Publication date: May 21, 2025
While genetic predisposition remains the strongest predictor, modifiable conditions like hypertension and type 2 diabetes also play a clear causal role. Using the UK Biobanks extensive dataincluding genetics, comorbidities, and lifestyle factorsresearchers built machine learning models to predict PDD risk. They paired this with explainable AI tools and Bayesian networks to understand how different risk factors interact. Demographic factors (age, sex) and comorbidities (depression, hypertension) followed closely. The UK Biobank offered cross-sectional data from over 500,000 participants, capturing everything from genetic profiles to lifestyle habits. Predicting dementia in people with Parkinsons disease. Predictive performance was measured using area under the curve (AUC), while SHAP values highlighted the most influential predictors.
| Concepts | Keywords |
|---|---|
| Biobank | Biobank |
| Diabetes | Causal |
| Pesticide | Conditions |
| Stage | Dementia |
| Diabetes | |
| Factors | |
| Genetic | |
| Hypertension | |
| Learning | |
| Mendelian | |
| Parkinsons | |
| Pdd | |
| Ppmi | |
| Predictive | |
| Risk |
Semantics
| Type | Source | Name |
|---|---|---|
| disease | MESH | Dementia |
| disease | MESH | hypertension |
| drug | DRUGBANK | Dextrose unspecified form |
| disease | MESH | chronic conditions |
| disease | MESH | lifestyle |
| disease | MESH | cognitive impairment |
| disease | MESH | causality |
| disease | MESH | type 2 diabetes |
| disease | MESH | polygenic risk score |
| disease | MESH | depression |
| disease | MESH | obesity |
| drug | DRUGBANK | Coenzyme M |