Guangdong University of Technology

The University of Hong Kong's Faculty of Dentistry has launched a community-based programme to detect oral health diseases among the elderly using mobile AI. WHAT IT'S ABOUT The Dental AI Community Care Project features an AI-powered mobile application for detecting gum inflammation. It will train community volunteers, comprising dental students and community residents, to provide personalised advice on oral care backed by GumAI, a technology developed by a team of university researchers in China and Malaysia. The mobile application presents gum analysis results in colours to easily identify potential oral issues: red for poor oral health, yellow indicates caution, and green shows good health. HKU Dentistry aims to expand the project, which currently runs for an initial three months, across the 18 districts of Hong Kong. The project is backed by an elderly-focused trade union and a support organisation; it also received support from law and district officials. WHY IT MATTERS Over a decade-old government survey noted that nearly nine in 10 seniors in the city had signs of gum disease or periodontitis while almost half of the elderly had untreated dental caries. Hong Kong seniors have increasingly accessed dental services over the past decade with the utilisation rate at 37% based on the latest government statistics in 2019. The Research Office of Hong Kong's Legislative Council Secretariat attributed this to the government's effort to increase service accessibility, including free dental care for seniors receiving long-term or day care services. However, dental services remain limited, partly due to the low availability of dental professionals – approximately 3.7 dentists serve every 10,000 residents in the city. THE LARGER TREND In June last year, HKU Dentistry announced its research demonstrating AI's detection of gum inflammation or gingivitis in intraoral images of over 500 individuals. Findings, which were published in the World Dental Federation's International Dental Journal, showed that the AI detected redness, swelling, and bleeding along the gum margin with over 90% accuracy. HKU Dentistry researchers collaborated with those from Hong Kong Chu Hai College in Hong Kong, China's Guangdong University of Technology, and the National University of Malaysia for this study. Beyond oral care, another research team from HKU Dentistry also developed a generative AI model for designing dental crowns. Their novel approach, called 3D-DCGAN (3D-Deep Convolutional Generative Adversarial Network), acquaints AI with good designs of natural and healthy dentitions. "During the training process, natural teeth morphological features were learned by the algorithm, so that it can design dental crowns comparable to a natural tooth — both morphologically and functionally," co-research investigator Dr Hao Ding explained. The research sought to address the limitations of current computer-aided design and manufacturing digital workflows, particularly considering labour and time.

Researchers have successfully demonstrated the use of artificial intelligence (AI) in detecting gum inflammation, also known as gingivitis, from intraoral photographs. A groundbreaking study led by researchers at the Faculty of Dentistry of the University of Hong Kong (HKU), in collaboration with multiple international institutions has successfully demonstrated the use of artificial intelligence (AI) in detecting gum inflammation, also known as gingivitis, from intraoral photographs. This cutting-edge technology can revolutionise early detection and prevention of oral and systemic diseases linked to gum inflammation, such as tooth loss, cardiovascular diseases, and diabetes. The study, published in the International Dental Journal, an official journal of the World Dental Federation (FDI), shows that AI algorithms can analyse patients' intraoral photographs to detect signs of inflammation like redness, swelling, and bleeding along the gum margin with over 90% accuracy, matching the visual examination of a dentist. This innovative technology enables population-wide monitoring of gum health and paves the way for more personalised dental care. The study was conducted by researchers from the HKU Faculty of Dentistry, the Department of Computer Science at Hong Kong Chu Hai College, the School of Information Engineering at Guangdong University of Technology, and the Faculty of Dentistry at The National University of Malaysia. It involved developing and testing an AI model using a dataset of over 567 images of gums with varying degrees of inflammation and is one of the first to explore the use of AI in detecting gum inflammation. Dr Walter Yu-Hang Lam, the study's leading HKU researcher, emphasises the significance of the findings for the early detection and management of gum disease. "Many patients do not attend regular dental check-ups, and they only seek dentists to alleviate pain when their teeth are at the end stage of dental diseases, in which tooth loss is inevitable, and only expensive rehabilitative treatments are available. Our study shows that AI can be a valuable screening tool in detecting and diagnosing gum disease, one of the key indicators of periodontal disease, allowing earlier intervention and better health outcomes for the population." He said. The use of AI in dentistry has been gaining momentum in recent years, with researchers exploring various applications of the technology, from detecting cavities to predicting treatment outcomes to biomimetic design of artificial teeth. The use of AI in gum inflammation detection is a promising development that could revolutionize how gum disease is detected, treated, and even prevented. Dr. Reinhard Chun-Wang Chau, an HKU co-investigator of the team, pointed out the benefits of using intraoral photographs in conjunction with AI technology and said: "Based on these intraoral photographs, patients can address the area that they did not clean well and seek dentist' help at an earlier stage." The collaborative nature of this study is a testament to the power of interdisciplinary research and knowledge exchange. By bringing together experts from different fields and regions, the researchers can develop an AI model that could accurately detect gum inflammation, with important implications for public health and wellbeing. For the project's next stage, Dr Lam plans to utilize the AI system for community services, making the technology more accessible to elderly and underserved communities, with the aim of improving oral health outcomes and reducing health disparities.

Human activities emit many kinds of pollutants into the air, and without a molecule called hydroxide (OH), many of these pollutants would keep aggregating in the atmosphere. Human activities emit many kinds of pollutants into the air, and without a molecule called hydroxide (OH), many of these pollutants would keep aggregating in the atmosphere. How OH itself forms in the atmosphere was viewed as a complete story, but in new research published in Proceedings of the National Academy of Sciences, a research team that includes Sergey Nizkorodov, a University of California, Irvine professor of chemistry, report that a strong electric field that exists at the surface between airborne water droplets and the surrounding air can create OH by a previously unknown mechanism. It's a finding that stands to reshape how scientists understand how the air clears itself of things like human-emitted pollutants and greenhouse gases, which OH can react with and eliminate. "You need OH to oxidize hydrocarbons, otherwise they would build up in the atmosphere indefinitely," said Nizkorodov. "OH is a key player in the story of atmospheric chemistry. It initiates the reactions that break down airborne pollutants and helps to remove noxious chemicals such as sulfur dioxide and nitric oxide, which are poisonous gases, from the atmosphere," said Christian George, an atmospheric chemist at the University of Lyon in France and lead author of the new study. "Thus, having a full understanding of its sources and sinks is key to understanding and mitigating air pollution." Before, researchers assumed that sunlight was the chief driver of OH formation. "The conventional wisdom is that you have to make OH by photochemistry or redox chemistry. You have to have sunlight or metals acting as catalysts," Nizkorodov said. "What this paper says in essence is you don't need any of this. In the pure water itself, OH can be created spontaneously by the special conditions on the surface of the droplets." The team built on research from Stanford University scientists led by Richard Zare that reported spontaneous formation of hydrogen peroxide on the surfaces of water droplets. The new findings help interpret the unexpected results from the Zare group. The team measured OH concentrations in different vials -- some containing an air-water surface and others containing only water without any air -- and tracked OH production in darkness by including a "probe" molecule in the vials that fluoresces when it reacts with OH. What they saw is that OH production rates in darkness mirror those and even exceed rates from drivers like sunlight exposure. "Enough of OH will be created to compete with other known OH sources," said Nizkorodov. "At night, when there is no photochemistry, OH is still produced and it is produced at a higher rate than would otherwise happen." The findings, Nizkorodov reported, alter understanding of the sources of OH, something that will change how other researchers build computer models that attempt to forecast how air pollution happens. "It could change air pollution models quite significantly," Nizkorodov said. "OH is an important oxidant inside water droplets and the main assumption in the models is that OH comes from the air, it's not produced in the droplet directly." To determine whether this new OH production mechanism plays a role, Nizkorodov thinks the next step is to perform carefully designed experiments in the real atmosphere in different parts of the world. But first, the team expects the results to make a splash in the atmospheric research community. "A lot of people will read this but will not initially believe it and will either try to reproduce it or try to do experiments to prove it wrong," said Nizkorodov. "There will be many lab experiments following up on this for sure." He added that UCI is a prime place for such science to continue happening, because other labs at UCI, like that of Ann Marie Carlton, professor of chemistry, focus their efforts on the role water droplets play in the atmosphere. This project, which was funded by the European Research Council, involved researchers from France's University Claude Bernard, China's Guangdong University of Technology, and Israel's Weizmann Institute.