Research on Cognitive Function among Older Adults Based on Machine Learning


Research on Cognitive Function among Older Adults Based on Machine Learning

Chang Chunyi, Wang Jingyi

Chang Chunyi, Wang Jingyi "Research on Cognitive Function among Older Adults Based on Machine Learning" Published in International Journal of Trend in Research and Development (IJTRD), ISSN: 2394-9333, Volume-13 | Issue-2 , April 2026, URL: http://www.ijtrd.com/papers/IJTRD29230.pdf

With the continuous acceleration of population aging, the size of the population aged 60 and above in China has continued to expand by the end of 2024, and the proportion of elderly people has been steadily increasing. In this context, cognitive decline has gradually become an important factor affecting the quality of life and social participation of older adults, while also imposing long-term pressure on family caregiving systems and the allocation of social medical resources. Therefore, systematically identifying the influencing factors of cognitive function among middle-aged and older adults, revealing their mechanisms of action, and improving risk identification capabilities are of great significance for actively responding to population aging and promoting healthy aging.Secondly, in terms of cognitive impairment risk prediction, all machine learning models demonstrate satisfactory classification performance. Compared with traditional models such as logistic regression and support vector machines, ensemble learning methods including random forest, XGBoost, and LightGBM show overall superior performance in terms of recall and discriminative ability. By integrating the prediction results of multiple base learners, the Stacking ensemble model further improves recall while maintaining a stable AUC, achieving a more balanced overall performance. These results indicate that the multi-model ensemble strategy can enhance the screening effectiveness for high-risk populations while balancing risk identification capability and model stability.

Older Adults; Cognitive Function; Machine Learning


Volume-13 | Issue-2 , April 2026

2394-9333

IJTRD29230