Pattern and Rule Mining for Identifying Signatures of Epileptic Patients from Clinical EEG Data

• Autorzy: Dasgupta Abhijit , Nayak Losiana , Das Ritankar , Basu Debasis , Chandra Preetam , De Rajat K.

Identyfikatory

DOI

10.3233/FI-2020-1968

• Języki publikacji: EN

Abstrakty

EN

Epilepsy is a neurological condition of human being, mostly treated based on the patients’ seizure symptoms, often recorded over multiple visits to a health-care facility. The lengthy time-consuming process of obtaining multiple recordings creates an obstacle in detecting epileptic patients in real time. An epileptic signature validated over EEG data of multiple similar kinds of epilepsy cases will haste the decision-making process of clinicians. In this paper, we have identified EEG data derived signatures for differentiating epileptic patients from normal individuals. Here we define the signatures with the help of various machine learning techniques, viz., feature selection and classification, pattern mining, and fuzzy rule mining. These signatures will add confidence to the decision-making process for detecting epileptic patients. Moreover, we define separate signatures by incorporating few demographic features like gender and age. Such signatures may aid the clinicians with the generalized epileptic signature in case of complex decisions.

Słowa kluczowe

EN

epileptic signature; epileptic network; feature selection; fuzzy logic; EEGLAB

• Wydawca: IOS Press
• Czasopismo: Fundamenta Informaticae
• Rocznik: 2020
• Tom: Vol. 176, nr 2
• Strony: 141--166
• Opis fizyczny: Bibliogr. 62 poz., rys., tab., wykr.

Twórcy

autor

Dasgupta Abhijit

• Machine Intelligence Unit, 203 Barrackpore Trunk Road, Kolkata 700108, India

autor

Nayak Losiana

• Machine Intelligence Unit, 203 Barrackpore Trunk Road, Kolkata 700108, India

autor

Das Ritankar

• Machine Intelligence Unit, 203 Barrackpore Trunk Road, Kolkata 700108, India

autor

Basu Debasis

• Department of Neuro-Medicine, Medical College and Hospital, Kolkata, India

autor

Chandra Preetam

• Department of Neuro-Medicine, Medical College and Hospital, Kolkata, India

autor

De Rajat K.

• Machine Intelligence Unit, 203 Barrackpore Trunk Road, Kolkata 700108, India

Bibliografia

• [1] Devinsky O. Sudden, unexpected death in epilepsy. New England Journal of Medicine. 2011 Nov 10; 365(19):1801-1811. DOI: 10.1056/NEJMra1010481.
• [2] Giourou E, Stavropoulou-Deli A, Giannakopoulou A, Kostopoulos GK, Koutroumanidis M. Introduction to Epilepsy and Related Brain Disorders. In: Cyberphysical Systems for Epilepsy and Related Brain Disorders 2015 (pp. 11-38). Springer, Cham. DOI: 10.1007/978-3-319-20049-1_2.
• [3] Donders J, Hunter SJ. Neuropsychological Conditions Across the Lifespan. Cambridge University Press. 2018 Aug 2016. ISBN: 9781316996751.
• [4] Devinsky O, Vezzani A, O’Brien TJ, Jette N, Scheffer IE, de Curtis M, Perucca P. Epilepsy. Nature Reviews Disease Primers, 2018. 4(18024). URL https://doi.org/10.1038/nrdp.2018.24.
• [5] Wendling F, Chauvel P, Biraben A, Bartolomei F. From intracerebral EEG signals to brain connectivity: identification of epileptogenic networks in partial epilepsy. Frontiers in Systems Neuroscience, 2010 Nov 25; 4:154. URL https://doi.org/10.3389/fnsys.2010.00154.
• [6] Dixit AB, Banerjee J, Tripathi M, Chandra PS. Presurgical epileptogenic network analysis: A way to enhance epilepsy surgery outcome. Neurology India, 2015 Sep 1. 63(5):743. DOI:10.4103/0028-3886.166546.
• [7] Tzallas AT, Tsipouras MG, Fotiadis DI. Automatic seizure detection based on time-frequency analysis and artificial neural networks. Computational Intelligence and Neuroscience, 2007. URL http://dx.doi.org/10.1155/2007/80510.
• [8] Polat K, Güneş S. Classification of epileptiform EEG using a hybrid system based on decision tree classifier and fast Fourier transform. Applied Mathematics and Computation, 2007 Apr 15; 187(2):1017-1026. URL https://doi.org/10.1016/j.amc.2006.09.022.
• [9] Gandhi T, Panigrahi BK, Bhatia M, Anand S. Expert model for detection of epileptic activity in EEG signature. Expert Systems with Applications, 2010 Apr 1; 37(4):3513-3520. URL https://doi.org/10.1016/j.eswa.2009.10.036.
• [10] Gopan G, Sinha N, Babu D. Statistical features based epileptic seizure EEG detection-an efficacy evaluation. In: 2015 International Conference on Advances in Computing, Communications and Informatics (ICACCI). IEEE, 2015 Aug 10 (pp. 1394-1398). DOI: 10.1109/ICACCI.2015.7275808.
• [11] Ahmadi A, Shalchyan V, Daliri MR. A new method for epileptic seizure classification in EEG using adapted wavelet packets. In: Electric Electronics, Computer Science, Biomedical Engineerings’ Meeting (EBBT). IEEE, 2017 Apr 20 (pp. 1-4). DOI: 10.1109/EBBT.2017.7956756.
• [12] Park C, Choi G, Kim J, Kim S, Kim TJ, Min K, Jung KY, Chong J. Epileptic seizure detection for multi-channel EEG with deep convolutional neural network. In: International Conference on Electronics, Information, and Communication (ICEIC). IEEE, 2018 Jan 24 (pp. 1-5). DOI: 10.23919/ELINFOCOM.2018.8330671.
• [13] Delorme A, Makeig S. EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis. Journal of Neuroscience Methods. 2004 Mar 15; 134(1):9-21. URL https://doi.org/10.1016/j.jneumeth.2003.10.009.
• [14] Naik GR, Kumar DK, Palaniswami M. Multi run ICA and surface EMG based signal processing system for recognising hand gestures. In: 2008 8th International Conference on Computer and Information Technology. IEEE, 2008 Jul 8 (pp. 700-705). DOI: 10.1109/CIT.2008.4594760.
• [15] Sedgwick P. Pearsons correlation coefficient. BMJ. 2012 Jul 4; 345:e4483. URL https://doi.org/10.1136/bmj.e4483.
• [16] Dasgupta A, Das R, Nayak L, De RK. Analyzing epileptogenic brain connectivity networks using clinical EEG data. In: 2015 International Conference on Bioinformatics and Biomedicine (BIBM). IEEE, 2015 Nov 9 (pp. 815-821). DOI: 10.1109/BIBM.2015.7359791.
• [17] Peng H, Long F, Ding C. Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2005 Aug 1; (8):1226-1238. DOI: 10.1109/TPAMI.2005.159.
• [18] Mika S, Ratsch G, Weston J, Scholkopf B, Mullers KR. Fisher discriminant analysis with kernels. In: Neural Networks for Signal Processing IX: Proceedings of the 1999 IEEE Signal Processing Society Workshop (cat. no. 98th8468). IEEE, 1999 Aug 25 (pp. 41-48). DOI: 10.1109/NNSP.1999.788116.
• [19] Zhou N, Wang L. A modified T-test feature selection method and its application on the HapMap genotype data. Genomics, Proteomics & Bioinformatics. 2007 Jan 1; 5(3-4):242-249. URL https://doi.org/10.1016/S1672-0229(08)60011-X.
• [20] Park H, Kwon S, Kwon HC. editor. Complete gini-index text (git) feature-selection algorithm for text classification. In: The 2nd International Conference on Software Engineering and Data Mining (SEDM). IEEE 2010 Jun 23 (pp. 366-371). ISBN: 978-1-4244-7324-3.
• [21] Urbanowicz RJ, Meeker M, La Cava W, Olson RS, Moore JH. Relief-based feature selection: introduction and review. Journal of Biomedical Informatics. 2018 Sep 1; 85:189-203. URL https://doi.org/10.1016/j.jbi.2018.07.014.
• [22] Wang L, Zhang Z, Design CX. Theory and applications. Support Vector Machines, volume 177. Springer Science & Business Media, 2005. ISBN 978-3-540-24388-5.
• [23] Priyadarsini RP, Valarmathi M, Sivakumari S. Gain ratio based feature selection method for privacy preservation. ICTACT Journal on soft computing. 2011 Apr; 1(4):201-205. DOI: 10.21917/ijsc.2011.0031.
• [24] Chen YT, Chen MC. Using chi-square statistics to measure similarities for text categorization. Expert Systems with Applications. 2011 Apr 1; 38(4):3085-3090. URL https://doi.org/10.1016/j.eswa.2010.08.100.
• [25] Luukka P. Feature selection using fuzzy entropy measures with similarity classifier. Expert Systems with Applications. 2011 Apr 1; 38(4):4600-4607. URL https://doi.org/10.1016/j.eswa.2010.09.133.
• [26] Saeys Y, Inza I, Larrañaga P. A review of feature selection techniques in bioinformatics. Bioinformatics. 2007 Oct 1; 23(19):2507-2517. URL https://doi.org/10.1093/bioinformatics/btm344.
• [27] Shang W, Huang H, Zhu H, Lin Y, Qu Y, Wang Z. A novel feature selection algorithm for text categorization. Expert Systems with Applications. 2007 Jul 1; 33(1):1-5. URL https://doi.org/10.1016/j.eswa.2006.04.001.
• [28] Liu H, Motoda H., editors. Computational methods of feature selection. CRC Press; 2007 Oct 29. ISBN:13:978-1-58488-879-6.
• [29] Yingwei L, Sundararajan N, Saratchandran P. Performance evaluation of a sequential minimal radial basis function (RBF) neural network learning algorithm. IEEE Transactions on Neural Networks. 1998 Mar; 9(2):308-318. DOI: 10.1109/72.661125.
• [30] Liaw A, Wiener M. Classification and regression by random Forest. R News, 2002. 2(3):18-22.
• [31] Orhan U, Hekim M, Ozer M. EEG signals classification using the K-means clustering and a multilayer perceptron neural network model. Expert Systems with Applications. 2011 Sep 15; 38(10):13475-13481. URL https://doi.org/10.1016/j.eswa.2011.04.149.
• [32] Schuster I, Jähnichen P. Classification using Logistic Regression. Universität Lepzig, 2012. URL http://asv.informatik.uni-leipzig.de/uploads/document/file\_link/530/TMI05.2\_logistic\_regression.pdf.
• [33] Genkin A, Lewis DD, Madigan D. Large-scale Bayesian logistic regression for text categorization. Technometrics. 2007 Aug 1; 49(3):291-304. DOI: 10.1198/004017007000000245.
• [34] Rodriguez JJ, Kuncheva LI, Alonso CJ. Rotation forest: A new classifier ensemble method. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2006 Aug 21; 28(10):1619-1630. DOI: 10.1109/TPAMI.2006.211.
• [35] Bernardo J, Berger J, Dawid A, Smith A, et al. Regression and classification using Gaussian process priors. Bayesian Statistics. 1998 Jun 6; 6:475. ISBN: 0198504853, 9780198504856.
• [36] Witten IH, Frank E, Hall MA, Pal CJ. Data Mining: Practical machine learning tools and techniques. Morgan Kaufmann; 2016 Oct 1. ISBN: 0128043571, 9780128043578.
• [37] Mika S, Ratsch G, Weston J, Scholkopf B, Mullers KR. Fisher discriminant analysis with kernels. In: Neural networks for signal processing IX: Proceedings of the 1999 IEEE signal processing society workshop (cat. no. 98th8468). IEEE 1999 Aug 25 (pp. 41-48). ISBN: 0-7803-5673-X.
• [38] Weinberger KQ, Saul LK. Distance metric learning for large margin nearest neighbor classification. Journal of Machine Learning Research. 2009; 10(Feb):207-244. URL http://www.jmlr.org/papers/volume10/weinberger09a/weinberger09a.pdf.
• [39] Kukreja M, Johnston SA, Stafford P. Comparative study of classification algorithms for immunosignaturing data. BMC bioinformatics. 2012 Dec; 13(1):139. URL https://doi.org/10.1186/1471-2105-13-139.
• [40] McCallum A, Nigam K. A comparison of event models for naive bayes text classification. In: AAAI-98 workshop on learning for text categorization. 1998 Jul 26; (vol. 752, No. 1, pp. 41-48). URL http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.65.9324&rep=rep1&type=pdf.
• [41] Agarwal R, Srikant R. Fast algorithms for mining association rules. In: Proceedings of the 20th VLDB Conference. 1994 (Vol, 1215, pp. 487-499). ISBN: 1-55860-238-0.
• [42] Han J, Pei J, Yin Y. Mining frequent patterns without candidate generation. In: ACM Sigmod Record 2000 May 16 (vol. 29, No. 2, pp. 1-12). ISBN: 1-58113-217-4.
• [43] Song M, Rajasekaran S. A transaction mapping algorithm for frequent itemsets mining. IEEE transactions on knowledge and data engineering. 2006 Feb 27; 18(4):472-481. DOI: 10.1109/TKDE.2006.1599386.
• [44] Hoseini MS, Shahraki MN, Neysiani BS. A new algorithm for mining frequent patterns in Can Tree. In: 2015 2nd International Conference on Knowledge-Based Engineering and Innovation (KBEI). IEEE, 2015 Nov 5 (pp. 843-846).
• [45] Zaki MJ. Scalable algorithms for association mining. IEEE transactions on knowledge and data engineering. 2000 May;. 12(3):372-390. DOI: 10.1109/69.846291.
• [46] Agarwal RC, Aggarwal CC, Prasad VVV. A tree projection algorithm for generation of frequent item sets. Journal of parallel and Distributed Computing. 2001 Mar 1; 61(3):350-371. URL https://doi.org/10.1006/jpdc.2000.1693.
• [47] Győrödi C, Győrödi R, Holban S. A comparative study of association rules mining algorithms. In: SACI 2004, 1st Romanian-Hungarian Joint Symposium on Applied Computational Intelligence. 2004 (pp. 213-222). URL http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.123.2771&rep=rep1&type=pdf.
• [48] Bonchi F, Goethals B. FP-Bonsai: the art of growing and pruning small fp-trees. In: Pacific-Asia Conference on Knowledge Discovery and Data Mining. Springer, 2004 May 26 (pp. 155-160). URL https://doi.org/10.1007/978-3-540-24775-3_19.
• [49] Borgelt C. Keeping things simple: finding frequent item sets by recursive elimination. In: Proceedings of the 1st international workshop on open source data mining: frequent pattern mining implementations. ACM, 2005 Aug 21 (pp. 66-70).
• [50] Chee CH, Jaafar J, Aziz IA, Hasan MH, Yeoh W. Algorithms for frequent itemset mining: a literature review. Artificial Intelligence Review. 2019 Dec 1; 52(4):2603-2621. URL https://doi.org/10.1007/s10462-018-9629-z.
• [51] Qodmanan HR, Nasiri M, Minaei-Bidgoli B. Multi objective association rule mining with genetic algorithm without specifying minimum support and minimum confidence. Expert Systems with Applications. 2011 Jan 1; 38(1):288-298. URL https://doi.org/10.1016/j.eswa.2010.06.060.
• [52] Khalid M. Intelligent traffic lights control by fuzzy logic. Malaysian Journal of Computer Science. 1996 Dec 1; 9(2):29-35. URL https://ejournal.um.edu.my/index.php/MJCS/article/view/2995.
• [53] Riordan D, Hansen BK. A fuzzy case-based system for weather prediction. Engineering Intelligent Systems for Electrical Engineering and Communications. 2002 Sep 1; 10(3):139-146. URL https://pdfs.semanticscholar.org/0719/a63450701017c89bfe3d60800485ae72c76b.pdf.
• [54] Woolf PJ, Wang Y. A fuzzy logic approach to analyzing gene expression data. Physiological Genomics. 2000 Jun 29; 3(1):9-15. URL https://doi.org/10.1152/physiolgenomics.2000.3.1.9.
• [55] Arqub OA. Adaptation of reproducing kernel algorithm for solving fuzzy Fredholm-Volterra integrodifferential equations. Neural Computing and Applications. 2017 Jun 1; 28(7):1591-1610. URL https://doi.org/10.1007/s00521-015-2110-x.
• [56] Arqub OA, Mohammed AS, Momani S, Hayat T. Numerical solutions of fuzzy differential equations using reproducing kernel Hilbert space method. Soft Computing. 2016 Aug 1; 20(8):3283-3302. URL https://doi.org/10.1007/s00500-015-1707-4.
• [57] Arqub OA, Al-Smadi M, Momani S, Hayat T. Application of reproducing kernel algorithm for solving second-order, two-point fuzzy boundary value problems. Soft Computing. 2017 Dec 1; 21(23):7191-7206. URL https://doi.org/10.1007/s00500-016-2262-3.
• [58] Hühn J, Hüllermeier E. FURIA: an algorithm for unordered fuzzy rule induction. Data Mining and Knowledge Discovery. 2009 Dec 1; 19(3):293-319. URL https://doi.org/10.1007/s10618-009-0131-8.
• [59] Chen CH, Li AF, Lee YC. A fuzzy coherent rule mining algorithm. Applied Soft Computing. 2013 JUl 1; 13(7):3422-3428. URL https://doi.org/10.1016/j.asoc.2012.12.031.
• [60] Eineborg M, Boström H. Classifying uncovered examples by rule stretching. In: International Conference on Inductive Logic Programming. Springer, 2001 Sep 9 (pp. 41-50). URL https://doi.org/10.1007/3-540-44797-0_4.
• [61] Dasgupta A, Nayak L, Das R, Basu D, Chandra P, De RK. Feature Selection and Fuzzy Rule Mining for Epileptic Patients from Clinical EEG Data. In: International Conference on Pattern Recognition and Machine Intelligence, Kolkata. Springer, 2017 Dec 5 (pp. 87-95). URL https://doi.org/10.1007/978-3-319-69900-4_11.
• [62] Hühn JC, Hüllermeier E. An analysis of the FURIA algorithm for fuzzy rule induction. In: Advances in machine learning I. Springer 2010 (pp. 321-344). URL https://doi.org/10.1007/978-3-642-05177-7_16.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).