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. Here, we developed a user-friendly web-tool to assist physicians in their decisions to differentially diagnose of patients with acute abdomen [3].

References

[1] H.Y. Akyildiz, A. Akcan, A. Ozturk, E. Sozuer, C. Kucuk, A. Yucel, D-dimer as a predictor of the need for laparotomy in patients with unclear non-traumatic acute abdomen. A preliminary study, Scandinavian Journal of Clinical & Laboratory Investigation 68(7). (2008) 612-7. doi:10.1080/00365510801971729.

[2] H.Y. Akyildiz, E. Sozuer, A. Akcan, C. Kucuk, T. Artis, I. Biri, N. Yilmaz, The value of D-dimer test in the diagnosis of patients with nontraumatic acute abdomen, Turkish Journal of Trauma & Emergency Surgery 16 (1). (2010) 22-26.

[3] G. Zararsiz, D. Goksuluk, S. Korkmaz, A. Ozturk, H.Y. Akyildiz, Statistical learning approaches in diagnosing patients with nontraumatic acute abdomen Turkish Journal of Electrical Engineer and Computer Science (2015) Accepted/In press.

Disclaimer: All images, designs or videos in this page are copyright of their respective owners. We do not own have these images, designs or videos. We collect them from search engine and other sources to be used as ideas for you. No copyright infringement is intended. If you have reason to believe that one of our content is violating your copyrights, please do not take any legal action. You can contact us directly to be credited or have the item removed from the site.