Machine learning revolutionizes mental health assessment

UNITED KINGDOM – A groundbreaking study published in the journal GigaScience has found that Artificial Intelligence (AI) can perform high-quality mental health assessments, potentially improving the future of diagnostics for mental health disorders.

The study, led by Denis Engemann of Inria, revealed that machine learning from large population cohorts can produce “proxy measures” for brain-related conditions without requiring a specialist’s mental health assessment.

For their study, the researchers used the UK Biobank, one of the most comprehensive and large biomedical databases on the planet, which contains extensive and health-related data on the UK population.

Mental health issues have been steadily increasing around the world, with the World Health Organization (WHO) estimating that between 2007 and 2017, mental health conditions and substance abuse disorders increased by 13 percent.

The ramifications are significant, affecting society in nearly every aspect of life, including school, work, family, friends, and community involvement.

One of the most critical issues in accurately and efficiently addressing these disorders is that a traditional mental health assessment necessitates the presence of an expert in the field, which is problematic given the small proportion of them in the world in comparison to mental health sufferers.

Now, the development of an AI-powered mental health assessment aims to provide a simple method of detecting, preventing, and treating such health issues.

The Inria team and their colleagues used data from the UK biobank to create their AI models, which includes questionnaire data about personal circumstances and habits such as age, education, tobacco and alcohol use, sleep duration, and physical exercise, in addition to biological and medical datasets.

For this study, the questionnaires also included sociodemographic and behavioral data, such as the individual’s moods and sentiments; the biological data also included Magnetic Resonance (MR) images of 10,000 participants’ brain scans.

The team combined the data sources to create models that approximate brain age and then scientifically defined intelligence and neuroticism traits.

They serve as “proxy measures,” which are indirect measurements that have a strong correlation with specific mental health conditions or outcomes that cannot be measured directly.

This method of generating approximations has previously been used successfully to predict brain age from MR images.

The researchers validated their proxy measures by showing the same results in a different subset of UK Biobank data.

Engemann commented that they generalize the methodology in two ways: “First, we demonstrated that, beyond biological ageing, the same proxy measure framework is applicable to constructs more directly related to mental health. Second, we showed that useful proxy measures can be derived from other inputs than brain images, such as sociodemographic and behavioral data.”

The study’s findings indicate that AI and specialists can collaborate to provide an accurate and personalized mental health assessment.

Although human interaction is still an important part of a mental health assessment, a person could allow a machine learning model to securely access their social media account in order to obtain proxy measures that can be useful to both the client and their mental health professional.

Would you like to get regular updates of such news articles? Subscribe to our HealthCare Africa News, email newsletters, which provide the latest news insights from Africa and the World’s health, pharma and biotech industry. SUBSCRIBE HERE

Related posts

Leave a Comment

This site uses Akismet to reduce spam. Learn how your comment data is processed.