news

한어Русский языкEnglishFrançaisIndonesianSanskrit日本語DeutschPortuguêsΕλληνικάespañolItalianoSuomalainenLatina

Beijing, July 22 (Xinhua) -- Early diagnosis is very important for effectively controlling the progression of Alzheimer's disease. Researchers from the University of Cambridge and other institutions in the UK have developed a new artificial intelligence (AI) model, which the team said can not only avoid invasive or expensive tests, but also predict Alzheimer's disease earlier.

It is reported that accurate early diagnosis of Alzheimer's disease currently relies on invasive or expensive testing methods, such as lumbar puncture or positron emission tomography. However, not all medical institutions have such testing conditions. As a result, up to one-third of patients may be misdiagnosed, and some patients cannot receive effective treatment due to late diagnosis. The AI ​​prediction model led by the University of Cambridge provides a non-invasive and low-cost method that can effectively predict whether the research subjects will develop Alzheimer's disease in the next three years. The relevant research has been published in the British journal "Electronic Clinical Medicine".

Based on cognitive test and MRI scan data from 400 patients with gray matter atrophy collected by a US research team, the research team used machine learning algorithms to build an AI prediction model and tested the model using real-world data from multiple clinics in the UK, Singapore, etc. Due to the use of multimodal data such as text and images, the model can more accurately predict the probability of early symptoms turning into Alzheimer's disease than traditional clinical diagnosis.

Test results showed that the model had an 82% accuracy rate in identifying people who would develop Alzheimer's disease within three years, and an 81% accuracy rate in identifying people who would not develop Alzheimer's disease within three years.

More than 55 million people worldwide suffer from dementia, the most common type of which is Alzheimer's disease. In the future, the research team hopes to expand the model to predict other types of dementia, such as vascular dementia and frontotemporal dementia, and use different types of data, such as markers in blood tests. (End)