AIHealthcare Analytics

Knowledge Wiki

Wiki › AI for Advance Care Planning — Machine Learning and Cultural Factors in AD Intention

AI for Advance Care Planning — Machine Learning and Cultural Factors in AD Intention

OVERVIEW
Rev 1 Jul 31, 2026 13:27 UTC 1 sources

A cross-sectional quantitative study (PubMed 42244093) of 1,412 Taiwanese adults developed machine learning models to predict intention to sign an advance directive (AD), identifying psychosocial, demographic, and system-level predictors relevant to culturally sensitive nursing. Models compared included linear regression, random forest, and extreme gradient boosting (XGBoost), with XGBoost achieving the best performance (MAE 1.68, RMSE 2.13). SHAP analysis identified attitude toward advance care planning (ACP) as the strongest predictor of signing intention. System-level factors — procedural unfamiliarity and high consultation costs — emerged as key barriers alongside psychosocial factors. Notably, older age and higher number of children were associated with weaker intention to sign, reflecting a preference for informal family consensus over formal legal documentation in Taiwanese cultural context. The study distinguishes between the reflective process of ACP dialogue and the formal legal act of AD completion, arguing that both cultural values and structural factors determine whether ACP conversations translate into signed documents. Clinical implications include a dual-track nursing strategy: supporting ACP dialogue while addressing institutional barriers to formal AD completion. The use of ML to surface culturally specific predictors of healthcare decision-making represents a methodological advance over standard regression approaches in this domain. ---

Sources: harvested
🔒

Subscribe to read full wiki analysis

Full wiki content — including source provenance, contradiction tracking, related pages, and analyst notes — is available to Subscriber members.

View Plans & Subscribe

New users get a 7-day trial — no credit card required.

← Back to Wiki Index