Translational assessment of nursing care models for oncology patients with cardiovascular risk factors
Year: 2026
Type: article
Abstract: Introduction: The objective of this study was to estimate patient-specific effects of alternative acute nursing care strategies for critically ill oncology patients with cardiovascular risk factors using routinely collected electronic health record data. Existing nursing care evaluations primarily characterize population-level associations or predict observed outcomes, but they do not estimate the potential outcomes of individual patients under standard and enhanced acute care while accounting for evolving clinical states and predictive uncertainty. Methods: We developed the Counterfactual Event Planner to estimate individualized treatment effects and compare alternative nursing care strategies through clinically constrained trajectory modeling and probabilistic outcome estimation. The proposed framework integrates the Manifold Based Decision Model, Agent based Contextual Navigator, and Probabilistic Outcome Synthesizer to construct clinically meaningful latent representations, explore context-aware intervention trajectories, and estimate potential outcome distributions. Furthermore, Counterfactual Pacing Strategy and Bayesian Outcome Updating enable dynamic trajectory simulation and uncertainty-aware outcome refinement, improving the reliability of individualized treatment effect estimation. Results and discussion: Extensive experiments on the MIMIC-IV and eICU Collaborative Research Database demonstrate that the proposed framework consistently outperforms representative statistical, neural, and causal inference baselines in individualized treatment effect estimation, policy evaluation, and outcome prediction while maintaining robust cross-hospital generalization. The proposed framework provides an effective and generalizable solution for counterfactual evaluation of nursing care strategies, supporting personalized clinical decision making for oncology patients with cardiovascular risk factors.
Authors: Huili Du, Jing Wang, Yuguang Xing
Institution: Xinxiang Central Hospital
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $3,801
OpenAlex ID: W7222957977