Sex differences in cognitive function trajectories and influencing factors in older adults: A machine learning study based on CHARLS and HRS
Clinical Snapshot
PICO Framework
| P — Population | Older adults from China (CHARLS) and United States (HRS) longitudinal cohorts |
| I — Intervention | Various sociodemographic, health, and environmental factors identified through machine learning |
| C — Comparator | Sex differences (male vs female) and cross-national differences (China vs US) |
| O — Outcomes | Cognitive function trajectories over time, identified through Latent Class Growth Models |
Bottom Line
This cross-national study of cognitive ageing trajectories in Chinese and American older adults suggests education is the primary modifiable factor influencing cognitive decline, with sex-specific patterns where men are more influenced by social networks and women by family and community factors. While the machine learning approach and large longitudinal datasets are methodologically sound, the abstract lacks crucial statistical details including effect sizes and confidence intervals. The findings highlight important cultural and healthcare system differences in cognitive ageing determinants, but direct application to Australian practice requires caution given different healthcare structures and cultural contexts. The study supports developing targeted, culturally-sensitive interventions for cognitive health promotion, but Australian clinicians should await local validation studies before implementing specific recommendations. The emphasis on education as a key protective factor aligns with existing evidence and supports continued advocacy for lifelong learning programs in aged care.
Key Findings
P Value: Not reported
Effect Size: Not reported in abstract
Primary Outcome: Cognitive function trajectories identified through Latent Class Growth Models
Nnt Or Sensitivity: Education identified as top influencing factor across all groups
Confidence Interval: Not reported
Clinical Application
Findings could inform targeted interventions but require validation in Australian context Limited direct applicability given different healthcare system (Medicare vs US insurance), cultural context, and absence of Australian data. Would need validation through studies like HILDA or Australian Longitudinal Study on Ageing Older adults in developed countries with established healthcare systems
Abstract
BACKGROUND: Identify the influencing factors that respectively affect the differences in cognitive function trajectories between China and the United States, and explore the reasons for gender and transnational differences. METHODS: Five waves of data from the China Health and Retirement Longitudinal Study (CHARLS) and the Health and Retirement Study (HRS) were utilized, and Latent Class Growth Models (LCGMs) was employed to identify cognitive trajectories. The optimal machine learning (ML) model was adopted and the Boruta algorithm was used to screen the variables. The SHAP value is used to explain the ranking of feature importance. RESULTS: The XGBoost model performs best among the six ML models. Education was the top influencing factor across groups. Family factors mattered more in China, while U.S. medical and endowment insurance had stronger effects. Men were more affected by external social networks; women were influenced by family responsibilities and community environments. CONCLUSION: Differences were linked to public services, social roles, and traditional culture. These results support the development of tailored interventions targeting gender-specific and culture pathways at the individual, family, society and community levels, offering actionable insights for promoting cognitive health in aging populations globally.
References
- 1.Cao, R., Xu, X., Chen, H., Sun, H., & Yan, C. (2026). Sex differences in cognitive function trajectories and influencing factors in older adults: A machine learning study based on CHARLS and HRS. Journal of Affective Disorders, 121258. https://doi.org/10.1016/j.jad.2026.121258
Related Research
Sleep medicine
Concordance of wearable device sleep metrics with patient-reported sleep quality: A systematic review
3 Aug 2026
Sleep medicine reviews
Machine and deep learning in REM sleep behavior disorder: a scoping review and analysis of reporting quality
3 Aug 2026
Neurological sciences : official journal of the Italian Neurological Society and of the Italian Society of Clinical Neurophysiology
Efficacy and safety of fecal microbiota transplantation in Parkinson's disease: a systematic review and meta-analysis of randomized controlled trials with GRADE assessment
1 Aug 2026
This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service