ABSTRACT
Objective:We aimed to explore a colorectal cancer risk prediction model through machine learning algorithm based on the big data in laboratory medicine.Methods:According to the labeling of colonoscopy combined with pathology or referring to the ICD-10 code, the colonoscopy patients in Shanghai Changhai Hospital from 2013.1.1 to 2019.6.30 and the outpatients and inpatients from 2010.1.1 to 2019.6.30 were divided into colorectal cancer groups and non-colorectal cancer group. Four machine learning algorithms, Extreme gradient boosting(Xgboost),Artificial Neural Network(ANN),Support Vector Machine(SVM),Random Forest(RF), are used to mine all routine laboratory test item data of the enrolled patients, select model features and establish a classification model for colorectal cancer. And the effectiveness of the model was prospectively verified in patients in the whole hospital of Changhai Hospital from 2019.7.1 to 2020.8.31.Result:A colorectal cancer risk prediction model (CRC-Lab7) including 7 characteristics of fecal occult blood, carcinoembryonic antigen, red blood cell distribution width, lymphocyte count, albumin/globulin, high-density lipoprotein cholesterol and hepatitis B virus core antibody was constructed by the XgBoost algorithm. The AUC of the model in the validation set and prospective validation set were 0.799 and 0.816, respectively, which was significantly higher than that of fecal occult blood (AUC was 0.68 and 0.706, respectively). It also has high diagnostic accuracy for colorectal cancer with negative fecal occult blood or under 50 years old.Conclusion:In this study, a colorectal cancer risk prediction model was established by mining routine laboratory big data. The model′s performance is better than fecal occult blood, and it has high diagnostic accuracy for colorectal cancer in patients with negative fecal occult blood and younger than 50 years old.
ABSTRACT
Objective:To evaluate the feasibility of a predictire model composed of non-specific test indexes in early diagnosis of gastric cancer.Methods:From the database of electronic medical record system of Shanghai Changhai Hospital, a total of 24 615 case records were included from January 1, 2010 to April 30, 2019, including 10 497 cases of gastric cancer, 5 198 cases of precancerous diseases, and 8 920 cases of health examination. Through stratified random sampling, the study population was divided into validation set, training set and test set. After data processing and quality control for all laboratory variables, the optimal machine learning algorithm and diagnostic efficiency grouping were selected through four machine learning algorithms, induding the gradient boosting decision tree, random forest, support vector machine, and artificial neural network, and the data were trained by backward stepwise regression method to build the best feature model.Result:In this study, a diagnostic model V22 consisting of 22 routine testing parameters was established. V22 could distinguish early gastric cancer from control group composed of healthy group and precancerous disease, AUC was 0.808, the sensitivity was 85.7%, and the specificity was 91.9%. For CEA negative gastric cancer, V22 also showed high diagnostic accuracy, AUC was 0.801.Conclusion:V22 was a valuable model for the diagnosis of gastric cancer. V22 was an auxiliary diagnostic model of gastric cancer with clinical application value, which could well distinguish early gastric cancer from the control group composed of healthy group and precancerous disease, and the detection rate of early gastric cancer was better than the traditional tumor marker CEA.
ABSTRACT
Objective To explore the value of MRI combined with tumor markers in the differential diagnosis of borderline ovarian tumor(BOT)and stage I epithelial ovarian carcinoma(EOC),increase the rate of preoperative diagnosis.Methods Fifty -six patients with BOT(BOT group)and forty -seven patients with stage I EOC(EOC group)confirmed pathologically underwent tumor markers and MRI examination were selected.The MRI imaging features and tumor markers level were compared between the two groups.Results BOTand EOC group onset age were (39.45 ±11.83),(44.38 ±12.44)years old respectively,two groups had statistically significant difference(t =2.05,P 0.05).However,the solid components were larger (76.0 ±54.9)mm and the septations were thicker (6.2 ± 3.5)mm in EOC group than in BOT group (49.0 ±47.2)mm,(3.6 ±3.5)mm(t =-2.642,-3.784,all P 0.05).The serum HE4 levels between BOT group[(86.9 ±82.2)pmol/L]and EOC group[(166.3 ±87.1)pmol/L]had statistically significant difference (t =-4.723,P <0.05).MRI prompt tumors maximum diameter and thickness of the separated solid ingredients combined serum HE4 levels to identify two groups of AUC of the tumor and its sensitivity,specificity were 0.820,72.3%,80.4%,respectively.Conclusion The fea-tures like younger,increased solid components,thickened septum and higher serum HE4 level may be helpful in the differential diagnosis of BOT and stage I EOC.
ABSTRACT
Objective To investigate the value of MRI in the prenatal diagnosis of abnormal fetal kidneys. Methods From December 2014 to March 2016, 51 women underwent MRI and were confirmed as having fetuses with abnormal fetal kidneys when follow up. Their clinical and MRI profiles were analyzed retrospectively, including MRI manifestation, the fetal kidney signal intensity of diffusion-weighted imaging (DWI) and apparent diffusion coefficient (ADC). The signal intensity of DWI and ADC of the abnormal kidney and the normal opposite kidney, and those of the normal and abnormal kidneys in different individuals were compared. The accuracies of MRI and ultrasound in evaluating abnormal fetal kidneys were also compared. Results MRI could accurately demonstrate the morphological features of abnormal fetal kidneys. There was no statistically significant difference between DWI signal intensity and ADC value of the abnormal kidney[368 ± 125,(1.516 ± 0.420)× 10-3 mm2/s] and the normal opposite one[410 ± 125,(1.362 ± 0.251)× 10-3 mm2/s], P values were 0.165 and 0.184,respectively. The DWI signal intensity of normal kidneys(401 ± 124)was higher than that of renal cysts(182 ± 40, P<0.01), and the ADC value of normal kidneys[(1.306 ± 0.252)× 10-3 mm2/s] was lower than that of renal cysts[(2.912 ± 0.235)× 10-3 mm2/s] and multicystic dysplastic kidneys[(1.870 ± 0.654)× 10-3 mm2/s], P values were<0.01 and 0.045, respectively. The diagnostic accuracy of MRI and prenatal ultrasound for abnormal fetal kidneys were 94%(63/67)and 85%(57/67), respectively. However, there was no statistical difference between the two methods (P=0.070). Conclusion MRI have an important role in the prenatal diagnosis and evaluation of abnormal fetal kidneys.
ABSTRACT
Objective To explore the diagnostic value of MR fast imaging sequences in fetal lung congenital cystic adenomatoid malformation(CCAM).Methods 8 cases with suspected CCAM by US were examined with MRI fast sequences,including single shot turbo spin echo (SSTSE)and balanced fast field echo(B-FFE),and undergone axial,sagital and coronal scanning sections of fetal chests.MRI findings were compared with surgery(2 fetuses),autopsy (3 fetuses)and CT examination (3 fetuses).Results 7 fetuses with CCAM and 1 fetus with bronchopulmonary sequestration(BPS)diagnosed by MRI were confirmed by following surgery,autopsy and CT examination.Among the 7 CCAM cases,2 leisions were on the left side,while the other 5 lesions were on the right side.Fur-thermore,2 cases were cystic type and the rest 5 cases were mass type.The BPS was located in the lower left lung lobar.Conclusion MR fast imaging sequences in fetal can clearly demonstrate location,type and extent of CCAM and can provide important supplement information of the prenatal fetal ultrasound examination.
ABSTRACT
BACKGROUND: The mitochondrial DNA with multiple copy number, maternal inheritance, high mutation rate, restructuring and other rare features, has important significance at levels of molecular ecology, molecular genetics, forensic and anthropological research.OBJECTIVE: To comprehensively analyze mitochondrial DNA in the development of research methods, and to explore the application of anthropological research.METHODS: With the key words of mitochondrial DNA, polymorphism, and haplogroup in English, a computer-based online search was conducted in Pubmed database from January 1999 to April 2009. Anthropology relevant articles were included, but animal experiments were excluded.RESULTS AND CONCLUSION: Among the first inspection of 235 documents, 33 met the inclusion criteria. Mitochondrial DNA characterized by multiple copy number, maternal inheritance, high mutation rate, and very few re-occurring features, thus by analyzing the scope and frequency of information, it could be used to infer the relationship between the different populations, as well as the reconstruction of mass incidents. Mitochondrial DNA variation information extraction method had experienced low RFLP, high-resolution RFLP, sequencing and RFLP and sequencing of hypervariable region. Mitochondrial DNA polymorphisms played an important role in interfering phylogenetic relationships, different groups of national origin and migration routes.Mitochondrial DNA database of various groups around the world did not restrict the full application in anthropology. Mathematical statistical model which was used to improve existing, build and enrich various groups of mitochondrial DNA database all over the world is the main direction for future research. Mitochondrial DNA is significance in molecular ecology, molecular genetics, forensic science and anthropology, as well as the study of tissue engineering, especially in the study of human origins and comparative phylogenetic relationships of different populations.
ABSTRACT
Objective To analyze the clinical therapeutic effect of close reduction and perculaneous Kirschner wire fixation in treating humeral supracondylar fracture in children.Methods We retrospectively analyzed 28 children who had humeral supracondylar fracture treater in our department from January 2006 to December 2008.They were 2 to 13 years old (mena age:7 years and 5 months). According to Garland typing ,3 children had type I fracture ,11 type II and 14 type III. Closed reduction was performed guided by C-arm X-ray machine. Then the fracture was perculaneously fixed with 2 or 3 Kirschner wires of 1.5mm,and the elbow and wrist joints were fixed in the functional position with upper limb plaster.Results All patients were followed up for average 4~12months. All patients obtained bone union. No Volkmann contracture os iatrogenic nerve injury occurred. Conclusion Close reduction and percutaneous Kirschner wires fixation for humeral supracondylar fracture in children has the advantages of small injury and stable bone fixation.In addition,it can prevent Volkmann contracture and achieve good elbow joint function recovery.
ABSTRACT
Objective: To establish a method for determining mycophenolic acid(MPA) and its glucuronide(MPAG) inhuman plasma. Methods: A high performance liquid chromatographic assay with diode array detection was developed, and thedetector wavelength was set at 254nm. The plasma sample purification was limited to protein precipitation with acetonitrile.The sample was separated on Hypersil ODS2 column (200 mm ?4. 6mm, 5?m), the mobile phase consisted of solution A(25% acetonitrile and 75% 0.02 mol/L KH2PO4,pH 3.0)and solution B(70% acetonitrile and 30% 0.02 mol/L K2HPO4,pH6.5)with gradient elution. The flow rate was 1. 0 ml/min. Results: Calibration curves of MPA and MPAG were linear be-tween 1. 0-5. 0 ?g/ml (r=0.994 4,n=6) and (2.5-100) ?g/ml (r= 0.999 5,n=7),respectively. The detection limit of MPAand MPAG were 0. 5?g/ml, and 1.0 ?g/ml, respectively. The mean recoveries of high, medium and low concentrations ofMPA were (95. 75?2.3l)%, (104.10?1.91) % and (98.11?4.24)%, and MPAG were (97.37?1. 43)%, (101.10?5. 41)%and (105. 44?7.59)%. Conclusion: The present study provides a reliable quantitative method for pharmacokineticstudy and monitor of MPA and MPAG.