A new study is revealing how artificial intelligence technologies provide a novel way to analyze speech patterns in older adults to identify loneliness, something occurring with frequency during the coronavirus pandemic.
Researchers at the University of California, San Diego, School of Medicine published a proof-of-concept paper in the American Journal of Geriatric Psychiatry about their use of natural language patterns-understanding software and other machine-learning tools to analyze the linguistics of and identify degrees of loneliness in 80 older adults aged 66 to 94 years who reside in independent living.
In addition to asking and documenting answers to questions from the self-reported UCLA Loneliness Scale, participants were interviewed by trained study staff members. Those conversations were analyzed using NLP-understanding software developed by IBMS, along with other machine-learning tools.
“NLP and machine learning allow us to systematically examine long interviews from many individuals and explore how subtle speech features, like emotions, may indicate loneliness,” said first author Varsha Badal, Ph.D., a postdoctoral research fellow. “Similar emotion analyses by humans would be open to bias, lack consistency and require extensive training to standardize.”
Early findings found that “lonely speech” could be used to detect loneliness in older adults, improving assessment and treatment, especially during physical distancing and social isolation periods.
They found lonely individuals had longer responses during interviews and expressed greater sadness to direct questions about loneliness, and men and women expressed their loneliness in different ways.
The study demonstrates the feasibility of using NLP analysis to better understand complex emotions such as loneliness. The authors noticed the machine-earning models predicted qualitative loneliness with 94% accuracy and that, “eventually, complex AI systems could intervene in real-time to help individuals to reduce their loneliness by adopting in positive cognitions, managing social anxiety and engaging in meaningful social activities.”
“Our IBM-UC San Diego Center is now exploring NLP signatures of loneliness and wisdom which are inversely linked in older adults, said study co-author Dilip Jeste, M.D., senior associate dean for healthy aging and senior care and co-director of the IBM-UC San Diego Center for Artificial Intelligence for Healthy Living. “Speech data can be combined with our other assessments of cognition, mobility, sleep, physical activity and mental health to improve our understanding of aging and to help promote successful aging.”
Another use for artificial intelligence
Artificial intelligence also may help detect illness in older adults, enabling them to live more independently for a longer period of time.
Researchers at the University of Peloponnese in Greece is creating prototype living spaces, so-called smart homes, to research how they may look and work in the near future for older adults, people with disabilities and those who have chronic conditions.
The aim, researchers said, is to allow people to live independently, safely and conveniently for longer in assisted living with the help of artificial intelligence.
One device, a smart mirror, uses facial recognition technology to detect early signs of potential ill health. Information such as heart rate, blood pressure and pupil size could be sent directly to a physician or family members if potential illness is detected.