A quick evaluation is required for patients with acute abdominal pain. It is crucial to differentiate between surgical and nonsurgical pathology. Practical and accurate tests are essential in this differentiation. Lately, D-dimer level is found to be an important adjuvant in this diagnosis and obviously outperforms leukocyte count, which is widely used for diagnosis of certain cases [1,2]. Here, we handle this problem in a statistical perspective and combine the information from leukocyte count along with D-dimer level to increase the diagnostic accuracy of nontraumatic acute abdomen. For this purpose, various statistical learning algorithms are considered and model performances are assessed using several measures. Our results revealed that naïve Bayes, robust quadratic discriminant analysis, bagged and boosted support vector machines, single and bagged k-nearest neighbors provide an increase in diagnostic accuracies up to 8.93% and 17.86%, compared with D- dimer level and leukocyte count, respectively. Highest accuracy was obtained as 78.57% with naïve Bayes algorithm. A user-friendly web-tool is also developed to assist physicians in their decisions to differentially diagnose of patients with acute abdomen.
This tool freely available through http://www.biosoft.hacettepe.edu.tr/DDNAA/.