Artificial Intelligence Recognises Loneliness in Senior Citizens
AI is now capable of identifying loneliness in senior citizens
A new study published by the American Journal of Geriatric Psychiatry carried out by researchers of University of California San Diego School of Medicine reveals that using artificial intelligence and natural language processing (NLP) loneliness in older adults can be detected. It specifically used NLP software and other machine learning (ML) tools in 80 senior citizens aged between 66 and 94 who live alone but independently to analyse linguistics.
“Most studies use either a direct question of ‘how frequent do you feel lonely,'” opines senior author of the study Ellen Lee, MD, Assistant Professor of Psychiatry at University of California San Diego School of Medicine. It can lead to biased responses because of the stigma associated with loneliness or UCLA Loneliness Scale which does not distinctly use the word ‘lonely,'”
“For this project, we used natural language processing, an unbiased quantitative assessment of expressed emotion and sentiment in concert with the specific loneliness measurements tools,” he elaborates.
Early findings discovered that “lonely speech” could be used to identify loneliness in senior citizens, enhancing assessment and treatment, especially practising physical distancing and social isolation periods. The study shows that lonely individuals had more extended responses during interviews and expressed greater misery to direct questions about loneliness, and young adults expressed their loneliness in different ways.
It also demonstrates the feasibility of leveraging NLP analysis to understand complex emotions like loneliness better. ML models predicted qualitative loneliness with 94% accuracy, authors notice. And “complex artificial intelligence systems could intermediate in real-time to help individuals to reduce their loneliness by embracing positive cognitions, engaging in meaningful social activities, and managing social anxiety,” says first author Varsha Badal, PhD, a postdoctoral research fellow.
IBM-UC San Diego centre explores NLP signatures of loneliness and wisdom that are inversely associated with senior citizens. “Speech data can be combined with our other assessment of cognition, mobility, sleep, physical activity and mental health. It will improve our understanding of ageing and to promote successful ageing,” emphasizes study co-author Dilip Jeste, M.D, Senior Associate Dean for Healthy living.
AI cannot only be used to identify loneliness but also can detect illness in older adults, allowing them to live more independently for a more extended period of time. Researchers at the University Of Peloponnese, Greece is creating prototype living spaces called smart homes for research purposes. It will give them insights into how they may look and work in the near future for senior citizens, people with disabilities and those who have chronic conditions.
The researchers aim to enable people to live independently, safely, and conveniently for longer in assisted living with the help of artificial intelligence (AI).
For instance, One device, a smart mirror, is already being used to identify early signs of potential illness. Information like heart rate, blood pressure, and pupil size could be delivered directly to a physician or family member once potential ill-health is identified.