The artificial intelligence developed by Harvard University determines the shortest path to human happiness

Deep Longevity, in collaboration with Harvard Medical School, offers a deep learning approach to mental health.

Deep Longevity published a paper in Aging-US outlining a machine learning approach to human psychology in collaboration with Nancy Etcoff, Ph.D., Harvard Medical School, Authority on happiness and beauty.

The authors created two numerical models of human psychology based on data from a US midlife study.

The first model is a set of deep neural networks which predict respondents’ chronological age and psychological well-being over 10 years using information from psychological surveys. This model depicts the trajectories of the human mind as it ages. It also shows that the ability to form meaningful connections, as well as mental autonomy and environmental mastery, develop with age. He also notes that the focus on personal progress is constantly decreasing, but the sense of having a purpose in life fades after only 40-50 years. These findings add to the growing body of knowledge about social and emotional selectivity and tasteful adaptation in the context of adult personality development.

The article describes an AI-based recommendation engine that can estimate an individual’s future psychological age and well-being based on a generated psychological survey. AI uses information from the respondent to put them on a 2D map of all possible psychological profiles and devise ways to improve their long-term well-being. This model of human psychology can be used in digital self-help applications and during therapist sessions. Credit: Michelle Keeler

The second model is a self-organizing map created to serve as the basis for a recommendation engine for mental health applications. This unsupervised learning algorithm divides all responders into groups depending on the likelihood of developing depression and identifies the shortest path toward a set of mental stability for any individual. Alex Zhavoronkov, Chief Sustainability Officer at Deep Longevity, explains, “Existing mental health apps offer general advice that applies to everyone yet doesn’t work for anyone. We’ve built a scientifically sound system that provides ultra-customization.”

To demonstrate the capabilities of this system, Deep Longevity has released the FuturSelf web service, a free online application that allows users to take the psychological test described in the original post. At the end of the assessment, users receive a report with insights aimed at improving their mental health in the long term and can enroll in a mentoring program that provides them with a steady flow of recommendations chosen by the AI. The data obtained from FuturSelf will be used to further develop Deep Longevity’s digital approach to mental health.

FuturSelf is a free online mental health service that provides guidance based on a psychological profile assessment by artificial intelligence. The core of FuturSelf is represented by a self-organizing map that ranks respondents and identifies the most appropriate ways to improve an individual’s well-being. Credit: Fedor Galkin

Leading bioscientist, Professor Vadim Gladyshev of Harvard Medical School, comments on the potential of FuturSelf:

“This study provides an intriguing perspective on psychological age, future well-being, and depression risk, and demonstrates new application of machine learning approaches to mental health issues. It also broadens our view of aging and shifts across life stages and emotional states.”

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.

The study was funded by the National Institute on Aging.

Reference: “Improving Future Well-Being Using Artificial Intelligence: Self-Organizing Maps (SOMs) to Identify Islands of Emotional Stability” By Fedor Galkin, Kirill Kochetov, Michael Keeler, Alex Zavoronkov, and Nancy Etkoff, June 20, 2022, Aging United States.
DOI: 10.18632 / age.204061