Objective This study is aimed to investigate the prognostic significance of ring sideroblast ( RS) in MDS( Myelodysplastic Sydrome ) and evaluate the correlation of RS and other prognostic index.Methods A total of 198 patients with MDS between March 2009 and December 2015 in Chinese PLA′s Gerneral hospital were chosen for this study .Based on the ratio of RS in nucleated red blood cell , patients were first separated into myelodysplastic syndrome without ring sideroblast (MDS RS-) group, RS≥15%, and myelodysplastic syndrome with ring sideroblast ( MDS RS +) group, RS <15%. Then, according to the proportion of blasts in bone marrow nucleated cells above 5%or below, patients were further divided into myelodysplastic syndrome with low blasts without ring sideroblast ( MDS-LB RS-) group, myelodysplastic syndrome with low blasts and ring sideroblast ( MDS-LB RS+) group, refractory anemia with excess blast without ring sideroblast ( RAEB RS-) group and refractory anemia with excess blast and ring sideroblast ( RAEB RS+) groupe.All patients had completed the morphological , genetics , molecular biology examination at dignosis, and followed up by phone.The results of the overall survival (OS) analysis have been presented in a Kaplan-Meier curve and cox regression model .Last, according to the percentage of RS in nucleated red blood cell , patients were separated into RS <5%groupe, 5%-15%group, 15%-40%group, RS≥40%group, and analyse their survival prognosis by statistical methods .Results Comparing to MDS RS-group, the morbidity age, WBC and PLT count were significantly higher [61 ±1.91 vs 52 ±1.37, t=-3.555, P<0.01, 3.82(0.47-323)vs 2.6(0.6-59.7), z=-4.014, P<0.01;139.5(7-608) vs 60(3-724), z =-3.988, P<0.01], bone marrow eythroid hyperplasia and gigantocyte were more obvious in MDS RS+group[χ2 =11.032, P<0.01, χ2 =5.165, P<0.05]; the percentage of GATA1 gene and abnormal rate of poor prognosis gene ( MLL, NRAS, WT1 ) , either mutation or high gene expression , were higher in MDS-LB RS+group than that in MDS-LB RS-( P<0.05 ); Contrasting with RAEB RS-group, the karyotype is worse in RAEB RS +group[χ2 =4.966, P<0.05];Comparing to 15%-40%group, the OS were poorer in RS≥40%;MDS RS+patients were more prone to adverse prognosis than MDS RS-patients.Conclusion Compared to MDS RS-group, MDS RS +patients had worse prognosis;RS maybe correlate to morbidity age , eythroid dysplasia and gene abnormality in affecting the survival prognosis of MDS.

OBJECTIVE: To establish a machine learning model based on extreme gradient boosting (XGBoost) algorithm for early prediction of severe acute pancreatitis (SAP), and explore its predictive efficiency. METHODS: A retrospective cohort study was conducted. The patients with acute pancreatitis (AP) who admitted to the First Affiliated Hospital of Soochow University, the Second Affiliated Hospital of Soochow University and Changshu Hospital Affiliated to Soochow University from January 1, 2020 to December 31, 2021 were enrolled. Demography information, etiology, past history, and clinical indicators and imaging data within 48 hours of admission were collected according to the medical record system and image system, and the modified CT severity index (MCTSI), Ranson score, bedside index for severity in acute pancreatitis (BISAP) and acute pancreatitis risk score (SABP) were calculated. The data sets of the First Affiliated Hospital of Soochow University and Changshu Hospital Affiliated to Soochow University were randomly divided into training set and validation set according to 8 : 2. Based on XGBoost algorithm, the SAP prediction model was constructed on the basis of hyperparameter adjustment by 5-fold cross validation and loss function. The data set of the Second Affiliated Hospital of Soochow University was served as independent test set. The predictive efficacy of the XGBoost model was evaluated by drawing the receiver operator characteristic curve (ROC curve), and compared it with the traditional AP related severity score; variable importance ranking diagram and Shapley additive explanation (SHAP) diagram were drawn to visually explain the model. RESULTS: A total of 1 183 AP patients were enrolled finally, of which 129 (10.9%) developed SAP. Among the patients from the First Affiliated Hospital of Soochow University and Changshu Hospital Affiliated to Soochow University, there were 786 patients in the training set and 197 in the validation set; 200 patients from the Second Affiliated Hospital of Soochow University were used as the test set. Analysis of all three datasets showed that patients who advanced to SAP exhibited pathological manifestation such as abnormal respiratory function, coagulation function, liver and kidney function, and lipid metabolism. Based on the XGBoost algorithm, an SAP prediction model was constructed, and ROC curve analysis showed that the accuracy for prediction of SAP reached 0.830, the area under the ROC curve (AUC) was 0.927, which was significantly improved compared with the traditional scoring systems including MCTSI, Ranson, BISAP and SABP, the accuracy was 0.610, 0.690, 0.763, 0.625, and the AUC was 0.689, 0.631, 0.875, and 0.770, respectively. The feature importance analysis based on the XGBoost model showed that the top ten items ranked by the importance of model features were admission pleural effusion (0.119), albumin (Alb, 0.049), triglycerides (TG, 0.036), Ca²⁺ (0.034), prothrombin time (PT, 0.031), systemic inflammatory response syndrome (SIRS, 0.031), C-reactive protein (CRP, 0.031), platelet count (PLT, 0.030), lactate dehydrogenase (LDH, 0.029), and alkaline phosphatase (ALP, 0.028). The above indicators were of great significance for the XGBoost model to predict SAP. The SHAP contribution analysis based on the XGBoost model showed that the risk of SAP increased significantly when patients had pleural effusion and decreased Alb. CONCLUSIONS A SAP prediction scoring system was established based on the machine automatic learning XGBoost algorithm, which can predict the SAP risk of patients within 48 hours of admission with good accuracy.
Humans ; Pancreatitis ; Acute Disease ; Retrospective Studies ; Hospitalization ; Algorithms

BACKGROUNDThoracic endovascular aortic repair (TEVAR) is an emerging treatment modality, which has been rapidly embraced by clinicians treating thoracic aortic disease. However, the clinical manifestations of systemic inflammatory response after TEVAR as post-implantation syndrome (PIS) resemble the perioperative infection. This study aimed to evaluate changes and diagnostic value of procalcitonin (PCT) and other traditional inflammatory markers for infections after TEVAR.

METHODSWe conducted a prospective clinical study that enrolled 162 consecutive aortic dissection cases, who underwent TEVAR in our institution between July 2011 and November 2012. The PCT, C-response protein (CRP), erythrocyte sedimentation rate (ESR) and blood routine examination were monitored before the operation and on days 1, 2, 3 and 5 after the operation. The diagnosis of infection was confirmed by the infection control committee with reference to Hospital Acquired Infection Diagnostic Criteria Assessment, released by the Ministry of Health of the People's Republic of China.

RESULTSPost endovascular repair of thoracic aorta, PCT changes significantly at different time points (χ(2) = 13.225, P = 0.021), without significant difference between the PIS group and the control group (0.24 ± 0.04 vs.0.26 ± 0.10, P = 0.804). PCT values were significantly higher in the first day after TEVAR than the preoperative levels (0.18 ± 0.03 vs. 0.11 ± 0.02, P < 0.001). Compared with PIS patients, the level of PCT, CRP, White blood cell (WBC) and neutrophil (NEU) in the infection patients elevated significantly (relatively χ(2) = 6.062, P = 0.048; χ(2) = 6.081, P = 0.048; χ(2) = 11.030, P = 0.004; χ(2) = 14.632, P = 0.001). According to the ROC analysis, the PCT levels in the first day after TEVAR (AUC = 0.785, P = 0.012) had better predictive values of infection than WBC, NEU CRP and ESR (AUC = 0.720, P = 0.040; AUC = 0.715, P = 0.045; AUC = 0.663, P = 0.274; AUC = 0.502, P = 0.991). The best predictive index was the changes of PCT between preoperative and postoperative (PCT), which possess AUC as 0.803 (P = 0.014). And PCT = 0.055 could be considered as an infection diagnosis cutoff value with a sensitivity of 83.3% and specificity 69.0%.

CONCLUSIONSPCT provides better diagnostic value of infection compared with other inflammatory markers. The potential applications of PCT in differential diagnosis of PIS and infection after percutaneous TEVAR deserve further studies.

Adult ; Aged ; Blood Sedimentation ; C-Reactive Protein ; metabolism ; Calcitonin ; metabolism ; Calcitonin Gene-Related Peptide ; Diagnosis, Differential ; Female ; Humans ; Male ; Middle Aged ; Prospective Studies ; Protein Precursors ; metabolism ; Vascular Surgical Procedures