Development And Validation Of A Novel Prognosis Prediction Model For Patients With Myelodysplastic Syndrome

Background: To explore the role of gene mutations in the prognosis of patients with myelodysplastic syndrome,and develop a practical prognostic model of myelodysplastic syndrome containing mutations.Methods:1.The MDS patients in the public cohort are from the GEO database.In the external validation cohort,the MDS patients who visited the First Hospital of Lanzhou University from June 2015 to June 2022 were included in the present study.2.Through performing univariate,multivariate Cox and Lasso regression analysis by using R software,the significant factors affecting the prognosis were investigated in the basic information,blood examination,chromosome karyotype and gene mutation of MDS patients.Meanwhile,a dynamic nomogram containing multiple risk factors was created on the Shinyapps website.3.Time-dependent receiver operating characteristic(ROC)curve,calibration curve and decision curve analysis(DCA)were used to evaluate the discrimination ability,accuracy and clinical benefit of the model.4.In MDS patients of various genders and ages,the Kaplan-Meier method was utilized to risk stratification and the applicability of the prognostic model.Results:1.Present study included 201 MDS patients from the public data and 115 MDS patients from our hospital.2.Univariate/multivariate Cox and Lasso regression analysis showed that age,percentage of bone marrow blasts,ETV6,TP53,EZH2 and ASXL1 mutation status were considered as independent factors for the prognosis of MDS patients.3.Present study uses the above six factors to construct a nomogram for predicting the 1-year,3-year and 5-year survival rates of MDS patients.Meanwhile,a dynamic nomogram containing the above risk factors was established on the Shinyapp website.4.ROC curve and AUC value show that the nomogram has a good distinguishing ability.The calibration curve and DCA show that the model has good accuracy and clinical practicability.5.The risk stratification results showed that regardless of age and gender,the survival outcome of MDS patients with high risk was worse than those of patients with low risk.Conclusion: Present study developed a dynamic nomogram containing six risk factors,which can provide an objective and effective prediction for the prognosis of MDS patients.