Capturing Built Environment and Automated External Defibrillator Resource Interplay in Tianjin Downtown

Automated external defibrillator resources (AEDRs) are the crux of out-of-hospital cardiac arrest (OHCA) responses, enhancing safe and sustainable urban environments. However, existing studies failed to consider the nexus between built environment (BE) features and AEDRs. Can explainable machine-learning (ML) methods reveal the BE-AEDR nexus? This study applied an Optuna-based extreme gradient boosting (OP_XGBoost) decision tree model with SHapely Additive exPlanations (SHAP) and partial dependence plots (PDPs) aiming to scrutinize the spatial effects, relative importance, and non-linear impact of BE features on AEDR intensity across grid and block urban patterns in Tianjin Downtown, China. The results indicated, that (1) marginally, the AEDR intensity was most influenced by the service coverage (SC) at grid scale and nearby public service facility density (NPSF_D) at block scale, while synergistically, it was shaped by comprehensive accessibility and land-use interactions with the prioritized block pattern; (2) block-level granularity and (3) non-linear interdependencies between BE features and AEDR intensity existed as game-changers. The findings suggested an effective and generalizable approach to capture the complex interplay of the BE-AEDR and boost the AED deployment by setting health at the heart of the urban development framework.