by Developing machine learning programs that can predict the future mental and physical health of aging Canadians is the focus of a cross-disciplinary research team from the University of Alberta. The team, led by Bo Cao, associate professor of psychiatry and Canada Research Chair in Computational Psychiatry, is utilizing health-related, lifestyle, socio-economic, and other data to create machine learning models that can assist healthcare teams in providing personalized care and promoting healthy aging.
Machine learning is an effective computational method for utilizing rich, de-identified data, according to Cao. To advance individualized patient prediction for specific health outcomes, machine learning techniques must be leveraged.
The team used machine learning in two recent studies to identify patterns and analyze data from the Canadian Longitudinal Study on Aging (CLSA), involving over 30,000 Canadians between the ages of 45 and 85 who will be followed for up to 25 years.
In their first study, published in the journal Gerontology, the team developed a biological age index by applying machine learning models to blood test data from the CLSA. This index determines the physiological age of an individual compared to their chronological age. The researchers found a positive association between a higher biological age and chronic illness, frequent consumption of processed and red meat, smoking, and passive exposure to smoke. Conversely, a negative association was found between a younger biological age and the consumption of fruits, legumes, and vegetables.
Understanding these associations and identifying risk factors for differential aging could lead to effective public health recommendations for promoting healthy longevity, as reported by the team in their paper.
In their second study, published in the Journal of Affective Disorders, the team developed a program that accurately predicted individuals who would experience depression onset within three years. The machine learning model was trained using records of individuals who were eventually diagnosed with depression. The most important predictors for depression onset were identified as existing subthreshold depression symptoms, emotional instability, low levels of life satisfaction, perceived health and social support, and nutrition risk.
The model achieved about 70% accuracy in predicting the development of depression within three years at the individual level, even when subthreshold depression symptoms were excluded.
Cao emphasizes that both the mental health machine learning model and the BioAge model are not yet refined enough for real-world implementation, but the goal is to involve clinicians, patients, and individuals with lived experience, in order to demonstrate the benefits of these models for the general public. Further research and testing are planned to advance this conversation and refine the models for practical use.
Note:
Source: Coherent Market Insights, Public sources, Desk research
We have leveraged AI tools to mine information and compile it
Money Singh is a seasoned content writer with over four years of experience in the market research sector. Her expertise spans various industries, including food and beverages, biotechnology, chemicals and materials, defense and aerospace, consumer goods, etc.
