BACKGROUND Colon cancer is one of the most common malignant tumors of the digestive system.Liver metastasis after colon cancer surgery is the primary cause of death in patients with colon cancer.AIM To construct a nov...BACKGROUND Colon cancer is one of the most common malignant tumors of the digestive system.Liver metastasis after colon cancer surgery is the primary cause of death in patients with colon cancer.AIM To construct a novel nomogram model including various factors to predict liver metastasis after colon cancer surgery.METHODS We retrospectively analyzed 242 patients with colon cancer who were admitted and underwent radical resection for colon cancer in Zhejiang Provincial People’s Hospital from December 2019 to December 2022.Patients were divided into liver metastasis and non-liver metastasis groups.Sex,age,and other general and clinicopathological data(preoperative blood routine and biochemical test indexes)were compared.The risk factors for liver metastasis were analyzed using singlefactor and multifactorial logistic regression.A predictive model was then constructed and evaluated for efficacy.RESULTS Systemic inflammatory index(SII),C-reactive protein/albumin ratio(CAR),red blood cell distribution width(RDW),alanine aminotransferase,preoperative carcinoembryonic antigen level,and lymphatic metastasis were different between groups(P<0.05).SII,CAR,and RDW were risk factors for liver metastasis after colon cancer surgery(P<0.05).The area under the curve was 0.93 for the column-line diagram prediction model constructed based on these risk factors to distinguish whether liver metastasis occurred postoperatively.The actual curve of the column-line diagram predicting the risk of postoperative liver metastasis was close to the ideal curve,with good agreement.The prediction model curves in the decision curve analysis showed higher net benefits for a larger threshold range than those in extreme cases,indicating that the model is safer.CONCLUSION Liver metastases after colorectal cancer surgery could be well predicted by a nomogram based on the SII,CAR,and RDW.展开更多
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
基金reviewed and approved by the Institutional Review Board of Zhejiang Provincial People’s Hospital(Approval No.2023-338).
文摘BACKGROUND Colon cancer is one of the most common malignant tumors of the digestive system.Liver metastasis after colon cancer surgery is the primary cause of death in patients with colon cancer.AIM To construct a novel nomogram model including various factors to predict liver metastasis after colon cancer surgery.METHODS We retrospectively analyzed 242 patients with colon cancer who were admitted and underwent radical resection for colon cancer in Zhejiang Provincial People’s Hospital from December 2019 to December 2022.Patients were divided into liver metastasis and non-liver metastasis groups.Sex,age,and other general and clinicopathological data(preoperative blood routine and biochemical test indexes)were compared.The risk factors for liver metastasis were analyzed using singlefactor and multifactorial logistic regression.A predictive model was then constructed and evaluated for efficacy.RESULTS Systemic inflammatory index(SII),C-reactive protein/albumin ratio(CAR),red blood cell distribution width(RDW),alanine aminotransferase,preoperative carcinoembryonic antigen level,and lymphatic metastasis were different between groups(P<0.05).SII,CAR,and RDW were risk factors for liver metastasis after colon cancer surgery(P<0.05).The area under the curve was 0.93 for the column-line diagram prediction model constructed based on these risk factors to distinguish whether liver metastasis occurred postoperatively.The actual curve of the column-line diagram predicting the risk of postoperative liver metastasis was close to the ideal curve,with good agreement.The prediction model curves in the decision curve analysis showed higher net benefits for a larger threshold range than those in extreme cases,indicating that the model is safer.CONCLUSION Liver metastases after colorectal cancer surgery could be well predicted by a nomogram based on the SII,CAR,and RDW.
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.
