RESUMO
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.
Assuntos
Humanos , Pancreatite , Doença Aguda , Estudos Retrospectivos , Hospitalização , AlgoritmosRESUMO
Objective:To evaluate narrow band imaging-magnifying endoscopy (NBI-ME) for the further assessment of lesions of low-grade intraepithelial neoplasia (LGIN) in the gastric biopsy.Methods:Data of 180 patients who underwent NBI-ME before endoscopic submucosal dissection (ESD) for biopsy of gastric LGIN at the First Affiliated Hospital of Soochow University from January 2017 to October 2020 were analyzed retrospectively. Taking the pathological results after ESD as the gold standard, the sensitivity, the specificity, the positive predictive value, the negative predictive value, and the accuracy of NBI-ME in predicting the pathological upgrading of gastric LGIN lesions after ESD were calculated, and the receiver operator characteristic (ROC) curve was drawn.Results:Among 180 gastric LGIN lesions, 115 (63.89%) were pathological upgraded and 65 (36.11%) were not after ESD. There were 10 missed diagnoses, 19 misdiagnoses, and 151 correct diagnoses in NBI-ME examination before ESD. The sensitivity, the specificity, the positive predictive value, the negative predictive value, and the accuracy of NBI-ME in predicting the pathological upgrading of gastric LGIN lesions after ESD were 91.3% (105/115), 70.8% (46/65), 84.7% (105/124), 82.1%(46/56) and 83.9% (151/180), respectively. The area under the ROC curve was 0.810 (95% CI: 0.737-0.883). Conclusion:Further NBI-ME examination of gastric LGIN lesions diagnosed by biopsy pathology can accurately predict whether the lesions have pathological upgrading after ESD, which is of important guiding significance for the patients to choose the treatment strategy of further follow-up or endoscopic resection.
RESUMO
Objective@#To make a postural transfer belt for patients with cervical spinal cord injury, to reduce and prevent the corresponding nursing problems with traditional methods of transfer@*Methods@#44 patients with cervical spinal cord injury admitted to the ward from January to June 2017 were selected as the control group by traditional methods of postural metastasis, and 48 patients with cervical spinal cord injury admitted to the ward from July to December 2017 were selected as the observation group by using self-made transfer belt.@*Results@#Number of the skin injury caused by transfer in observation group was 0 cases, in control group was four cases, and there was significant difference (χ2=1.91, P=0.049). Falls occur due to metastasis: there were 0 cases in the observation group and five cases in the control group, there was significant difference (χ2=2.39, P=0.026). The number of caregivers in the observation group decreased on average (1.21±0.08), and the number of caregivers in the control group decreased on average (0.86±0.09). The differences between the two groups are statistically significant (t=2.905, P=0.005). The results of the investigation on the escorts in the observation group showed that 46 (95.8%) people believed that the transfer belt was convenient for patients. 47 people believed that the transfer belt was safer and more labor-saving to use, accounting for 97.9%, and 47 people believed that the transfer belt would continue to be used when they went home, who occupied 97.9%.@*Conclusion@#The self-made transfer belt is convenient for the caregivers to carry the patients with cervical spinal cord injury, which effectively prevents the occurrence of skin injury, falls and other nursing problems, and improves the quality and experience of the caregivers. This technology is worthwhile to spread.
RESUMO
ObjectiveTo investigate the value of combined measurement of serum alpha-fetoprotein (AFP), Dickkopf-1 (DKK1), and cytoskeleton-associated protein 4 (CKAP4) in the diagnosis of hepatocellular carcinoma (HCC). MethodsA total of 122 patients with HCC (76 patients in the early stage), 152 patients with liver cirrhosis, and 105 patients with chronic hepatitis B, who were admitted to The First Affiliated Hospital of Soochow University from January 2013 to December 2017, were enrolled, and 101 individuals who underwent physical examination during the same period of time were enrolled as healthy control group. A one-way analysis of variance was used for comparison of continuous data between multiple groups, and the least significant difference t-test was used for further comparison between two groups; the chi-square test was used for comparison of categorical data between multiple groups. A binary logistic regression analysis was used to obtain the new variable of predicted probability, and the receiver operating characteristic (ROC) curve analysis was performed for each index and predicted probability to investigate the area under the ROC curve (AUC), sensitivity, and specificity of the three indices used alone or in combination. ResultsThe HCC group had significantly higher serum levels of AFP, DKK1, and CKAP4 than the liver cirrhosis group, the chronic hepatitis B group, and the healthy control groups (F=121.618, 84.559, and 91.769, P＜0.001). The combination of AFP, DKK1, and CKAP4 had an AUC of 0.967 (95% confidence interval ［CI］: 0.950-0.984), a sensitivity of 0.869, and a specificity of 0.980, which were significantly higher than the AUCs, sensitivities, and specificities of the three indices used alone (all P＜0.05). The combination of the three indices had an AUC of 0.965 (95%CI: 0.942-0.988), a sensitivity of 0.868, and a specificity of 0.980 in the diagnosis of early-stage HCC, which were significantly higher than the AUCs, sensitivities, and specificities of the three indices used alone (all P＜0.05). ConclusionCombined measurement of serum AFP, DKK1, and CKAP4 improves the accuracy, sensitivity, and specificity of HCC diagnosis and thus has an important clinical value in the screening for and early diagnosis of HCC.
RESUMO
Objective To investigate healthy status and disease distribution of couples through analysing the results of pre‐preg‐nancy laboratory examination and to explore high risk factors ,in order to provide scientific references for the realization of eugenics . Methods The routine blood test ,serum markers of hepatitis B ,five items(TORCH) examination ,detection of female vaginal secre‐tions were carried out in 8 313 couples planning pregnancy from 2013 to 2014 ,and the results of pre‐pregnancy health examination were analysed and evaluated .Results The thyroid dysfunction accounted for 17 .43% of all women undergoing examination ,which was the most common disease .Among items carried out in all couples ,thalassemia and positive of hepatitis B surface antigen were the most common ,accounted for 10 .20% and 9 .94% respectively .Conclusion The pre‐pregnancy health examination could screen high risk factors ,which is benefit for guiding eugenics and effectively reducing the birth defects and adverse pregnancy and is a sig‐nificant measure for eugenics .
RESUMO
<p><b>OBJECTIVE</b>To evaluate the diagnostic value of endoscopic ultrasonography (EUS) for submucosal tumors (SMTs) of upper gastrointestinal tract.</p><p><b>METHODS</b>A retrospective analysis was made based on clinical data of 206 upper gastrointestinal SMTs patients from January 2009 to July 2013 in The First Affiliated Hospital of Soochow University. Preoperative EUS findings were compared with postoperative pathological diagnosis, and the sensitivity, specificity and accuracy of EUS diagnosis in property and layer origin of SMTs were calculated.</p><p><b>RESULTS</b>The sensitivity, specificity and accuracy of EUS diagnosis in SMTs property were 60.2%, 67.1% and 61.2%. The sensitivity, specificity and accuracy of EUS diagnosis in layer origin of SMTs were 98.0%, 98.2% and 98.1%.</p><p><b>CONCLUSION</b>EUS has limited value in the diagnosis of property of SMT, and has high accuracy of identifying the origin layer, which is helpful to choose therapeutic schedule of SMT under endoscopy.</p>