that were potentially connected to smoking activity. We found that individuals with a history of smoking – whether as a current or former smoker – were significantly more likely to have disruption to their cementum than those who did not.  

“Smoking is known to have a systemic impact on the body and numerous studies have highlighted the correlation between smoking, peridontitis and tooth loss. This study shows, for the first time, the biological record of smoking-related oral health damage within the dental structure.” 

The paper, Reconstructing smoking history through dental cementum analysis – a preliminary investigation on modern and archaeological teeth is now published in PLOS One. 

Researchers build a better dental implant

Preclinical study demonstrates a new ‘smart’ implant and minimally invasive surgery to better retain feel and function of natural teeth

Peer-Reviewed Publication

Tufts University

FacebookXLinkedInWeChatBlueskyMessageWhatsAppEmail

 

image: 

From left to right: Study co-authors Subhashis Ghosh, Jake Jinkun Chen, and Siddhartha Das in Chen’s lab at Tufts’ Biomedical Research and Public Health Building.

view more 

Credit: Jenna Schad/Tufts University

Each year, millions of people in the U.S. get dental implants as a long-term, natural-looking fix for missing teeth. But traditional implants don’t fully mimic real teeth.

Researchers from Tufts University School of Dental Medicine and Tufts University School of Medicine recently described a new approach to dental implants that that could better replicate how natural teeth feel and function. Their study, published in Scientific Reports, shows early success with both a “smart” implant and a new gentler surgical technique in rodents.  

“Natural teeth connect to the jawbone through soft tissue rich in nerves, which help sense pressure and texture and guide how we chew and speak. Implants lack that sensory feedback,” says Jake Jinkun Chen, DI09, a professor of periodontology and director of the Division of Oral Biology at the School of Dental Medicine and the senior author on the study.

Traditional dental implants use a titanium post that fuses directly to the jawbone to support a ceramic crown, and the surgery often cuts or damages nearby nerves. To tie these inert pieces of metal into the body’s sensory system, the Tufts team developed an implant wrapped in an innovative biodegradable coating. This coating contains stem cells and a special protein that helps them multiply and turn into nerve tissue. As the coating dissolves during the healing process, it releases the stem cells and protein, fueling the growth of new nerve tissue around the implant.

The coating also contains tiny, rubbery particles that act like memory foam. Compressed so that the implant is smaller than the missing tooth when it’s first inserted, these nanofibers gently expand once in place until the implant snugly fits the socket. This allows for a new minimally invasive procedure that preserves existing nerve endings in the tissue around the implant.

“This new implant and minimally invasive technique should help reconnect nerves, allowing the implant to ‘talk’ to the brain much like a real tooth,” explains Chen. “This breakthrough also could transform other types of bone implants, like those used in hip replacements or fracture repair.”

Six weeks after surgery, the implants stayed firmly in place in rats, with no signs of inflammation or rejection. “Imaging revealed a distinct space between the implant and the bone, suggesting that the implant had been integrated through soft tissue rather than the traditional fusion with the bone,” says Chen. This may restore the nerves around it.

The research was conducted by Chen and School of Dental Medicine faculty Qisheng Tu and Zoe Zhu, as well as postdoctoral scholars Siddhartha Das (lead author) and Subhashis Ghosh at Tufts University School of Medicine.

These initial results are promising, but it will take more studies and time—for example, research in larger animal models to look at outcomes, including safety and efficacy—before trials can begin in human volunteers.

The researchers’ next step will be a preclinical study to see if brain activity confirms that the new nerves surrounding the prototype implant indeed relay sensory information.

Citation: Research reported in this article was supported by the National Institutes of Health under award numbers RO1DK131444, R01DE030074, R01DE025681, and R01DE032006. Complete information on authors, funders, methodology, limitations, and conflicts of interest is available in the published paper. 

Disclaimer: The content is solely the responsibility of the authors and does not necessarily represent the official views of the funders.  

---

Journal

Scientific Reports

DOI

10.1038/s41598-025-99923-8 

Toothbrush-shaped ultrasound allows for gum monitoring

 

Peer-Reviewed Publication

American Chemical Society

FacebookXLinkedInWeChatBlueskyMessageWhatsAppEmail

 

image: 

The toothbrush-shaped ultrasound transducer (left image) features a small head size (right image), allowing easy access to premolars and molars in the back of the mouth.

view more 

Credit: Adapted from ACS Sensors 2025, DOI: 10.1021/acssensors.5c00521

When visiting the dentist, you might remember being poked and prodded by a thin metal instrument to check your teeth and gums. This technique, called periodontal probing, is used to look for signs of gum disease. Now, researchers publishing in ACS Sensors report a toothbrush-shaped ultrasound transducer that can provide a less invasive screening for gum disease. In proof-of-concept demonstrations on animal tissues, the device produced measurements similar to those of a manual probe.

Gum disease is a common condition affecting tissue that surrounds and supports teeth. If left untreated, it causes the gums to pull away from the teeth, creating pockets where harmful bacteria can grow. Currently, manual periodontal probing is the standard way to check for gum disease, but the technique is uncomfortable and can miss early stages. So, Jesse Jokerst and colleagues developed a small, non-invasive ultrasound method capable of imaging teeth and gums — even hard-to-reach molars and premolars at the back of the mouth.

Ultrasounds work by sending sound waves into the body. When the sound waves encounter a structure, like gum tissue or a tooth, they are reflected and detected by a transducer. The transducer then converts the reflected sound waves into an image. Currently, most ultrasound transducers have large heads that are about the same size as a wireless earbuds case. Although they work for larger parts of the body, these transducers cannot access smaller spaces like those in the mouth. Smaller transducers that are about half the length and width of traditional devices are available, but current models have limited image resolution because they are only able to produce and detect low frequencies. To overcome these limitations, the researchers created an even smaller toothbrush-shaped transducer that operates at a higher frequency and can produce high-quality images of teeth and gums.

To test the transducer’s accuracy, the researchers used the new instrument to measure the gum thickness and gum height of pig teeth. Then the researchers repeated the measurements using a manual metal periodontal probe. After analyzing the correlation between the two sets of measurements, the team found that the ultrasound measurements were statistically similar to those of the manual technique. The results support the reliability of the toothbrush-shaped transducer as a less invasive technique for monitoring gum health.

“We designed this tool to meet the realities of clinical dentistry — it is miniaturized, accurate and easy to use. Future work will use this device with patients to image below the gumline, where we will monitor treatments and diagnose earlier to reduce dental pain and help patients keep a healthy smile," says Jokerst.

Study predicts national fluoride ban would substantially increase children’s tooth decay and dental costs

 

• Mass General Brigham researchers developed a model to estimate the impact on children’s dental health and its cost if fluoride were no longer added to U.S. public drinking water.
• The model estimated that a fluoride ban would result in a 7.5 percentage point increase in tooth decay and cost an additional $9.8 billion over 5 years.
• This translates to tooth decay in 25.4 million more teeth, the equivalent of a decayed tooth for one out of every three children.

Fluoride has been added to public water systems in the United States since 1945 to strengthen tooth enamel and fight off bacteria, ultimately reducing tooth decay. Mass General Brigham researchers developed a model to estimate dental health outcomes for children if the United States were to ban fluoridation of public water. The new study, published in JAMA Health Forum, found that banning fluoride would substantially increase dental decay and costs particularly for publicly insured and uninsured children.

“Fluoride replaces weaker ions within tooth enamel, making it stronger and less susceptible to tooth decay caused by bacteria,” said senior author Lisa Simon MD, DMD, Division of General Internal Medicine at Brigham and Women’s Hospital, a founding member of the Mass General Brigham healthcare system. “There’s strong evidence from other countries and cities, such as Calgary in Canada, showing that when fluoride is eliminated, dental disease increases. Our study offers a window into what would happen in the United States if water fluoridation ceased.”

Simon and the research team focused on children for the study, because fluoride strengthens teeth during development, and more robust data links fluoridated water to oral health in this age group.

The study used detailed oral health and water fluoridation data collected from 8,484 children (ages 0-19, 49% girls) in the nationally representative National Health and Nutrition Examination Survey (NHANES). Using this dataset, the researchers developed a microsimulation model to see how banning fluoride from drinking water would impact oral health, quality of life and dental care costs.

The researchers simulated two scenarios over 5- and 10-year periods, which align with policy planning horizons. First, maintaining current fluoride levels, and second, eliminating the addition of fluoride to public water.

"Using a simulation model to track the progression of diseases in current populations, we estimated the impact of removing fluoride on the risk of tooth decay and the related dental care costs, including treatment for decay and complications from delayed treatment. We ran the simulation 1,000 times to see how different factors could affect the results. This approach helps ensure that our predictions are more reliable and reflective of real-world variability,” said first author Sung Eun Choi, PhD, assistant professor of Oral Health Policy & Epidemiology at Harvard School of Dental Medicine.

The researchers found that eliminating fluoride increased the total number of decayed teeth by 7.5 percentage points, or 25.4 million more teeth with tooth decay over five years (equivalent to a tooth for one out of every three American children). The number of fluorosis cases—a discoloring of tooth enamel due to excessive fluoride intake—decreased by 0.2 million. They also estimated a cost of $9.8 billion in additional dental care costs over five years, which rose to $19.4 billion after 10 years.

“Most of the increased cost could be attributed to publicly insured children, meaning it would be a direct public health cost,” said Simon.

The study did not model cognitive effects from fluoride exposure as current levels of fluoride in public water are not associated with worse neurobehavioral outcomes. The researchers note that their model demonstrates meaningful, ongoing benefit from fluoride at safe levels currently recommended by the Environmental Protection Agency, the National Toxicity Program, and the Centers for Disease Control and Prevention.

“We know fluoride works. We’re able to show just how much it works for most communities and how much people stand to lose if we get rid of it,” said Simon.

 

Dental flosser for at-home stress monitoring

FacebookXLinkedInWeChatBlueskyMessageWhatsAppEmail

 

image: 

This dental floss pick has a sensor that can assess your stress level.

view more 

Credit: Atul Sharma

Over time, stress and anxiety can build to a point where life’s challenges become overwhelming and cause physical effects. Now, in ACS Applied Materials & Interfaces, researchers report a dental floss pick with a built-in sensor that could monitor stress as part of a daily routine. The device, which accurately senses levels of the stress hormone cortisol in minutes, could help users recognize when it’s time to get help.

Unchecked chronic stress can lead to health conditions such as heart disease and mental disorders. Catching rising stress levels early is important, but daily blood tests at a doctor’s office aren’t feasible for most people, and self-reported questionnaires are subjective. That’s why researchers are developing point-of-care tests that measure cortisol levels in saliva, which mirror the hormone’s concentrations in blood. Although the saliva tests are promising, many of them require people to remember to perform the complicated analyses or use a bulky mouthguard. In addition, the anxiety of performing a test can cause stress levels to spike. So, Sameer Sonkusale and colleagues took a completely different approach by integrating a cortisol sensor into a dental floss pick — something many people use every day.

The team’s dental pick features floss that collects saliva. The floss is connected to a microfluidic thread that transports saliva to a flexible electrochemical sensor embedded in the handle of the pick. The sensor is made of an electrode with an electropolymerized molecularly imprinted polymer (eMIP) on it. The researchers made the eMIP by embossing cortisol molecules into an electrically conductive film and then removing them — similar to a shoe leaving an impression in wet cement. During tests, salivary cortisol binds in the impressions, decreasing the electrical current flowing through the sensor, which produces a signal that is wirelessly transmitted to a mobile device. The strength of the signal corresponds to the amount of cortisol in the saliva. Finally, the analyzed saliva moves to an adsorbent waste pad next to the sensor and the pick can be discarded.

The device takes around 10 minutes to report a result. In tests with cortisol-spiked artificial saliva, the dental pick was sensitive enough to detect small increases in cortisol that could be early indicators of stress. In tests with real human saliva samples, the dental flosser performed just as well as the commonly used ELISA saliva test for measuring levels of cortisol.

Overall, the researchers say that this device is one of the best-performing cortisol sensors reported so far, and it could someday be modified to detect other clinically important salivary molecules.