Machine Learning Predicts Healthy Ageing in Community-Dwelling Adults

Strategic Insights -

Research from the University of Waterloo has made new findings on machine learning, shedding light on the determinants of healthy ageing in middle-aged and older adults. The study used a retrospective cohort design to analyze the characteristics of 6332 participants aged 50 or older from the English Longitudinal Study of Ageing. The researchers developed machine learning models to predict healthy ageing based on sociodemographic, health, lifestyle, and psychosocial characteristics.

Key Takeaways:

  • The study found that 27.9% of participants aged 50 or older were ageing healthily after 4 years, with normal physical performance, greater household wealth, chronological age, and self-perceived age between 50 and 59 years positively contributing to the outcome.
  • The machine learning model based on the random forest algorithm achieved the best performance on the test data set (area under the curve = 0.78, 95% CI 0.76-0.80).
  • Physical inactivity, abdominal obesity, and not using the internet or email at baseline negatively affected the outcome of healthy ageing.
  • The study suggests that machine learning models can help predict healthy ageing based on the characteristics of community-dwelling middle-aged and older adults.
  • The research concluded that the available evidence can provide the basis for health strategies to promote active aging.
  • The study included participants aged 50 or older from the English Longitudinal Study of Ageing, a cohort study that has been ongoing since 2002.
  • The researchers used decision tree, logistic regression, neural network, and random forest algorithms to develop machine learning models and applied the SHapley Additive exPlanations algorithm to determine the contribution of each predictor to the outcome.
  • The study highlights the importance of considering various factors, including sociodemographic, health, lifestyle, and psychosocial characteristics, in predicting healthy ageing among community-dwelling middle-aged and older adults.
  • The research identified potential predictors of healthy ageing, including normal physical performance, greater household wealth, chronological age, and self-perceived age between 50 and 59 years.

Statistics:

  • 6332 participants were included in the study, with a median age of 64 years.
  • 27.9% of participants were ageing healthily after 4 years.
  • The machine learning model based on the random forest algorithm achieved an area under the curve (AUC) of 0.78 (95% CI 0.76-0.80) on the test data set.
  • Physical inactivity affected 44.1% of participants, abdominal obesity affected 21.5%, and not using the internet or email affected 10.2% of participants.

Sources:

  • Development of Prediction Models for Healthy Ageing in Community-Dwelling Middle-Aged and Older Adults: A Longitudinal Study Using Machine Learning. Journal of the American Medical Directors Association, 2025;26(11):105843.
  • University of Waterloo. School of Public Health Sciences.
  • Journal of the American Medical Directors Association. Elsevier Science Inc, Ste 800, 230 Park Ave, New York, NY 10169, USA.
  • Elsevier. www.elsevier.com.
  • NewsRx. Research from University of Waterloo Yields New Findings on Machine Learning (Development of Prediction Models for Healthy Ageing in Community-Dwelling Middle-Aged and Older Adults: A Longitudinal Study Using Machine Learning). Journal of Engineering. October 20, 2025; p 3140.