A new artificial intelligence (AI) tool using speech analysis is capable of identifying cognitive impairment in Spanish-speaking older adults.
The algorithm, the subject of a recent study led by the University of Texas Southwestern Medical Center, could function as an early detection tool that “might aid in identifying” older adults at risk of developing dementia, according to C. Munro Cullum, professor of psychiatry, neurological surgery, and neurology, and vice chair and chief of the Division of Psychology at UT Southwestern.
“Machine learning-based tools like this one may play an increasingly significant role in the future of cognitive screening for dementia,” said Cullum, who authored the study.
Data for the study were gathered from 195 Spanish-speaking adults as part of a clinical trial in Spain. Researchers utilized four language models to train independent machine learning models, using data from the participants in conjunction with the AcceXible, a web-based platform for disease detection through speech analysis.
The final model of the speech analysis algorithm was able to “differentiate cognitively normal” participants from those with dementia with an overall accuracy ranging between 88.4% and 87.5%.
This could contribute to improving the quality of life for older adults at risk of dementia through early detection, an area that disproportionately affects marginalized racial and ethnic groups, leading to delayed dementia diagnoses.
“Ultimately, such technology may assist in identifying patients exhibiting signs of cognitive decline who may require clinical evaluation and consideration for treatment,” said Cullum in a news release about the study.
The use of AI to aid in detection of dementia is being studied by multiple institutions, as previously reported by MCB. Earlier this year, researchers at the University of California San Francisco say they have found a new way to use artificial intelligence to spot indicators of Alzheimer’s up to seven years before symptoms appear.
