This study focuses on the early identification and precision prevention of acute kidney injury (AKI) following interventional therapy in patients with liver cancer. A prospective, phased mixed-methods research design will be adopted. In the first phase, a prospective cohort study will be conducted to systematically collect clinical and nursing-related data. A Super Learner ensemble algorithm will be employed to develop and validate an AKI risk prediction model, enabling precise risk stratification of patients. In the second phase, a prospective randomized controlled trial will be implemented. Guided by the Health Belief Model (HBM), a risk-stratified proactive nursing intervention will be delivered, and its effectiveness will be compared with that of routine nursing care in reducing the incidence of AKI, improving adherence to hydration protocols, optimizing the management of nephrotoxic medications, and enhancing patients' self-management capabilities. By integrating intelligent risk prediction with proactive nursing intervention strategies, this study aims to establish a reproducible and scalable precision prevention and management model for AKI in liver cancer patients undergoing interventional therapy. The findings are expected to provide scientific evidence for early AKI warning and proactive nursing practice, thereby promoting the precision, intelligence, and standardization of oncologic interventional nursing care.
Completed eligibility screening in Phase I of the study
Completed AKI risk assessment using the established prediction model
Classified by the model as at risk for AKI (moderate- or high-risk patients prioritized; low-risk patients included only for exploratory/observational analysis)
Conscious and able to communicate effectively
Development of AKI within 24 hours after interventional therapy according to KDIGO criteria
Severe psychiatric disorders, cognitive impairment, or communication barriers preventing participation in HBM-based assessment or intervention
Requirement for postoperative ICU admission and continuous life-support therapy
Mandatory use of nephrotoxic medications that cannot be discontinued, substituted, or adjusted during the study period
Single group
Risk-stratified active nursing intervention group
BehavioralThe intervention employed in this study is a proactive nursing intervention package based on AKI risk stratification and the Health Belief Model (HBM). Prior to interventional therapy, participants are assessed using the AKI risk prediction model and categorized into low-, moderate-, and high-risk groups. Stratified and weighted interventions are then implemented according to the assigned risk level. The intervention is delivered at five critical time points: one day before the procedure, postoperative day 1, postoperative day 2, postoperative day 3, and after hospital discharge. Intervention strategies are designed around the six core constructs of the Health Belief Model, including perceived susceptibility, perceived severity, perceived benefits, perceived barriers, cues to action, and self-efficacy. Specific measures encompass medication management, fluid therapy, renal function monitoring, patient and family education, behavioral support, and follow-up management
Standard care (usual post-interventional nursing care)
BehavioralStandard care (usual post-interventional nursing care)
Postoperative acute kidney injury incidence
The primary outcome was the occurrence of postoperative acute kidney injury (AKI). AKI was assessed within the first 7 days following interventional therapy and defined according to the Kidney Disease: Improving Global Outcomes (KDIGO) guidelines as the presence of any of the following: (1) an increase in serum creatinine of ≥0.3 mg/dL (≥26.5 μmol/L) within 48 hours; (2) an increase in serum creatinine to ≥1.5 times the baseline level, known or presumed to have occurred within the prior 7 days; or (3) a urine output of \<0.5 mL/kg/h for at least 6 hours.
Click on the lead sponsor to view all of their trials.
This trial is not recruiting at the moment. You can still explore other options:
