Support Vector Machine Diagnosis of Acute Abdominal Pain
2010 (English)In: Biomedical Engineering Systems and Technologies: International Joint Conference, BIOSTEC 2009 Porto, Portugal, January 14-17, 2009, Revised Selected Papers / [ed] Fred, Ana; Filipe, Joaquim; Gamboa, Hugo, Springer Berlin/Heidelberg, 2010, 347-355 p.Chapter in book (Other academic)Text
This study explores the feasibility of a decision-support system for patients seeking care for acute abdominal pain, and, specifically the diagnosis of acute diverticulitis. We used a linear support vector machine (SVM) to separate diverticulitis from all other reported cases of abdominal pain and from the important differential diagnosis non-specific abdominal pain (NSAP). On a database containing 3337 patients, the SVM obtained results comparable to those of the doctors in separating diverticulitis or NSAP from the remaining diseases. The distinction between diverticulitis and NSAP was, however, substantially improved by the SVM. For this patient group, the doctors achieved a sensitivity of 0.714 and a specificity of 0.963. When adjusted to the physicians’ results, the SVM sensitivity/specificity was higher at 0.714/0.985 and 0.786/0.963 respectively. Age was found as the most important discriminative variable, closely followed by C-reactive protein level and lower left side pain.
Place, publisher, year, edition, pages
Springer Berlin/Heidelberg, 2010. 347-355 p.
, Communications in Computer and Information Science, ISSN 1865-0929 ; 52
IdentifiersURN: urn:nbn:se:liu:diva-126224DOI: 10.1007/978-3-642-11721-3_27ISBN: 978-3-642-11720-6 (print)ISBN: 978-3-642-11721-3 (online)OAI: oai:DiVA.org:liu-126224DiVA: diva2:913022