Statistical learning approaches in diagnosing patients with nontraumatic acute abdomen

ÇAKIR, Elif; Korkmaz, Selcuk; ZARARSIZ, Gökmen; AKYILDIZ, Hızır Yakup; Goksuluk, Dincer

Statistical learning approaches in diagnosing patients with nontraumatic acute abdomen

Gökmen ZARARSIZ, (Erciyes Üniversitesi, Biyoistatistik Anabilim Dalı, Kayseri, Türkiye)

Hızır Yakup AKYILDIZ, (Erciyes Üniversitesi, Tıp Fakültesi, Genel Cerrahi Ana Bilim Dalı, Kayseri, Türkiye)

Dinçer GÖKSÜLÜK, (Erciyes Üniversitesi, Biyoistatistik Anabilim Dalı, Kayseri, Türkiye)

Selçuk KORKMAZ, (Hacettepe Üniversitesi, Tıp Fakültesi, Biyoistatistik Anabilim Dalı, Ankara, Türkiye)

Ahmet ÖZTÜRK (Erciyes Üniversitesi, Biyoistatistik Anabilim Dalı, Kayseri, Türkiye)

Turkish Journal of Electrical Engineering and Computer Sciences

5 0

Yıl: 2016 Cilt: 24 Sayı: 5 Sayfa Aralığı: 3685 - 3697 Metin Dili: İngilizce İndeks Tarihi: 29-07-2022

Statistical learning approaches in diagnosing patients with nontraumatic acute abdomen

Öz:

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 has been found to be an important adjuvant in this diagnosis and obviously outperforms leukocyte count, which is widely used for diagnosis of certain cases. Here, we handle this problem from a statistical perspective and combine the information from leukocyte count 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 the na¨ıve Bayes algorithm, robust quadratic discriminant analysis, bagged and boosted support vector machines, and single and bagged k-nearest neighbors provide an increase in diagnostic accuracies of up to 8.93% and 17.86% compared with D-dimer level and leukocyte count, respectively. Highest accuracy was obtained as 78.57% with the na¨ıve Bayes algorithm. Analysis has been done via the R programming language based on the codes developed by the authors. A user-friendly web-tool is also developed to assist physicians in their decisions to differentially diagnose patients with acute abdomen. It is available at http://www.biosoft.hacettepe.edu.tr/DDNAA/.

Anahtar Kelime:

Konular: Mühendislik, Elektrik ve Elektronik

Belge Türü: Makale Makale Türü: Araştırma Makalesi Erişim Türü: Erişime Açık

[1] Arora B, Gupta A, Nandi S, Sarwal A, Goyal P, Gogna S, Karwasra RK. Comparative analysis of clinical, radiological and operative findings in acute abdomen. Int J Enhanc Res Med Dent Care 2015; 2: 3-6.
[2] Stoker J, van Randen A, Lameris W, Boermeester MA. Imaging patients with acute abdominal pain. Radiology 2009; 253: 31-46.
[3] Marincek B. Nontraumatic abdominal emergencies: acute abdominal pain: diagnostic strategies. Eur Radiol 2002; 12: 2136-2150.
[4] Fahel E, Amaral PCG, Filho EMA, Ettinger JETM, Souza ELQ, Fortes MF, Alcantara RSM, Regis AB, Neto MPG, Sousa MM et al. Non-traumatic acute abdomen: videolaparoscopic approach. JSLS-J Soc Laparoend 1999; 3: 187-192.
[5] Akyildiz HY, Akcan A, Ozt¨urk A, Sozuer E, Kucuk C, Yucel A. D]dimer as a predictor of the need for laparotomy in patients with unclear non]traumatic acute abdomen. A preliminary study. Scand J Clin Lab Inv 2008; 68: 612-617.
[6] Maglinte DD, Gage SN, Harmon BH, Kelvin FM, Hage JP, Chua GT, Ng AC, Graffis RF, Chernish SM. Obstruction of the small intestine: accuracy and role of CT in diagnosis. Radiology 1993; 188: 61-64.
[7] Frager D, Medwid SW, Baer JW, Mollinelli B, Friedman M. CT of small-bowel obstruction: value in establishing the diagnosis and determining the degree and cause. Am J Roentgenol 1994; 162: 37-41.
[8] Flasar MH, Goldberg E. Acute abdominal pain. Med Clin N Am 2006; 90; 481-503.
[9] Cartwright SL, Knudson MP. Evaluation of acute abdominal pain in adults. Am Fam Physician 2008; 77: 971-978.
[10] Akyıldız HY, S¨oz¨uer E, Akcan A, K¨u¸c¨uk C, Artis T, Biri ˙I, Yılmaz N. The value of D-dimer test in the diagnosis of patients with non-traumatic acute abdomen. Ulus Travma Acil Cer 2010; 16: 22-26.
[11] Marshall RJ. The predictive value of simple rules for combining two diagnostic tests. Biometrics 1989; 45: 1213-1222.
[12] Bardella MT, Molteni N, Cesana B, Baldassarri AR, Binanchi PA. IgA antigliadin antibodies, cellobiose/mannitol sugar test, and carotenemia in the diagnosis of and screening for celiac disease. Am J Gastroenterol 1991; 86: 309-311.
[13] Bozkurt MR, Yurtay N, Yılmaz Z, Sertkaya C. Comparison of different methods for determining diabetes. Turk J Electtr Eng Co 2014; 22: 1044-1055.
[14] Chen H, Lin Z, Wu H, Wang L, Wu T, Tan C. Diagnosis of colorectal cancer by near-infrared optical fiber spectroscopy and random forest. Spectrochim Acta Mol Biomol Spectrosc 2015; 135: 185-191.
[15] Hastie T, Tibshirani R, Friedman J. The Elements of Statistical Learning: Data Mining, Inference and Prediction. 2nd ed. New York, NY, USA: Springer, 2009.
[16] Todorov V, Filzmoser P. An object oriented framework for robust multivariate analysis. J Stat Softw 2009; 32: 1-47.
[17] Tan PN, Steinbach M, Kumar V. Introduction to Data Mining, 1st ed. Boston, MA, USA: Addison-Wesley Longman Publishing Co., 2005.
[18] Ozt¨urk A, ¨ Ozdamar K. Comparison of linear, quadratic and flexible discriminant analysis by using generated and ¨ real data. Erciyes Med J 2008; 30: 266-277.
[19] Hothorn T, Hornik K, Zeileis A. Unbiased recursive partitioning: a conditional inference framework. J Comp Graph Stat 2006; 15: 651-674.
[20] Vapnik V. The Nature of Statistical Learning Theory. 2nd ed. New York, NY, USA: Springer-Verlag, 1995.
[21] Pochet N, Smet FD, Suykens JAK, De Moer BLR. Systematic benchmarking of microarray data classification: assessing the role of non-linearity and dimensionality reduction. Bioinformatics 2004; 20: 3185-3195.
[22] Breiman L. Bagging predictors. Mach Learn 1996; 24: 123-140.
[23] Dietterich TG. Ensemble methods in machine learning. In: Proceedings of the 1st International Workshop on Multiple Classifier Systems; 2123 June 2000; Cagliari, Italy. pp. 1-15.
[24] Kuhn M. Building predictive models in R using the caret package. J Stat Soft 2008; 28: 1-26.
[25] Silva FR, Vidotti VG, Cremasco F, Dias M, Gomi ES, Costa VP. Sensitivity and specificity of machine learning classifiers for glaucoma diagnosis using spectral domain OCT and standard automated perimetry. Arq Bras Oftalmol 2013; 76: 170-174.
[26] Shankle WR, Datta P, Dillencourt M, Pazzani M. Improving dementia screening tests with machine learning methods. Alzheimers Res 1996; 2: 1-15.

APA	ZARARSIZ G, AKYILDIZ H, Goksuluk D, Korkmaz S, ÇAKIR E (2016). Statistical learning approaches in diagnosing patients with nontraumatic acute abdomen. , 3685 - 3697.
Chicago	ZARARSIZ Gökmen,AKYILDIZ Hızır Yakup,Goksuluk Dincer,Korkmaz Selcuk,ÇAKIR Elif Statistical learning approaches in diagnosing patients with nontraumatic acute abdomen. (2016): 3685 - 3697.
MLA	ZARARSIZ Gökmen,AKYILDIZ Hızır Yakup,Goksuluk Dincer,Korkmaz Selcuk,ÇAKIR Elif Statistical learning approaches in diagnosing patients with nontraumatic acute abdomen. , 2016, ss.3685 - 3697.
AMA	ZARARSIZ G,AKYILDIZ H,Goksuluk D,Korkmaz S,ÇAKIR E Statistical learning approaches in diagnosing patients with nontraumatic acute abdomen. . 2016; 3685 - 3697.
Vancouver	ZARARSIZ G,AKYILDIZ H,Goksuluk D,Korkmaz S,ÇAKIR E Statistical learning approaches in diagnosing patients with nontraumatic acute abdomen. . 2016; 3685 - 3697.
IEEE	ZARARSIZ G,AKYILDIZ H,Goksuluk D,Korkmaz S,ÇAKIR E "Statistical learning approaches in diagnosing patients with nontraumatic acute abdomen." , ss.3685 - 3697, 2016.
ISNAD	ZARARSIZ, Gökmen vd. "Statistical learning approaches in diagnosing patients with nontraumatic acute abdomen". (2016), 3685-3697.

APA	ZARARSIZ G, AKYILDIZ H, Goksuluk D, Korkmaz S, ÇAKIR E (2016). Statistical learning approaches in diagnosing patients with nontraumatic acute abdomen. Turkish Journal of Electrical Engineering and Computer Sciences, 24(5), 3685 - 3697.
Chicago	ZARARSIZ Gökmen,AKYILDIZ Hızır Yakup,Goksuluk Dincer,Korkmaz Selcuk,ÇAKIR Elif Statistical learning approaches in diagnosing patients with nontraumatic acute abdomen. Turkish Journal of Electrical Engineering and Computer Sciences 24, no.5 (2016): 3685 - 3697.
MLA	ZARARSIZ Gökmen,AKYILDIZ Hızır Yakup,Goksuluk Dincer,Korkmaz Selcuk,ÇAKIR Elif Statistical learning approaches in diagnosing patients with nontraumatic acute abdomen. Turkish Journal of Electrical Engineering and Computer Sciences, vol.24, no.5, 2016, ss.3685 - 3697.
AMA	ZARARSIZ G,AKYILDIZ H,Goksuluk D,Korkmaz S,ÇAKIR E Statistical learning approaches in diagnosing patients with nontraumatic acute abdomen. Turkish Journal of Electrical Engineering and Computer Sciences. 2016; 24(5): 3685 - 3697.
Vancouver	ZARARSIZ G,AKYILDIZ H,Goksuluk D,Korkmaz S,ÇAKIR E Statistical learning approaches in diagnosing patients with nontraumatic acute abdomen. Turkish Journal of Electrical Engineering and Computer Sciences. 2016; 24(5): 3685 - 3697.
IEEE	ZARARSIZ G,AKYILDIZ H,Goksuluk D,Korkmaz S,ÇAKIR E "Statistical learning approaches in diagnosing patients with nontraumatic acute abdomen." Turkish Journal of Electrical Engineering and Computer Sciences, 24, ss.3685 - 3697, 2016.
ISNAD	ZARARSIZ, Gökmen vd. "Statistical learning approaches in diagnosing patients with nontraumatic acute abdomen". Turkish Journal of Electrical Engineering and Computer Sciences 24/5 (2016), 3685-3697.