PDF herunterladen
Appl Clin Inform 2016; 07(01): 1-21
DOI: 10.4338/ACI-2015-08-RA-0102
Research Article
Schattauer GmbH

A Temporal Mining Framework for Classifying Un-Evenly Spaced Clinical Data

An Approach for Building Effective Clinical Decision-Making System
Nancy Yesudhas Jane
1   Ramanujan Computing Centre, Anna University, Chennai, India
,
Khanna Harichandran Nehemiah
1   Ramanujan Computing Centre, Anna University, Chennai, India
,
Kannan Arputharaj
2   Department of Information Science and Technology, Anna University, Chennai, India
› Institutsangaben
Weitere Informationen

Publikationsverlauf

received: 19. August 2015

accepted: 08. Januar 2015

Publikationsdatum:
16. Dezember 2017 (online)

   Lizenzen und Reprints

Summary

Background

Clinical time-series data acquired from electronic health records (EHR) are liable to temporal complexities such as irregular observations, missing values and time constrained attributes that make the knowledge discovery process challenging.

Objective

This paper presents a temporal rough set induced neuro-fuzzy (TRiNF) mining framework that handles these complexities and builds an effective clinical decision-making system. TRiNF provides two functionalities namely temporal data acquisition (TDA) and temporal classification.

Method

In TDA, a time-series forecasting model is constructed by adopting an improved double exponential smoothing method. The forecasting model is used in missing value imputation and temporal pattern extraction. The relevant attributes are selected using a temporal pattern based rough set approach. In temporal classification, a classification model is built with the selected attributes using a temporal pattern induced neuro-fuzzy classifier.

Result

For experimentation, this work uses two clinical time series dataset of hepatitis and thrombosis patients. The experimental result shows that with the proposed TRiNF framework, there is a significant reduction in the error rate, thereby obtaining the classification accuracy on an average of 92.59% for hepatitis and 91.69% for thrombosis dataset.

Conclusion

The obtained classification results prove the efficiency of the proposed framework in terms of its improved classification accuracy.

Keywords

Clinical time-series data - temporal mining - temporal data acquisition - rough set - neuro-fuzzy
 

  • References

  • 1 Augusto JC. Temporal reasoning for decision support in medicine. Artificial Intelligence in Medicine 2005; 33 (01) 1-24.
    CrossrefPubMedGoogle Scholar
  • 2 Bellazzi R, Zupan B. Predictive data mining in clinical medicine: current issues and guidelines. International Journal of Medical Informatics 2008; 77 (02) 81-97.
    CrossrefPubMedGoogle Scholar
  • 3 Adlassnig KP, Combi C, Das AK, Keravnou ET, Pozzi G. Temporal representation and reasoning in medicine: Research directions and challenges. Artificial Intelligence in Medicine 2006; 38 (02) 101-113.
    CrossrefPubMedGoogle Scholar
  • 4 Carrault G, Cordier MO, Quiniou R, Wang F. Temporal abstraction and inductive logic programming for arrhythmia recognition from electrocardiograms. Artificial Intelligence in Medicine 2003; 28 (03) 231-63.
    CrossrefPubMedGoogle Scholar
  • 5 Keravnou E, Shahar Y. Temporal Reasoning in Medicine. in Fisher MD. et al. Handbook of Temporal Reasoning in Artificial Intelligence. Elsevier; 2005: 587-653.
    Google Scholar
  • 6 Kalia O, Athena S, Elpida K. Temporal abstraction and temporal Bayesian networks in clinical domains: A survey. Artificial Intelligence in Medicine 2014; 60 (03) 133-149.
    CrossrefPubMedGoogle Scholar
  • 7 Chittaro L, Montanari A. Temporal representation and reasoning in artificial intelligence: issues and approaches. Annals of Mathematics and Artificial Intelligence 2000; 28 1–4 47-106.
    CrossrefPubMedGoogle Scholar
  • 8 Miguel RA, Paulo F. Purificación Cariñena: Discovering Metric Temporal Constraint Networks On Temporal Databases. Artificial Intelligence in Medicine 2013; 58 (03) 139-154.
    CrossrefPubMedGoogle Scholar
  • 9 Wright DJ. Forecasting data published at irregular time intervals using extension of Holt’s method. Management Science 1986; 32 (04) 499-510.
    CrossrefPubMedGoogle Scholar
  • 10 Shahar Y. A framework for knowledge-based temporal abstraction. Artificial intelligence 1997; 90 (01) 79-133.
    CrossrefPubMedGoogle Scholar
  • 11 Combi C, Shahar Y. Temporal reasoning and temporal data maintenance in medicine: Issues and challenges. Computers in Biology and Medicine 1997; 27 (05) 353-368.
    CrossrefPubMedGoogle Scholar
  • 12 Stacey M, McGregor C. Temporal abstraction in intelligent clinical data analysis: A survey. Artificial Intelligence in Medicine 2006; 39: 1-24.
    PubMedGoogle Scholar
  • 13 Shahar Y, Musen MA. Knowledge-based temporal abstraction in clinical domains. Artificial Intelligence in Medicine 1996; 08: 267-298.
    CrossrefPubMedGoogle Scholar
  • 14 Haimowitz IJ, Kohane IS. Managing temporal worlds for medical trend diagnosis. Artificial Intelligence in Medicine 1996; 08: 299-321.
    CrossrefPubMedGoogle Scholar
  • 15 Miksch S, Horn W, Popow C, Paky F. Utilizing temporal data abstraction for data validation and therapy planning for artificially ventilated new born infants. Artificial Intelligence in Medicine 1996; 08: 543-576.
    CrossrefPubMedGoogle Scholar
  • 16 Semrl A. Real time monitoring of dense continuous data. In: Presented at computers in anaesthesia and intensive care: Knowledge based information management 1999
    PubMedGoogle Scholar
  • 17 O’Connor MJ, Grosso WE, Tu SW, Musen MA. RASTA: a distributed temporal abstraction system to facilitate knowledge-driven monitoring of clinical databases. MedInfo2001 2001; 10: 508-512.
    PubMedGoogle Scholar
  • 18 Tu Bao H, Trong NDung, Saori K, Si Quang L, DungDuc N, Hideto Y, Katsuhiko T. Mining Hepatitis Data with Temporal Abstraction. KDD ‘03 Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining 2003; 69-377.
    PubMedGoogle Scholar
  • 19 Moskovitch R, Shahar Y. Classification of multivariate time series via temporal abstraction and time intervals mining. Knowledge and Information Systems 2014; 42 (01) 1-40.
    CrossrefPubMedGoogle Scholar
  • 20 Iyad Batal, Hamed Valizadegan, Cooper Gregory F, Hauskrecht Milos. A Temporal Pattern Mining Approach for Classifying Electronic Health Record Data. ACM Trans Intelligent System Technologies. 2013 04. 4
    PubMedGoogle Scholar
  • 21 Moerchen F. Algorithms for time series knowledge mining. Proceedings of the international conference on Knowledge Discovery and Data mining (SIGKDD) 2006; 668-673.
    PubMedGoogle Scholar
  • 22 Allen JF. Maintaining knowledge about temporal intervals. Communications of the ACM 1983; 26 (11) 832-843.
    CrossrefPubMedGoogle Scholar
  • 23 Bodyanskiy Y, Kolodyazhniy V, Otto P. Neuro-Fuzzy Kolmogorov’s Network for Time Series Prediction and Pattern Classification. in Furbach Ulrich. ed ‘KI’. Springer; 2005. 3698 191-202.
    Google Scholar
  • 24 Petkovic D, Ojbasic ZC, Lukic S. Adaptive neuro fuzzy selection of heart rate variability parameters affected by autonomic nervous system. Expert Systems with Applications 2013; 11: 4490-4495.
    PubMedGoogle Scholar
  • 25 Jang JSR, Sun CT, Mizutani E. Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence. Prentice Hall, Inc; 1996
    Google Scholar
  • 26 McNameea RL, Sunb M, Sclabassi R. A neuro-fuzzy inference system for modeling and prediction of heart rate variability in the neuro-intensive care unit. Computers in Biology and Medicine 2005; 35: 875-89.
    CrossrefPubMedGoogle Scholar
  • 27 Khanna HNehemiah, Kannan A, Vijaya K, Nancy YJane, Brindha JMerin. Intelligent Rule Mining for Decision Making from Clinical Data Sets. ICGST International Journal on Bioinformatics and Medical Engineering 2007; 07: 37-45.
    PubMedGoogle Scholar
  • 28 Hepatitis Dataset for Discovery Challenge. European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases. 16th ECML + 9th PKDD Conference, October 3–10, Porto, Portugal: http://lisp.vse.cz/challenge/ecmlpkdd2005/ (Accessed: 1 Jan 2006).
    PubMedGoogle Scholar
  • 29 Thrombosis Dataset for Discovery Challenge. 3rd European Conference on Principles and Practice of Knowledge Discovery in Databases. September 15–18, 1999 Prague: Czech Republic. http://lisp.vse.cz/pkdd99/ (Accessed: 1 Jan 2006).
    PubMedGoogle Scholar
  • 30 Vijaya K, Khanna HNehemiah, Kannan A, Bhuvaneswari NGAmma. Fuzzy Neuro Genetic Approach for Predicting the Risk of Cardiovascular Diseases. International Journal of Data Mining, Modelling and Management 2010; 02 (04) 388-402.
    CrossrefPubMedGoogle Scholar
  • 31 Kindie NahatoBiredagn, Khanna HarichandranNehemiah, Kannan Arputharaj. Knowledge Mining from Clinical Datasets Using Rough Sets and Back propagation Neural Network. Computational and Mathematical Methods in Medicine. 2015
    PubMedGoogle Scholar
  • 32 Liu Zitao, Milos Hauskrecht. Clinical time series prediction: Toward a hierarchical dynamical system framework. Artificial intelligence in medicine. 2014
    PubMedGoogle Scholar
  • 33 Kalman RE. Mathematical description of linear dynamical systems. J Soc IndAppl Math Ser A: Control 1963; 01 (02) 152-192.
    PubMedGoogle Scholar
  • 34 Rasmussen CE, Williams CKI. Gaussian processes for machine learning. Cambridge, MA, USA: MIT Press; 2006
    Google Scholar
  • 35 Pandit SM, Wu S-M. Time series and system analysis with applications. NewYork, USA: Wiley; 1983. 56 21 389-405.
    Google Scholar
  • 36 Adorf HM. Interpolation of irregularly sampled data series – a survey. In: Astro-nomical Data Analysis Software and Systems IV 1995; 77: 460-463.
    PubMedGoogle Scholar
  • 37 Dezhbakhsh H, Levy D. Periodic properties of interpolated time series. EconLett 1994; 44 (03) 221-8.
    PubMedGoogle Scholar
  • 38 Kreindler DM, Lumsden CJ. The effects of the irregular sample and missing data in time series analysis. Nonlinear Dyn Psychol Life Sci 2006; 10 (02) 187-214.
    PubMedGoogle Scholar
  • 39 Rehfeld K, Marwan N, Heitzig J, Kurths J. Comparison of correlation analysis techniques for irregularly sampled time series. Nonlinear Process Geophys 2011; 18 (03) 389-404.
    CrossrefPubMedGoogle Scholar
  • 40 Chu C-SJ. Time series segmentation: a sliding window approach. Inf Sci 1995; 85 (01) 147-173.
    CrossrefPubMedGoogle Scholar
  • 41 Keogh E, Chakrabarti K, Pazzani M, Mehrotra S. Dimensionality reductionfor fast similarity search in large time series databases. Knowl Inf Syst 2001; 03 (03) 263-286.
    CrossrefPubMedGoogle Scholar
  • 42 Bahadori Mohammad Taha, Yan Liu. Granger Causality Analysis in Irregular Time Series. SDM; 2012
    Google Scholar
  • 43 Cuevas-Tello J C, Tino P, Raychaudhury S, Yao S, Harva M. Uncovering delayed patterns in noisy and irregularly sampled time series: an astronomy application. Pattern Recognition 2009; 43 (03) 36.
    PubMedGoogle Scholar
  • 44 Scargle JD. Studies in astronomical time series analysis. I – Modeling random processes in the time domain. The Astrophysical Journal Supplement Series 1981; 45 (01) 1-71.
    CrossrefPubMedGoogle Scholar
  • 45 Ceusters W, Smith B. Strategies for referent tracking in electronic health records. J Biomed Inform 2006; 39 (03) 362-378.
    CrossrefPubMedGoogle Scholar
  • 46 Ohsaki M, Sato Y, Yokoi H, Yamaguchi T. A Rule Discovery Support System for Sequential Medical Data. In the Case Study of a Chronic Hepatitis Dataset. International Workshop on Active Mining. IEEE International Conference on Data Mining ICDM; Maebashi: 2002: 97-102.
    Google Scholar
  • 47 Jensen S. Mining Medical Data for Predictive and Sequential Patterns Discovery Challenge on Thrombosis Data. Freiburg. 2001
    Google Scholar
  • 48 Zytkow J, Tsumoto S, Takabayashi K. Medical (Thrombosis) Data Description. In: Siebes A, Berka P. PKDD2000 Discovery Challenge; Lyon: 2000
    Google Scholar
  • 49 Zytkow J, Gupta S. Guide to Medical Data on Collagen Disease and Thrombosis. In: Berka P. PKDD2001 Discovery Challenge on Thrombosis Data; Freiburg: 2000
    Google Scholar
  • 50 Little RJA, Rubin DB. Statistical analysis with missing data. Wiley; 2nd edition. 2002
    Google Scholar
  • 51 Enders C. Applied missing data analysis. Guilford, New York: 2010
    Google Scholar
  • 52 Holt CC. Forecasting seasonals and trends by exponentially weighted moving averages. International Journal of Forecasting 2004; 20 (01) 5-10.
    CrossrefPubMedGoogle Scholar
  • 53 Han J, Kamber M. Data Mining, Concepts and Techniques. 2nd ed. Morgan Kaufmann Publishers Inc; San Francisco. CA. USA: 2001
    Google Scholar
  • 54 Pawlak Z. Roughsets. International J Comp Inf Sci 1982; 11 (05) 341-356.
    PubMedGoogle Scholar
  • 55 Dash M, Liu H. Attribute Selection for Classification. Intelligent Data Analysis An International Journal 1997; 01 1–4 131-156.
    PubMedGoogle Scholar
  • 56 Komorowski J, Zdzislaw Pawlak, Lech Polkowski, Andrzej Skowron. Rough Sets Perspective on Data and Knowledge. in Pawlak Z. (Eds). et al. The Handbook of Data Mining and Knowledge Discovery. 1999: 134-149.
    Google Scholar
  • 57 Jensen Richard, Qiang Shen. Rough set based attribute selection: A review. Rough Computing: Theories, Technologies and Applications 2007; 70-107.
    PubMedGoogle Scholar
  • 58 Chouchoulas A, Shen Q. Rough set-aided keyword reduction for text categorisation. Applied Artificial Intelligence 2001; 15 (09) 843-873.
    CrossrefPubMedGoogle Scholar
  • 59 Pradipta M. ParthaGarai Fuzzy-Rough Simultaneous Attribute Selection and Attribute Extraction Algorithm. IEEE Trans. Cybernetics 2013; 43 (04) 1166-1177.
    PubMedGoogle Scholar
  • 60 Breiman L, Friedman J, Olshen R, Stone C. Classification and Regression Trees. Wadsworth International Group; 1984
    Google Scholar
  • 61 Cooray TMJA. Applied Time Series: Analysis and Forecasting. Alpha Science International Limited Oxford; 2008
    Google Scholar
  • 62 Zimmerman Donald W. A Note on Interpretation of the Paired-Samples t Test. Journal of Educational and Behavioral Statistics 1997; 22 (03) 349-360.
    PubMedGoogle Scholar
  • 63 Ohrn A, Komorowski J, Skowron A, Synak P. The Design and Implementation of a Knowledge Discovery Toolkit Based on Rough Sets – The Rosetta system. In: Polkowski and Skowron 1998; 76-399.
    PubMedGoogle Scholar
  • 64 Demuth H, Beale M. Neural network toolbox for use with MATLAB. Users guide. http://www.mathworks.com Edition. The Math Works Inc; 2013
    PubMedGoogle Scholar
  • 65 Gabrys B, Burgiela A. General fuzzy min-max neural network for clustering and classification. IEEE Trans. Neural Networks 2000; 11 (03) 769-783.
    CrossrefPubMedGoogle Scholar
  • 66 Quinlan JR. Induction of decision trees. Machine Learning 1986; 01 (01) 81-106.
    PubMedGoogle Scholar
  • 67 Quinlan JR. C4.5: Programs for Machine Learning. Morgan Kaufmann Los Altos. 1993
    PubMedGoogle Scholar
  • 68 Xiao-Hua Zhou, Nancy A, Obuchowski McClish Donna K. Statistical Methods in Diagnostic Medicine. 2nd Edition. New York: Wiley; March 2011
    Google Scholar
  • 69 Wilcoxon F. Individual comparisons by ranking methods. Biometrics 1945; 01 (06) 80-83.
    PubMedGoogle Scholar