Objective:To construct a nomogram model for predicting the occurrence of acute kidney injury (AKI) in patients with cardiac arrest (CA) after cardiopulmonary resuscitation (CPR), and to verify its validity for early prediction.Methods:The study retrospectively included patients aged 18 years and older who received CPR for CA and were admitted to the emergency room of Tianjin Medical University General Hospital from February 2016 to September 2023. The general information, underlying diseases, resuscitation related indicators, and first laboratory test results of patients were collected. The patients were randomly divided into training and validation groups at a ratio of 7:3. AKI diagnosis was based on the diagnostic criteria of the Kidney Disease Improving Global Outcomes. Univariate and multivariate logistic regression models were used to identify independent risk factors for AKI in patients with cardiac arrest, and a nomogram was constructed on the basis of the independent risk factors. The predictive performance was evaluated by the area under the curve (AUC) of the receiver operating characteristic. The calibration curve, decision curve and clinical impact curve were used to evaluate the model. Bootstrap and cross validation methods were used for internal validation.Results:A total of 527 patients with cardiac arrest were included in the study, 230 patients developed AKI, with an AKI incidence of 43.6%. There was no statistically significant difference in clinical baseline data between the training and validation groups (all P>0.05), indicating comparability between the two groups of data. Multivariate logistic analysis revealed that age ( OR=1.346, 95% CI: 1.197-1.543, P<0.001), CA to CPR time ( OR=2.214, 95% CI: 1.512-3.409, P=0.016), adrenaline dosage ( OR=1.921, 95% CI: 1.383-2.783, P=0.004), APACHE-Ⅱ score ( OR=1.531, 95% CI: 1.316-1.820, P<0.001), baseline creatinine ( OR=1.137, 95% CI: 1.090-1.196, P<0.001), and lactate ( OR=2.558, 95% CI: 1.680-4.167, P<0.001) were the independent risk factors for AKI in patients with cardiac arrest. Initial defibrillable rhythm ( OR=0.214, 95% CI: 0.051-0.759, P=0.023) was a protective factor for AKI in patients with cardiac arrest. A nomogram prediction model was constructed based on the above variables. The AUC of the training group was 0.943 (95% CI: 0.921-0.965) and that of the validation group was 0.917 (95% CI: 0.874-0.960). This prediction model demonstrated good discrimination, calibration and clinical applicability. Conclusions:A nomogram predictive model was constructed on the basis of age, CA to CPR time, initial defibrillable rhythm, adrenaline dosage, the APACHE-Ⅱ score, and baseline creatinine and lactate levels. This nomogram has good predictive value for the early occurrence of AKI in patients with cardiac arrest after cardiopulmonary resuscitation, which can provide new strategies for the early identification of AKI and precise intervention.

Objective:To construct an early prediction model for post cardiopulmonary resuscitation-acute kidney injury (PCPR-AKI) by machine learning and provide a basis for early identification of acute kidney injury (AKI) high-risk patients and accurate treatment.Methods:It was a single-center retrospective study. The clinical data of patients admitted to Tianjin Medical University General Hospital after cardiopulmonary resuscitation following cardiac arrest from January 1, 2016 to October 31, 2023 were collected. The end-point event of the study was defined as AKI occurring within 48 hours after cardiopulmonary resuscitation. The patients were divided into AKI group and non-AKI group according to the AKI diagnostic criteria, and the differences of baseline clinical data between the two groups were compared. The patients who met the inclusion criteria were randomly (using the train_test_split function, set the random seeds to 1, 2, and 3) divided into training and validation sets at a ratio of 7∶3. Random forest (RF), support vector machine, decision tree, extreme gradient boosting and light gradient boosting machine algorithm were used to develop the early prediction model of PCPR-AKI. The receiver-operating characteristic curve and decision curve analysis were used to evaluate the performance and clinical practicality of the predictive models, and the importance of variables in the optimal model was screened and ranked.Results:A total of 547 patients were enrolled, with age of 66 (59, 70) years old and 282 males (51.6%). There were 238 patients (43.5%) having incidence of AKI within 48 hours after cardiopulmonary resuscitation. In the AKI group, 182 patients (76.5%) were in stage 1, 47 patients (19.7%) were in stage 2, and 9 patients (3.8%) were in stage 3. There were statistically significant differences in the age, time to reach resuscitation of spontaneous circulation, time from cardiac arrest to starting cardiopulmonary resuscitation, proportion of initial defibrillation rhythm, proportion of electric defibrillation, proportion of mechanical ventilation, adrenaline dosage, sodium bicarbonate dosage, proportion of coronary heart disease, proportion of hypertension, proportion of diabetes, serum creatinine, blood urea nitrogen, blood lactic acid, blood potassium, brain natriuretic peptide, troponin, D-dimer, neuron specific enolase, and 24 hours urine volume after cardiopulmonary resuscitation between AKI group and non-AKI group (all P<0.05). Among the five machine learning algorithms, RF model achieved the best performance and clinical practicality, with area under the curve of 0.875, sensitivity of 0.863, specificity of 0.956, and accuracy rate of 90.7%. In the variable importance ranking of RF model, the top 10 variables were as follows: time to reach resuscitation of spontaneous circulation, time from cardiac arrest to starting cardiopulmonary resuscitation, initial defibrillable rhythm, serum creatinine, mechanical ventilation, blood lactate acid, adrenaline dosage, brain natriuretic peptide, D-dimer and age. Conclusions:An early predictive model for PCPR-AKI is successfully constructed based on machine learning. RF model has the best predictive performance. According to the importance of the variables, it can provide clinical strategies for early identification and precise intervention for PCPR-AKI.