Polygenic and polysocial risk scores in post-type 2 diabetes dementia: Risk stratification and predictive modeling in the UK Biobank cohort - PubMed
6 hours ago
- #dementia risk
- #social determinants
- #machine learning
- Dementia is a common complication of type 2 diabetes mellitus (T2DM), influenced by genetic susceptibility and social disadvantages.
- The study investigated the independent and joint effects of polygenic risk scores (PRS) and polysocial risk scores (PsRS) on post-T2DM dementia risk using UK Biobank data.
- Among 5,624 T2DM participants, those with the highest PsRS had a significantly elevated all-cause dementia risk (HR = 2.738; 95% CI: 1.556-4.818, p < 0.001).
- In genetically susceptible individuals, machine learning models (e.g., XGBoost) predicted dementia risk effectively, with employment status and educational level identified as key social contributors via SHAP interpretation.
- The findings emphasize addressing modifiable social factors in dementia prevention for high-genetic-risk populations.