OBJECTIVE To establish a risk prediction model for antibiotic-associated diarrhea(AAD)in intensive care unit(ICU)patients receiving mechanical ventilation so as to provide bases for early identification of high-risk population and formulation of corresponding individualized prevention strategies.METHODS A total of 1016 pa-tients who received mechanical ventilation and were treated with antibiotics in the ICU of The First Medical Center of Chinese PLA General Hospital from Jan.1,2020 to Jun.30,2022 were retrospectively enrolled in the study and were divided into the AAD group with 200 cases and the non-AA group according to the diagnostic criteria for AAD.Multivariate logistic regression analysis was performed for risk factors for AAD in the ICU patients receiv-ing mechanical ventilation,and the nomogram prediction model was established with R software.The performance of the model was evaluated by means of receiver operating characteristic(ROC)curves and calibration curves.RESULTS Among the 1016 patients who underwent mechanical ventilation,200 had AAD,and the incidence rate of AAD was 19.69％.Multivariate logistic regression analysis showed that hemoglobulin[OR=0.990,95％CI(0.983 to 0.997)],C-reactive protein[OR=1.046,95％CI(1.009 to 1.085)],serum phosphorus[OR=0.498,95％CI(0.328 to 0.755)],serum lipase[OR=1.001,95％CI(1.000 to 1.002)],ceftriaxo ne sodium[OR=2.331,95％CI(1.253 to 4.334)],linezolid[OR=2.387,95％CI(1.329 to 4.289)],fluconazole[OR=2.083,95％CI(1.238 to 3.505)]and sedatives[OR=0.307,95％CI(0.160 to 0.590)]were the risk factors for the AAD in the ICU patients receiving mechanical ventilation.The area under ROC curve(AUC)of the predic-tion model established based on the risk factors was 0.705 for the training set,0.751 for the validation set.Hos-mer-Lemeshow test indicated that the predicated probability of the model was consistent with the actual risk for the occurrence(x2=6.057,5.304,P=0.641,0.725).CONCLUSION The nomogram model that is established based on the above influencing factors can quantitatively predict the risk for AAD in the ICU patients undergo-ing mechanical ventilation,and it has certain clinical predictive efficiency.

OBJECTIVE To establish a risk prediction model for antibiotic-associated diarrhea(AAD)in intensive care unit(ICU)patients receiving mechanical ventilation so as to provide bases for early identification of high-risk population and formulation of corresponding individualized prevention strategies.METHODS A total of 1016 pa-tients who received mechanical ventilation and were treated with antibiotics in the ICU of The First Medical Center of Chinese PLA General Hospital from Jan.1,2020 to Jun.30,2022 were retrospectively enrolled in the study and were divided into the AAD group with 200 cases and the non-AA group according to the diagnostic criteria for AAD.Multivariate logistic regression analysis was performed for risk factors for AAD in the ICU patients receiv-ing mechanical ventilation,and the nomogram prediction model was established with R software.The performance of the model was evaluated by means of receiver operating characteristic(ROC)curves and calibration curves.RESULTS Among the 1016 patients who underwent mechanical ventilation,200 had AAD,and the incidence rate of AAD was 19.69％.Multivariate logistic regression analysis showed that hemoglobulin[OR=0.990,95％CI(0.983 to 0.997)],C-reactive protein[OR=1.046,95％CI(1.009 to 1.085)],serum phosphorus[OR=0.498,95％CI(0.328 to 0.755)],serum lipase[OR=1.001,95％CI(1.000 to 1.002)],ceftriaxo ne sodium[OR=2.331,95％CI(1.253 to 4.334)],linezolid[OR=2.387,95％CI(1.329 to 4.289)],fluconazole[OR=2.083,95％CI(1.238 to 3.505)]and sedatives[OR=0.307,95％CI(0.160 to 0.590)]were the risk factors for the AAD in the ICU patients receiving mechanical ventilation.The area under ROC curve(AUC)of the predic-tion model established based on the risk factors was 0.705 for the training set,0.751 for the validation set.Hos-mer-Lemeshow test indicated that the predicated probability of the model was consistent with the actual risk for the occurrence(x2=6.057,5.304,P=0.641,0.725).CONCLUSION The nomogram model that is established based on the above influencing factors can quantitatively predict the risk for AAD in the ICU patients undergo-ing mechanical ventilation,and it has certain clinical predictive efficiency.