BACKGROUND Because of the powerful abilities of self-learning and handling complex biological information,artificial neural network(ANN)models have been widely applied to disease diagnosis,imaging analysis,and prognos...BACKGROUND Because of the powerful abilities of self-learning and handling complex biological information,artificial neural network(ANN)models have been widely applied to disease diagnosis,imaging analysis,and prognosis prediction.However,there has been no trained preoperative ANN(preope-ANN)model to preoperatively predict the prognosis of patients with gastric cancer(GC).AIM To establish a neural network model that can predict long-term survival of GC patients before surgery to evaluate the tumor condition before the operation.METHODS The clinicopathological data of 1608 GC patients treated from January 2011 to April 2015 at the Department of Gastric Surgery,Fujian Medical University Union Hospital were analyzed retrospectively.The patients were randomly divided into a training set(70%)for establishing a preope-ANN model and a testing set(30%).The prognostic evaluation ability of the preope-ANN model was compared with that of the American Joint Commission on Cancer(8th edition)clinical TNM(cTNM)and pathological TNM(pTNM)staging through the receiver operating characteristic curve,Akaike information criterion index,Harrell's C index,and likelihood ratio chi-square.RESULTS We used the variables that were statistically significant factors for the 3-year overall survival as input-layer variables to develop a preope-ANN in the training set.The survival curves within each score of the preope-ANN had good discrimination(P<0.05).Comparing the preope-ANN model,cTNM,and pTNM in both the training and testing sets,the preope-ANN model was superior to cTNM in predictive discrimination(C index),predictive homogeneity(likelihood ratio chi-square),and prediction accuracy(area under the curve).The prediction efficiency of the preope-ANN model is similar to that of pTNM.CONCLUSION The preope-ANN model can accurately predict the long-term survival of GC patients,and its predictive efficiency is not inferior to that of pTNM stage.展开更多
Study objective: Syncope is one of the most common presentation of patients seen in emergency departments (ED). Risk assessment of syncope is challenging. The San Francisco Syncope Rule is the most widely used risk as...Study objective: Syncope is one of the most common presentation of patients seen in emergency departments (ED). Risk assessment of syncope is challenging. The San Francisco Syncope Rule is the most widely used risk assessment, but has moderate accuracy. The aim of our study was to investigate blood biomarkers as prognostic factors for adverse outcome. Methods: In this observational study we included consecutive adults presenting with syncope to our ED. Management decisions were left to the discretion of the treating physicians. Patients were monitored for adverse events until discharge and underwent a phone interview 30 days after enrolment. Adverse outcome was defined as recurrent syncope, rehospitalization and death within 30 days. Results: We included 132 adult patients of whom 19 (14%) had an adverse event (recurrent syncope = 3, rehospitalisation = 12, death = 4). No difference in the San Francisco Syncope Rule was found in patients with and without adverse events (SFSR ≥ 1: 37% vs. 39%, p = 0.877). Median levels of ProADM (1.23 vs. 0.81 nmol/l;p = 0.006) and NT-proBNP (454 vs 134ng/l;p = 0.035) were higher and median levels for cholesterol (3.68 vs 4.57 mmol/l;p = 0.008) and prealbumin (0.19 vs0.26 g/l;p = 0.005) were lower in patients with adverse events. Prealbumin (AUC 0.72) and ProADM (AUC 0.70) had the highest prognostic accuracy. Conclusion: Biomarkers predicted poor outcome and might be helpful in the context of a clinical algorithm for an improved triage of syncope patients in the ED.展开更多
创伤性脑损伤(TBI)每年会影响全球数千万人,严重威胁人类健康,军人作为特殊群体尤为高发。目前,对于TBI的临床诊断主要依赖于计算机断层扫描(CT)和格拉斯哥昏迷量表(Glasgow Coma Score,GCS)。然而,CT检测的假阳性和患者暴露于电离辐射...创伤性脑损伤(TBI)每年会影响全球数千万人,严重威胁人类健康,军人作为特殊群体尤为高发。目前,对于TBI的临床诊断主要依赖于计算机断层扫描(CT)和格拉斯哥昏迷量表(Glasgow Coma Score,GCS)。然而,CT检测的假阳性和患者暴露于电离辐射的高风险及GCS存在较大的主观性等限制了TBI尤其是轻中度TBI(mmTBI)的精准诊断。近年来,胶质纤维酸性蛋白(GFAP)和泛素C端水解酶L1(UCH-L1)正在成为新的TBI诊断血液标志物,其应用越来越广泛。该文梳理了GFAP和UCH-L1的理化性质、功能及其在TBI诊断中与已有标志物相比存在的优势,阐述了其在战时环境下的应用潜力,并展望了TBI快速诊断的研发趋势。展开更多
基金the Scientific and Technological Innovation JointCapital Projects of Fujian Province,No.2016Y9031the Construction Project of Fujian Province Minimally Invasive Medical Center,No.[2017]171+4 种基金the General Project of Miaopu Scientific Research Fund of Fujian Medical University,No.2015MP021the Youth Project of Fujian Provincial Health and Family Planning Commission,No.2016-1-41the Fujian Province Medical Innovation ProjectChinese Physicians Association Young Physician Respiratory Research Fund,No.2015-CXB-16the Fujian Science and Technology Innovation Joint Fund Project,No.2017Y9004
文摘BACKGROUND Because of the powerful abilities of self-learning and handling complex biological information,artificial neural network(ANN)models have been widely applied to disease diagnosis,imaging analysis,and prognosis prediction.However,there has been no trained preoperative ANN(preope-ANN)model to preoperatively predict the prognosis of patients with gastric cancer(GC).AIM To establish a neural network model that can predict long-term survival of GC patients before surgery to evaluate the tumor condition before the operation.METHODS The clinicopathological data of 1608 GC patients treated from January 2011 to April 2015 at the Department of Gastric Surgery,Fujian Medical University Union Hospital were analyzed retrospectively.The patients were randomly divided into a training set(70%)for establishing a preope-ANN model and a testing set(30%).The prognostic evaluation ability of the preope-ANN model was compared with that of the American Joint Commission on Cancer(8th edition)clinical TNM(cTNM)and pathological TNM(pTNM)staging through the receiver operating characteristic curve,Akaike information criterion index,Harrell's C index,and likelihood ratio chi-square.RESULTS We used the variables that were statistically significant factors for the 3-year overall survival as input-layer variables to develop a preope-ANN in the training set.The survival curves within each score of the preope-ANN had good discrimination(P<0.05).Comparing the preope-ANN model,cTNM,and pTNM in both the training and testing sets,the preope-ANN model was superior to cTNM in predictive discrimination(C index),predictive homogeneity(likelihood ratio chi-square),and prediction accuracy(area under the curve).The prediction efficiency of the preope-ANN model is similar to that of pTNM.CONCLUSION The preope-ANN model can accurately predict the long-term survival of GC patients,and its predictive efficiency is not inferior to that of pTNM stage.
文摘Study objective: Syncope is one of the most common presentation of patients seen in emergency departments (ED). Risk assessment of syncope is challenging. The San Francisco Syncope Rule is the most widely used risk assessment, but has moderate accuracy. The aim of our study was to investigate blood biomarkers as prognostic factors for adverse outcome. Methods: In this observational study we included consecutive adults presenting with syncope to our ED. Management decisions were left to the discretion of the treating physicians. Patients were monitored for adverse events until discharge and underwent a phone interview 30 days after enrolment. Adverse outcome was defined as recurrent syncope, rehospitalization and death within 30 days. Results: We included 132 adult patients of whom 19 (14%) had an adverse event (recurrent syncope = 3, rehospitalisation = 12, death = 4). No difference in the San Francisco Syncope Rule was found in patients with and without adverse events (SFSR ≥ 1: 37% vs. 39%, p = 0.877). Median levels of ProADM (1.23 vs. 0.81 nmol/l;p = 0.006) and NT-proBNP (454 vs 134ng/l;p = 0.035) were higher and median levels for cholesterol (3.68 vs 4.57 mmol/l;p = 0.008) and prealbumin (0.19 vs0.26 g/l;p = 0.005) were lower in patients with adverse events. Prealbumin (AUC 0.72) and ProADM (AUC 0.70) had the highest prognostic accuracy. Conclusion: Biomarkers predicted poor outcome and might be helpful in the context of a clinical algorithm for an improved triage of syncope patients in the ED.
文摘创伤性脑损伤(TBI)每年会影响全球数千万人,严重威胁人类健康,军人作为特殊群体尤为高发。目前,对于TBI的临床诊断主要依赖于计算机断层扫描(CT)和格拉斯哥昏迷量表(Glasgow Coma Score,GCS)。然而,CT检测的假阳性和患者暴露于电离辐射的高风险及GCS存在较大的主观性等限制了TBI尤其是轻中度TBI(mmTBI)的精准诊断。近年来,胶质纤维酸性蛋白(GFAP)和泛素C端水解酶L1(UCH-L1)正在成为新的TBI诊断血液标志物,其应用越来越广泛。该文梳理了GFAP和UCH-L1的理化性质、功能及其在TBI诊断中与已有标志物相比存在的优势,阐述了其在战时环境下的应用潜力,并展望了TBI快速诊断的研发趋势。
