Objective To differentiate diagnose hypocellular myelodysplastic syndrome(hypo-MDS)and aplas-tic anemia(AA)based on machine learning models including Muti-Grained Cascade Forest(gcForest),Broad Learning System(BLS),and Gradient Boosting Decision Tree(GBDT).Methods The basic information,medical history and clinical examination data of hypo-MDS patients and AA patients who were first diagnosed in hematology department of North China University of Science and Technology Affiliated Hospital from Jan-uary 1,2008 to December 31,2022 were retrospectively collected.The final input variables were determined based on result of factor analysis,literature review results and clinical experts'opinions.The research sub-jects were randomly divided into 70％of training samples and 30％of verification samples.The differential diagnosis models of gcForest,BLS,GBDT for hypo-MDS and A A were established,respectively.The per-formance of each model is compared by sensitivity,specificity,ROC curve,AUC,Brier score,calibration curve and DCA curve,and the optimal discriminant classification model is selected.Results Nine indicators including age,red blood cell count,hemoglobin content,neutrophils,promyelocytes,medium-sized,late-sized erythrocytes,mature lymphocytes and mature plasma cells were identified as the input variables of the model based on result of factor analysis,literature review results and clinical experts'opinions.For the valida-tion set,the accuracy rates of gcForest,BLS,and GBDT differential diagnosis models were 76.74％,79.07％and 83.92％.The sensitivities were 62.16％,72.92％and 87.69％.The specificities were 87.76％,86.84％and 80.77％.Brier scores were 0.147,0.143 and 0.119.AUC values were 0.767(95％CI:0.731～0.805),0.785(95％CI:0.739～0.834)and 0.834(95％CI:0.808～0.861).As for AUC,the value of GBDT model was higher than that of gcForest model(P＜0.05).The calibration curve of GBDT model was closer to the diagonal than the other two models,and the area under clinical decision curve was the lar-gest.Conclusion Among those three models,GBDT model was the best one for the differentiation and diag-nosis of hypo-MDS and AA.
维普
万方数据
