A methodological review of data mining techniques in predictive medicine: An application in hemodynamic prediction for abdominal aortic aneurysm disease

• Autorzy: Paramasivam V. , Yee T. S. , Dhillon S. K. , Sidhu A. S.

Identyfikatory

DOI

10.1016/j.bbe.2014.03.003

• Języki publikacji: EN

Abstrakty

EN

Modern clinics and hospitals need accurate real-time prediction tools. This paper reviews the importance and present trends of data mining methodologies in predictive medicine by focusing on hemodynamic predictions in abdominal aortic aneurysm (AAA). It also provides potential data mining working frameworks for hemodynamic predictions in AAA. These frameworks either allow the coupling between a typical computational modeling simulation and various data mining techniques, using the existing medical datasets of real-patient and mining it directly using various data mining techniques or implementing visual data mining approach to already available computed results of various hemodynamic features within the AAA models. These approaches allow the possibility of statistically predicting rupture potentials of aneurismal patients and ideally provide an alternate solution for substituting tedious and time-consuming computational modeling. Prediction trends of patient-specific aneurismal conditions via mining huge volume of medical data can also speed up the decision making process in real life medicine.

Słowa kluczowe

EN

data mining techniques; hemodynamic prediction; abdominal aortic aneurysm

PL

techniki eksploracji danych; hemodynamika; tętniak aorty brzusznej

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2014
• Tom: Vol. 34, no. 3
• Strony: 139--145
• Opis fizyczny: Bibliogr. 67 poz., rys.

Twórcy

autor

Paramasivam V.

• Curtin Sarawak Research Institute, Curtin University, Miri, Sarawak, Malaysia

autor

Yee T. S.

• Curtin Sarawak Research Institute, Curtin University, Miri, Sarawak, Malaysia

autor

Dhillon S. K.

• Institute of Biological Sciences, Faculty of Science, University of Malaya, Kuala Lumpur, Malaysia

autor

Sidhu A. S.

• Curtin Sarawak Research Institute, Curtin University, CDT250, 98009 Miri, Sarawak, Malaysia; Faculty of Health Sciences, Curtin University, Perth, Australia

Bibliografia

• [1] Vliet JAVD, Boll APM. Abdominal aortic aneurysm. Lancet 1997;349:863–6.
• [2] Cotran RS, Kumar V, Robbins SL. Robbins pathologic basis of decease. London: Saunders; 1994 [chapter 11].
• [3] Thompson MM, Bell RPF. ABC of arterial and venous disease: arterial aneurysm. Br Med J 2000;320:1193–6.
• [4] Newman AB, Arnold AM, Burke GL, O'Leary DH, Manolio TA. Cardiovascular disease and mortality in older adults with small abdominal aortic aneurysms detected by ultrasonography: the cardiovascular health study. Ann Intern Med 2001;134:182–90.
• [5] Kleinstreuer C, Li Z. Analysis and computer program for rupture-risk prediction of abdominal aortic aneurysm. Biomed Eng Online 2006;5:19.
• [6] VanDamme H, Sakalihasan N, Limet R. Factors promoting rupture of abdominal aortic aneurysms. Acta Chir Belg 2005;105(1):1–11.
• [7] Filipovic N, Kojic M, Stojanovic B, Ivanovic M, Rankovic V. Three-dimensional computer simulations of blood flow through the abdominal aortic aneurysm. International Congress of Computational Bioengineering. 2003. pp. 15–20.
• [8] Fillinger MF, Raghavan ML, Marra P, Cronenwett L, Kennedy E. In vivo analysis of mechanical wall stress and abdominal aortic aneurysm rupture risk. J Vasc Surg 2002;36:589–96.
• [9] Finol EA, Keyhani K, Amon CH. The effect of asymmetry in abdominal aortic aneurysm under physiologically realistic pulsatile flow conditions. J Biomech Eng 2003;125(2):207–17.
• [10] Scotti ChM, Shkolnik AD, Muluk SC, Finol EA. Fluid–structure interaction in abdominal aortic aneurysms: effects of asymmetry and wall thickness. Biomed Eng Online 2005;4:64.
• [11] Di Martino ES, Guadagni G, Fumero A, Ballerini G, Spirito R, Biglioli P, et al. Fluid–structure interaction within realistic three-dimensional models of the aneurysmatic aorta as a guidance to assess the risk of rupture of the aneurysm. Med Eng Phys 2001;23:647–55.
• [12] Li Z. Computational analyses and simulations of fluid– structure applied to stented abdominal aortic aneurysms. [PhD dissertation] North Carolina State University, Department of Mechanical and Aerospace Engineering; 2005.
• [13] Vorp DA, Vande Geest JP. Biomechanical determinants of abdominal aortic aneurysm rupture. J Am Heart Assoc 2005;25:1558–66.
• [14] Leuprecht A, Perktold K. Computer simulations on non- Newtonian effects on blood flow in large arteries. Comput Methods Biomech Biomed Eng 2001;4:149–63.
• [15] Cho YJ, Kensey KR. Effects of the non-Newtonian viscosity of blood on flows in a diseased arterial vessel. Part 1: Steady flow. Biorheology 1991;28:241–62.
• [16] Perktold K, Resch M, Florian H. Pulsatile non-Newtonian flow characteristics in a three-dimensional human carotid bifurcation model. J Biomech Eng 1991;113:464–75.
• [17] Cokelet G. The rheology and tube flow of blood. In: Skalak R, Chen S, editors. Handbook of bioengineering. New York: McGraw-Hill; 1987.
• [18] Grossi E. In: Suzuki K, editor. Artificial neural network – methodological advances and biomedical applications. 1st ed. Intech; 2011.
• [19] Han J, Kamber M. Data mining: concepts and techniques. Morgan Kaufmann; 2000.
• [20] Adriaans P, Zantinge D. Data mining. Longman; 1996.
• [21] Breiman L. Classification and regression trees. Wadsworth; 1984.
• [22] Quinlan JR. Introduction of decision trees. Mach Learn 1986;1(81):106.
• [23] Quinlan JR. C4.5. Program for machine learning. Morgan Kaufmann; 1992.
• [24] Mehta M. SLIQ. A fast scalable classifier for data mining. In: Proceedings of International Conference on Extending Database Technology, vol. 18; 1996. p. 32.
• [25] Loh Y, Vanichsetakul N. Tree-structured classification via generalized discriminant analysis. J Am Stat Assoc 1988;83:715–28.
• [26] Loh Y, Shih S. Split selection methods for classification trees. Stat Sinica 1997;7:815–40.
• [27] Rastogi R, Shim K. Public: a decision tree classifier that integrates building and pruning. Proc of 24th International Conference on Very Large Data Bases. 1998. pp. 404–15.
• [28] Kaas GV. An exploratory technique for investigating large quantities of categorical data. Appl Stat 1980;29:119–27.
• [29] Utgoff E. An incremental ID3. In: Proc 5th Conference on Machine Learning. 1988. pp. 107–20.
• [30] Shafer J. SPRINT: a scalable parallel classifier for data mining. In: Proc 22nd International Conference on Very Large Database. 1996. pp. 544–55.
• [31] Gehrke J. BOAT optimistic decision tree construction. In: Proc ACM-SIGMOID International Conference on Management of Data. 1999. pp. 169–80.
• [32] Lossos IS. Cerebrospinal fluid lactate dehydrogenase isoenzyme analysis for the diagnosis of central nervous system involvement in hematooncologic patients. Cancer 2000;88(7):1599–604.
• [33] Rainer TH. Derivation of a prediction rule for post-traumatic acute lung injury. Resuscitation 1999;42(3):187–96.
• [34] Selker HP. A comparison of performance of mathematical predictive methods for medical diagnosis: identifying acute cardiac ischemia among emergency department patients. J Investig Med 1995;43(5):468–76.
• [35] Temkin NR. Classification and regression tress (CART) for prediction of function at 1 year following head trauma. J Neurosurg 1995;85(5):764–71.
• [36] Longarce TA. Proposed criteria for the diagnosis of well-differentiated endometrial carcinoma. A diagnosis test for myoinvasion. Am J Surg Pathol 1995;19(4):371–406.
• [37] Ghosh S, Majunder PP. Mapping a quantitative trait locus via the EM algorithm and Bayesian classification. Genet Epidemiol 2000;19(2):97–126.
• [38] Hennessy D. Statistical methods for the objective design of screening procedures for macromolecular crystallization. Acta Crystallogr D: Biol Crystallogr 2000;56(7):817–27.
• [39] McCue LA. Functional classification of cNMP-binding proteins and nucleotide cyclases with implications for novel regulatory pathways in mycobacterium tuberculosis. Genome Res 2000;10(2):204–19.
• [40] Huitema AD. Validation of techniques for the prediction of carboplatin exposure: application of Bayesian methods. Clin Pharmacol Ther 2000;67(6):621–30.
• [41] Demser J. Naïve Bayesian based monogram for prediction of prostate cancer recurrence. Stud Health Technol Inform 1999;68:436–41.
• [42] Kukar M. Machine learning in prognosis of the femoral neck fracture recovery. Artif Intell Med 1996;8(5):431–51.
• [43] Kasif S, Delcher AL. Modeling biological data and structure with probabilistic networks. Comput Methods Mol Biol 1998;335–52.
• [44] Stultz CM. Predicting protein structure with probabilistic models. Protein Struct Biol Biomed Res 1997;447–506.
• [45] Arnold GE, Dunker AK, Johns SJ, Douthart RJ. Use of conditional probabilities for determining relationship between amino acid sequence and protein secondary structure. Proteins 1992;12(4):382–99.
• [46] Riis SK, Krogh A. Improving prediction of protein secondary structure using structured neural networks and multiple sequence alignments. J Comput Biol 1996;3:163–83.
• [47] Rost B, Sander C. Combining evolutionary information andneural networks to predict protein secondary structure. Proteins 1994;19:55–72.
• [48] Qian N, Sejnowski TJ. Predicting the secondary structure of globular proteins using neural network models. J Mol Biol 1988;202:865–84.
• [49] Claros MG. Prediction of n-terminal protein sorting signals. Curr Opin Struct Biol 1997;7:394–8.
• [50] Pedersen AG, Nielsen H. Neural network prediction of translation initiation sites in eukaryotes: perspective for EST and genome analysis. Intell Syst Mol Biol 1997;5:226–33.
• [51] Emanuelsson O, Nielsen H, Heijne GV. ChloroP: a neural network based method for predicting chloroplast transit peptides and their cleavage sites. Protein Sci 1999;8(5):978–84.
• [52] Uberbacher EC, Mural RJ. Locating protein-coding regions in human DNA sequences by a multiple sensor-neural network approach. Proc Natl Acad Sci U S A 1991;88:11261–5.
• [53] Snyder EE, Stormo GD. Identification of protein coding regions in genomic DNA. J Mol Biol 1995;248:1–18.
• [54] Burden FR, Winkler DA. A quantitative structure-activity relationships model for the acute toxicity of substituted benzenes to tetrahymena pyriformis using Bayesian regularized neural networks. Chem Res Toxicol 2000;13:436–40.
• [55] Turton EP. Ruptured abdominal aortic aneurysm: a novel method of outcome prediction using neural network technology. Eur J Vasc Endovasc Surg 2000;19(2):184–9.
• [56] Maimon O, Rokach L. Data mining and knowledge discovery handbook. 2nd ed. USA: Springer Science & Business Media Inc.; 2005.
• [57] Chen H, Fuller SS, Friedman C, Hersh W. Knowledge management and data mining in biomedicine. USA: Springer Science & Business Media Inc.; 2005.
• [58] Age S. Support Vector Machine (VSM) for pattern classification. Springer-Verlag London Ltd.; 2005.
• [59] Kulikowski JL. Pattern recognition based on ambiguous indications of experts. In: Kuryriski M, Puchala E, Wozniak M, editors. Computer recognition system. Wroclaw: Wroclaw University of Technology; 2001.
• [60] Shouman M, Turner T, Stocker R. Applying k-nearest neighbor in diagnosing heart disease patients. Intl J Inf Ed Tech 2012;2(3):220–3.
• [61] Kolachalama VB, Bressloff NW, Nair PB. Mining data from hemodynamics simulation via Bayesian emulation. Biomed Eng Online 2007;6:47.
• [62] Radovic M, Petrovic D, Filipovic N. Data mining application in the wall shear stress distribution prediction for aneurysm and carotid bifurcation models. 3rd Serbian (28th Yu) Congress on Theoretical and Applied Mechanics. 2011. pp. 1112–20.
• [63] Rodriguez JF, Soudah E, Lopez R, Doblare M, Onate E. Neural network for simulation the mechanical stress in abdominal aneurysm. III International Congress on Computational Bioengineering; 2007.
• [64] Shum J, Martufi G, Di Martino ES, Washington CB, Grisafi J, Muluk SC, et al. Quantitative assessment of abdominal aortic aneurysm geometry. Ann Biomed Eng 2011;39(1): 277–86.
• [65] Martufi G, Di Martino ES, Amon CH, Muluk SC, Finol EA. Three-dimensional geometrical characterization of abdominal aortic aneurysms: image-based wall thickness distribution. J Biomech Eng 2009;131(6):061015.
• [66] Milijkovic O, Ivanovic M, Filipovic N, Kojic M. AI models of the hemodynamic simulation. J Serb Soc Comp Mech 2008;2 (2):59–72.
• [67] Morizawa S, Shimoyama K, Obayashi S, Funamoto K, Hayase T. Implementation of visual data mining for unsteady blood flow field in an aortic aneurysm. J Vis 2011;14:393–8.