Objective To develop and assess a machine learning model using the Shapley additive explanations(SHAP)method to predict fracture risk in multiple myeloma(MM)patients.Methods A retrospective study analyzed 181 MM patients in Zhejiang University Medical School Affiliated First Hospital from June 2021 to June 2024.Data included patient information,lab tests,medical history,and disease staging.Univariate analysis and recursive feature elimination(RFE)were employed for the purpose of variable selection.Predictive models were developed utilizing extreme gradient boosting(XGBoost),random forest(RF),light gradient boosting machine(LightGBM),and Logistic regression(LR).The performance of these models was evaluated through 5-fold cross-validation,and SHAP values were utilized to assess variable contributions in the optimal model.Results A total of 181 MM patients were included,with 50 in fracture group and 131 in non fracture group.RFE identified five key variables,notably including ferritin and B-type natriuretic peptide.The area under receiver operating characteristic curve values for the XGBoost,RF,LightGBM,and LR models were 0.861,0.846,0.755,and 0.780,respectively,with XGBoost demonstrating superior performance.SHAP analysis revealed that B-type natriuretic peptide was the most influential variable in the XGBoost model.Conclusion The XGBoost model demonstrates efficacy in predicting fracture risk among MM patients,with SHAP values enhancing its interpretability.

Objective To develop and assess a machine learning model using the Shapley additive explanations(SHAP)method to predict fracture risk in multiple myeloma(MM)patients.Methods A retrospective study analyzed 181 MM patients in Zhejiang University Medical School Affiliated First Hospital from June 2021 to June 2024.Data included patient information,lab tests,medical history,and disease staging.Univariate analysis and recursive feature elimination(RFE)were employed for the purpose of variable selection.Predictive models were developed utilizing extreme gradient boosting(XGBoost),random forest(RF),light gradient boosting machine(LightGBM),and Logistic regression(LR).The performance of these models was evaluated through 5-fold cross-validation,and SHAP values were utilized to assess variable contributions in the optimal model.Results A total of 181 MM patients were included,with 50 in fracture group and 131 in non fracture group.RFE identified five key variables,notably including ferritin and B-type natriuretic peptide.The area under receiver operating characteristic curve values for the XGBoost,RF,LightGBM,and LR models were 0.861,0.846,0.755,and 0.780,respectively,with XGBoost demonstrating superior performance.SHAP analysis revealed that B-type natriuretic peptide was the most influential variable in the XGBoost model.Conclusion The XGBoost model demonstrates efficacy in predicting fracture risk among MM patients,with SHAP values enhancing its interpretability.

Objective:To investigate the application value of white noise therapy on the alleviation of procedural pain of colostomy newborns.Methods:By a prospective, randomized and controlled trial, a total of 88 colostomy newborns in Hunan Children′s Hospital from January 2018 to January 2020 divided into experimental group (44 cases) and control group (44 cases) according to the random number table method. The control group received routine nursing; based on thesis, the experimental group played white noise intervention therapy on the basis of routine nursing. The intervention effect was assessed byNeonatal Infant Acute Pain Assessment Scale (NIAPAS), the first crying time and the duration of first crying, the first painful face and the duration of first painful face as well as heart rate and blood oxygen saturation.Results:The first crying time and the duration of first crying, the first painful face and the duration of first painful face were (28.05 ± 7.39) s, (46.18 ± 13.29) s, (32.89 ± 6.79) s, (52.75 ± 10.71) s in the experimental group, significantly shorter than in the control group (35.79 ± 5.81) s, (35.79 ± 5.81) s, (38.64 ± 10.53) s, (59.79 ± 13.52) s, the difference was statistically significant ( t values were 2.71-5.47, all P<0.05). During and after the procedure, the scores of NIAPAS were (6.32 ± 1.62) points, (4.18 ± 1.06) points in the experimental group, significantly lower than that in the control group (7.43 ± 1.78) points, (4.79 ± 1.34) points ( t=3.06, 2.38, both P<0.05); the heart rate were (152.82 ± 13.25) times/min and (147.84 ± 12.37) times/min in the experimental group, significantly lower than in the control group (166.11 ± 13.79) times/min and (155.77 ± 12.84) times/min ( t=4.61, 2.95, both P<0.05); the blood oxygen saturation were 0.979 8 ± 0.009 5 and 0.980 9 ± 0.012 4 in the experimental group, significantly higher than in the control group 0.969 1 ± 0.014 9, 0.972 3 ± 0.017 8, the difference was statistically significant ( t=4.01, 2.65, both P<0.05). Conclusions:White noise therapy can effectively alleviate procedural pain and stabilizing vital signs of colostomy newborns.