Altered Coagulation In Inflammatory Bowel Disease:Predicting The Disease Status And Assisting The Diagnosis

Background and aimsOur study aimed at evaluating the coagulation status in patients with inflammatory bowel disease(IBD),and exploring the possibility of using coagulation parameters to predict the disease status and to assist the diagnosis.MethodsWe enrolled 987 hospitalized IBD patients and 1027 healthy controls during March 2011 to June 2016.The results of count of the blood cells(CBC)and the coagulation panel of all participants were collected.We compared the data of IBD and healthy controls to determine whether coagulation status was altered under inflammatory conditions.Correlation analysis and multiple linear regression analysis were adopted to decide the relationship between coagulation parameters and disease status.Computerbased machine learning including artificial neural network(ANN)and support vector machine(SVM),together with receiving operator curve(ROC)was used to estimate the value of coagulation parameters in the diagnosis of IBD.ResultsCompared with healthy controls,IBD patients showed higher platelet count and plateletocrit,lower mean platelet volume,platelet distribution width and platelet-large cell ratio,prolonged prothrombin time and activated partial thromboplastin time,and increased fibrinogen and INR(p < 0.001).CRP and ESR significantly correlated with hypercoagulation(nearly all p < 0.05).In ulcerative colitis(UC)patients,coagulation parameters demonstrated significant correlation with clinical activity while in Crohn’s disease(CD)patients,only fibrinogen positively parallel with Simple Crohn’s Disease Activity Index(p = 0.046,β = 0.8).As for endoscopic activity,in the UC group,Baron score and platelet-related parameters were closely interrelated while in the CD group,coagulation parameters showed little relevance with SES-CD.Multiple linear regression analysis revealed that in the CD group,patients with colon involvement displayed more obviously altered coagulation status(all p < 0.05).Stricturing lesion and perianal disease also correlated with part of the coagulation parameters.While in UC patients,abnormality of coagulation status was influenced by disease extent.ROC analysis demonstrated that coagulation parameters were of medium predictive value for diagnosing IBD since area under ROC was 0.748 with the sensitivity of 71.1% and the specificity 70.7%.The overall accuracy of the ANN model was 0.75 with the sensitivity of 73.3% and the specificity of 76.5% while in the SVM model,the overall accuracy was 0.744 with the sensitivity of 67.4% and the specificity of 77.0%.When we used the nine coagulation parameters to assist further classification of IBD,the results were less satisfactory.Area under ROC was only 0.68 and the overall accuracy of the ANN model and the SVM model were 0.68 and 0.636 respectively.ConclusionsHypercoagulation is present in IBD patients.Disease status and coagulation are closely correlated in IBD.In CD patients,coagulation parameters are able to indicate the level of inflammatory biomarkers,location of the lesion,disease behavior as well as presence of perianal disease while in UC patients,coagulation parameters are indicative of the the level of inflammatory biomarkers,endoscopic activity and disease extent.