Researchers aim to use AI for early screening and prognosis of dry eye disease

Dry eye disease (DED) is one of the most common eye diseases, affecting up to 30% of the world's population. This disease can affect many different types of people and can ultimately be a major hindrance to your overall quality of life. Early screening and prognosis are essential for the progression of a patient's disease. However, this can be difficult. In this study, researchers aim to use artificial intelligence (AI) to aid in early screening and prognosis of his DED. The use of AI can not only make screening more accessible to individuals, but also support personalized treatment interventions for patients.

The researchers announced their results as follows. Big data mining and analysis April 22nd.

DED can affect a wide range of people, including people who wear contact lenses, wear makeup, stay up late, spend a lot of time looking at screens, and people over the age of 30. Symptoms of this disease are dry eyes, irritation and burning, tearing, eye fatigue, and pain. It is easy to see how this disease can dramatically impact a large portion of the modern world's population. This is where the joint efforts of the worlds of eye disease detection and computer scientists and engineers can help.

By addressing challenges, providing insights, and charting future research paths, we will significantly contribute to advances in the detection of ophthalmological diseases through sophisticated technical methods. ”

Mini Han Wang, writer, researcher

There are seven aspects to this AI-based disease detection. Timely intervention and correct prognosis through AI screening process is the first part. The use of AI-driven thorough investigation of DED is another feature, a supporting principle to ensure a level of thoroughness and reliability throughout the process. A systematic approach follows, followed by a fusion of computer science, engineering and ophthalmology. Next, standards for DED detection need to be devised and maintained for future researchers and practitioners, which will naturally lead to advances in the field. Finally, all studies, methodologies, and tools must be compiled so that researchers, scholars, and practitioners have access to all currently published information.

While ophthalmologists set guidelines for disease frameworks and diagnostic flags, AI does much of the heavy lifting. Ideally, this AI would be able to use images and videos taken from users' phones to reach users around the world. AI uses these images and risk factors in a patient's life to create a smart, informed prognosis. Furthermore, AI can continuously learn and advance research by contributing to predictive models for DED.

The use of AI detection for DED has a lot of potential, especially considering that the risk factors are normal activities in many people's daily lives. Further research is needed to make the detection methods sufficiently accessible and accurate.

“However, there are still challenges for engineers in selecting diagnostic criteria and combinations of different types of datasets. Using reliable algorithms, images and videos captured from mobile phones for accessibility purposes, and early screening “This will enable a holistic approach to healthcare,” he said. Mr. Wang.

Through continuous testing and collaboration between technicians and ophthalmologists, this testing method can contribute to early screening for DED and subsequent treatment measures to reduce worsening of symptoms or restore quality of life for patients. There is a great possibility that it will be helpful.

Mini Han Wang and Xiangrong Yu of Zhuhai People's Hospital, Mini Han Wang is also from the Department of Ophthalmology and Visual Sciences, Chinese University of Hong Kong, Department of Data Science, City University of Macau, and Department of Big Data, City University of Macau. Ruming Xin, Zhuhai Institute of Advanced Technology, Chinese Academy of Sciences, First Affiliated Hospital of Shandong First Medical University, Yi Pan, Shenzhen Institute of Advanced Technology, Feng Gu, University of Staten Island, Chinese Academy of Sciences, Department of Optoelectronic Engineering, Jinan University, New York University. Junbin Fang, Chi Pui Pang, Kelvin KL Chong, Carol Yim-Lui Cheung, Xulin Liao, Department of Ophthalmology and Visual Sciences, Chinese University of Hong Kong; Mr. Xiao Fang, Zhuhai Aier Eye Hospital; Mr. Jie Yang, Department of Ophthalmology and Visual Science, Chongqing University of Industry, Trade and Industry; Department of Intelligence, Ruoyu Zhou and Wenjian Liu, Department of Data Science, Macau City University, Xiaoshu Zhou, Science and Technology Exchange Center for Cooperation with China and Portuguese-speaking Countries, and Fengling Wang, Department of Artificial Intelligence, Hezhou University, contributed to this research. did.

China Natural National Natural Science Foundation, Shenzhen Key Research Institute of Intelligent Bioinformatics, Shenzhen Science and Technology Program, Guangdong Provincial Basic and Applied Basic Research Foundation, Zhuhai Technology Research Foundation, MOE Humanities and Social Sciences Project, Science and Technology Research Program of Chongqing Municipal Board of Education. This research was made possible by the Chongqing Natural Science Foundation of China.