Objective To develop a machine learning-based risk prediction model for postoperative acute kidney injury(AKI)and a model for mortality in obese patients admitted to intensive care unit(ICU)in order to improve early warning and prognostic evaluation to support clinical decision-making.Methods Data of obese postoperative ICU patients were retrospectively retrieved from the MIMIC-Ⅳ and eICU databases for statistical analysis.Ultimately,2 520 patients(670 from MIMIC-Ⅳ and 1 850 from eICU databases)were included to build the risk prediction models for AKI and mortality.The data included demographic information,vital signs,laboratory findings,surgical types,comorbidities,and medication use.After data cleaning and preprocessing,Boruta feature selection was applied,followed by the construction of prediction models using 7 machine learning algorithms,that is,Gradient Boosting Machine(GBM),Generalized Linear Model(GLM),k-Nearest Neighbors(KNN),Na?ve Bayes(NB),Neural Network(NNET),Support Vector Machine(SVM),and XGBoost.Model performance was evaluated through cross-validation and external validation.Results In the risk prediction models of AKI,the SVM model achieved the highest AUC value of 0.80 in the testing set and 0.71 in the external validation test.For the risk prediction models of mortality,the GBM model outperformed others in the prediction,attaining an AUC value of 0.91 in the testing set.Conclusion Risk predictive models for postoperative AKI and mortality in obese ICU patients are successfully constructed,and are valuable tools for clinicians to optimize early intervention and improve clinical outcomes for the patients.

Objective:To investigate the clinical effects of pelvic radiotherapy on improving the patient′s position variability by using stretching exercises before radiotherapy.Methods:The study period was from January 2017 to May 2019. The study subjects were patients with pelvic malignancies who visited Zhejiang Cancer Hospital during this period and needed radiotherapy. A total of 278 patients were divided into study group and control group according to the random number table method, with 139 cases in each group. The study group performed hip joint stretching and rotation exercises before radiotherapy, while the control group had no special intervention. By comparing the changes in the sacral slope angle (SSA) of the patients between the two groups, the position variability during radiotherapy was reflected. The effects of complications, compliance, and degree of benefit were analyzed.Results:The daily compliance of the study group was above 95%. No patients reported adverse events such as dyskinesias and related pain and falls. The SSA change in the study group patients was significantly reduced ( P<0.05). The daily SSA and baseline SCT in the study group were significantly lower ( P<0.05). The average change in the study group was (0.95 ± 0.24)°(0.52°-1.33°), while the average change in the control group was (2.31 ± 1.05)°(1.17°-5.26°),and there was significant difference ( P<0.05). The comparison of the average differences between the treatment days showed that the average change in the study group was (0.96 ± 0.64)°(0.72°-1.28°)and in the control group was (2.09 ± 1.12)°(0.94°-3.28°),and there was significant difference ( P<0.05). Pearson correlation analysis was used to evaluate its correlation to the overall change of each patient. The reliability between the two assessors showed moderately positive correlation ( r=0.52, P=0.18), and there was also a moderately positive correlation in the control group ( r=0.59, P=0.26). The patients in the study group scored (7.12 ± 0.16) scores on the degree of benefit of participating in the study group. Conclusions:The stretching exercise before radiotherapy can effectively reduce the position variability of patients with pelvic radiotherapy, which is beneficial to improve the effect of diagnosis and treatment.