A paper outlining a machine learning approach to human psychology was just published in Aging-US by Deep Longevity and Nancy Etcoff, Ph.D., an expert on joy and beauty.
Two computer models of human psychology were built by the authors using information from the Midlife in the US study.
The first model uses a group of deep neural networks to forecast the respondents’ ages in years and their psychological health using data from a psychological survey. This model illustrates the trajectory of the human mind as it ages. It also indicates that, like mental autonomy and environmental mastery, the capacity to form meaningful connections improves with age.
It suggests that the emphasis on personal development gradually decreases while the sense of having a purpose in life only begins to fade after 40 to 50 years. These results add to the conversation about hedonic adaptability and socioemotional selectivity in the context of adult personality development.
A self-organizing map was created as the foundation of a recommendation engine for mental health applications in the second model. The quickest route for every individual to reach a cluster of mental stability is determined by this unsupervised learning approach, which separates all respondents into clusters depending on their probability of developing depression.
Existing mental health applications offer generic advice that applies to everyone yet fits no one. We have built a system that is scientifically sound and offers superior personalization.
Alex Zhavoronkov, Chief Longevity Officer, Deep Longevity
Deep Longevity has made the psychological exam mentioned in the original paper available to users of its free web service FuturSelf as a way of showcasing the system’s potential.
Users can join a guiding program that offers them a continual stream of recommendations made by AI after the evaluation, which results in a report with insights targeted at enhancing their long-term mental well-being. To improve Deep Longevity’s digital approach to mental health, data from FuturSelf will be utilized.
This study offers an interesting perspective on psychological age, future well-being, and risk of depression, and demonstrates a novel application of machine learning approaches to the issues of psychological health. It also broadens how we view aging and transitions through life stages and emotional states.
Vadim Gladyshev, Biogerontology Expert and Professor, Harvard Medical School
The authors plan to continue studying human psychology in the context of aging and long-term well-being. They are working on a follow-up study on the effect of happiness on physiological measures of aging.
Galkin, F., et al. (2022) Optimizing future well-being with artificial intelligence: self-organizing maps (SOMs) for the identification of islands of emotional stability. Aging. doi.org/10.18632/aging.204061.