Predicting risk for portal vein thrombosis in acute pancreatitis patients: A comparison of radical basis function artificial neural network and logistic regression models

Journal of Critical Care

Volumn 39, Issue , 2017, Pages 115-123

  Fei, Yang ^a   Hu, Jian ^b   Gao, Kun ^a   Tu, Jianfeng ^a   Li, Wei qin ^a   Wang, Wei ^c  

^a MEDICAL SCHOOL OF NANJING UNIVERSITY   (China)

^b NANJING UNIVERSITY OF SCIENCE AND TECHNOLOGY   (China)

^c NANJING UNIVERSITY OF CHINESE MEDICINE   (China)

Author keywords

Logistic regression; Neural network; Pancreatitis; Radical basis function; Thrombosis

Indexed keywords

AMYLASE; D DIMER; BIOLOGICAL MARKER; FIBRIN DEGRADATION PRODUCT; FIBRIN FRAGMENT D;

ACUTE PANCREATITIS; ADULT; ARTICLE; ARTIFICIAL NEURAL NETWORK; CARDIOVASCULAR RISK; CONTROLLED STUDY; DIAGNOSTIC TEST ACCURACY STUDY; ERYTHROCYTE VOLUME; FEMALE; HUMAN; LOGISTIC REGRESSION ANALYSIS; MAJOR CLINICAL STUDY; MALE; MEASUREMENT ACCURACY; PORTAL VEIN THROMBOSIS; PREDICTION; PREDICTIVE VALUE; PROTHROMBIN TIME; RADIAL BASED FUNCTION; RECEIVER OPERATING CHARACTERISTIC; SENSITIVITY AND SPECIFICITY; ACUTE DISEASE; COMPARATIVE STUDY; COMPLICATION; HEPATIC PORTAL VEIN; METABOLISM; MIDDLE AGED; NERVE CELL NETWORK; PANCREATITIS; PHYSIOLOGY; REGRESSION ANALYSIS; RETROSPECTIVE STUDY; STATISTICAL MODEL; VEIN THROMBOSIS;

ACUTE DISEASE; ADULT; BIOMARKERS; FEMALE; FIBRIN FIBRINOGEN DEGRADATION PRODUCTS; HUMANS; LOGISTIC MODELS; MALE; MIDDLE AGED; NERVE NET; PANCREATITIS; PORTAL VEIN; REGRESSION ANALYSIS; RETROSPECTIVE STUDIES; ROC CURVE; SENSITIVITY AND SPECIFICITY; VENOUS THROMBOSIS;

EID: 85017614364     PISSN: 08839441     EISSN: 15578615     Source Type: Journal    
DOI: 10.1016/j.jcrc.2017.02.032     Document Type: Article

References (29)

1. [1] Butler, J.R., Eckert, G.J., Zyromski, N.J., Leonardi, M.J., Lillemoe, K.D., Howard, T.J., Natural history of pancreatitis-induced splenic vein thrombosis: a systematic review and meta-analysis of its incidence and rate of gastrointestinal bleeding. HPB(Oxford) 13 (2011), 839–845.
2. [2] Heider, T.R., Azeem, S., Galanko, J.A., Behrns, K.E., The natural history of pancreatitis-induced splenic vein thrombosis. Ann Surg 239 (2004), 876–880.
3. [3] Dörffel, T., Wruck, T., Rukert, R.I., Romaniuk, P., Dorffel, O., Wermke, W., Vascular complication in acute pancreatitis assessed by color duplex ultrasonography. Pancreas 21 (2002), 126–133.
4. [4] Koklu, S., Coban, S., Yuksel, O., Arhan, M., Left-sided portal hypertension. Dig Dis Sci 52 (2007), 1141–1149.
5. [5] Tripodi, A., Legnani, C., Palareti, G., The risk of a first and a recurrent venous thrombosis associated with an elevated D-dimer level and an elevated thrombin potential: results of the THE-VTE study: comment. J Thromb Haemost 13 (2015), 2283–2286.
6. [6] Singh, V.K., Wu, B.U., Bollen, T.L., Repas, K., Maurer, R., Mortele, K.J., Early systemic inflammatory response syndrome is associated with severe acute pancreatitis. Clin Gastroenterol Hepatol 7 (2009), 1247–1251.
7. [7] Chung, W.S., Lin, C.L., Comorbid risks of deep vein thrombosis and pulmonary thrombo-embolism in patients with chronic pancreatitis: a nationwide cohort study. J Thromb Haemost 14 (2016), 98–104.
8. [8] Fei, Y., Zong, G.Q., Chen, J., Liu, R.M., Evaluation of the value of D-dimer, P-selectin, and platelet count for prediction of portal vein thrombosis after devascularization. Clin Appl Thromb Hemost 22 (2016), 471–475.
9. [9] Hwang, Y.N., Lee, J.H., Kim, G.Y., Jiang, Y.Y., Kim, S.M., Classification of focal liver lesions on ultrasound images by extracting hybrid textural features and using an artificial neural network. Biomed Mater Eng 26:Suppl. 1 (2015), S1599–S1611.
10. [10] Seixas, J.M., Faria, J., Souza Filho, J.B., Vieira, A.F., Kritski, A., Trajman, A., Artificial neural network models to support the diagnosis of pleural tuberculosis in adult patients. Int J Tuberc Lung Dis 17 (2013), 682–686.
11. [11] Fei, Y., Hu, J., Li, W.Q. et al., Artificial neural networks predict the incidence of portosplenomesenteric venous thrombosis in patients with acute pancreatitis. J Thromb Haemost, Dec 13 2016, 10.1111/jth.13588 [Epub ahead of print].
12. [12] Etemad, S.A., Arya, A., Classification and translation of style and affect in human motion using RBF neural networks. Neurocomputing 129 (2014), 585–595.
13. [13] Babu, R.V., Savitha, R., Suresh, S., Agarwal, B., Subject independent human action recognition using spatio-depth information and meta-cognitive RBF network. Eng Appl Artif Intell 26 (2013), 2010–2021.
14. [14] Banks, P.A., Bollen, T.L., Dervenis, C., Gooszen, H.G., Johnson, C.D., Sarr, M.G., Classification of acute pancreatitis–2012: revision of the Atlanta classification and definitions by international consensus. Gut 62 (2013), 102–111.
15. [15] Zhou, J., Ke, L., Tong, Z.H., Li, G., Li, W.Q., Li, N. et al., Risk factors and outcome of splanchnic venous thrombosis in patients with necrotizing acute pancreatitis. Thromb Res 135 (2015), 68–72.
16. [16] Mortelé, K.J., Mergo, P.J., Taylor, H.M., Wiesner, W., Cantisani, V., Ernst, M.D. et al., Peripancreatic vascular abnormalities complicating acute pancreatitis: contrast-enhanced helical CT findings. Eur J Radiol 52 (2004), 67–72.
17. [17] Balthazar, E.J., Acute pancreatitis: assessment of severity with clinical and CT evaluation. Radiology 223 (2002), 603–613.
18. [18] Terrin, N., Schmid, C.H., Griffith, J.L., D'Agostino, R.B., Selker, H.P., External validity of predictive models: a comparison of logistic regression, classification trees, and neural networks. J Clin Epidemiol 56 (2003), 721–729.
19. [19] Pradhan, B., Lee, S., Landslide susceptibility assessment and factor effect analysis: backpropagation artificial neural networks and their comparison with frequency ratio and bivariate logistic regression modelling. Environ Model Softw 25 (2010), 747–759.
20. [20] Morteza, A., Nakhjavani, M., Asgarani, F., Filipe, L., Carvalho, F., Karimi, R. et al., Inconsistency in albuminuria predictors in type 2 diabetes: a comparison between neural network and conditional logistic regression. Transl Res 161 (2013), 397–405.
21. [21] Friedrichs, F., Schmit, M., On the power of Boolean computations in generalized RBF neural networks. Neurocomputing 63 (2005), 483–498.
22. [22] Marinaro, M., Scarpetta, S., On-line learning in RBF neural networks: a stochastic approach. Neural Netw 13 (2000), 719–729.
23. [23] Kokshenev, I., Braga, A.P., An efficient multi-objective learning algorithm for RBF neural network. Neurocomputing 73 (2010), 2799–2808.
24. [24] Ferreira, P.M., Ruano, A.E., Choice of RBF model structure for predicting greenhouse inside air temperature. IFAC proceedings, 35, 2002, 91–96.
25. [25] Sayahi, T., Tatar, A., Bahrami, M., A RBF model for predicting the pool boiling behavior of nanofluids over a horizontal rod heater. Int J Therm Sci 99 (2016), 180–194.
26. [26] Riverol, C.C., Pilipovik, V., The use of radial basis function networks (RBFN) to predict critical water parameters in desalination plants. Expert Syst Appl 10 (2010), 7285–7287.
27. [27] Cook, D.F., Chiu, C.C., Predicting the internal bond strength of particleboard, utilizing a radial basis function neural network. Eng Appl Artif Intell 10 (1997), 171–177.
28. [28] Lin, C.L., Wang, J.F., Chen, C.Y., Chen, C.W., Yen, C.W., Improving the generalization performance of RBF neural networks using a linear regression technique. Expert Syst Appl 36 (2009), 12049–12053.
29. [29] Iliyas, S.A., Elshafei, M., Habib, M.A., Adeniran, A.A., RBF neural network inferential sensor for process emission monitoring. Control Eng Pract 21 (2013), 962–970.