Every year, ten million people are diagnosed with dementia. Different forms of dementia and similar symptoms make it hard to diagnose and treat effectively.
Researchers have created a machine learning (ML) tool that can accurately identify different types of dementia using common clinical data. This data includes patient demographics, family medical history, medication use, neurological exam scores, and MRI scans.
The study, published in Nature Medicine, highlights the potential of this AI tool for diagnosing Alzheimer’s disease (AD) and related dementias using routine clinical data. This is especially important in areas with limited access to advanced medical testing.
The AI tool was trained on data from over 50,000 people across nine global datasets. It achieved a high accuracy score, showing it can distinguish between different types of dementia effectively.
When compared to neurologists working alone, the AI tool improved diagnosis accuracy by more than 26% across all dementia types. In a test with 12 neurologists, the AI-enhanced diagnoses were more confident and accurate.
There is a shortage of neurology experts worldwide, while the number of dementia patients is rising. This AI tool can help by providing early diagnoses and assisting doctors, which can prevent the diseases from worsening.
With dementia cases expected to double in the next 20 years, this AI tool aims to meet the growing demand for accurate diagnosis and treatment.
This research was supported by the Karen Toffler Charitable Trust, National Institute on Aging, American Heart Association, Gates Ventures, and the National Institutes of Health.
Source: futurity
