Abstract
A machine learning (ML)-based text classification system has several classifiers. The performance evaluation (PE) of the ML system is typically driven by the training data size and the partition protocols used. Such systems lead to low accuracy because the text classification systems lack the ability to model the input text data in terms of noise characteristics. This research study proposes a concept of misrepresentation ratio (MRR) on input healthcare text data and models the PE criteria for validating the hypothesis. Further, such a novel system provides a platform to amalgamate several attributes of the ML system such as: data size, classifier type, partitioning protocol and percentage MRR. Our comprehensive data analysis consisted of five types of text data sets (TwitterA, WebKB4, Disease, Reuters (R8), and SMS); five kinds of classifiers (support vector machine with linear kernel (SVM-L), MLP-based neural network, AdaBoost, stochastic gradient descent and decision tree); and five types of training protocols (K2, K4, K5, K10 and JK). Using the decreasing order of MRR, our ML system demonstrates the mean classification accuracies as: 70.13 ± 0.15%, 87.34 ± 0.06%, 93.73 ± 0.03%, 94.45 ± 0.03% and 97.83 ± 0.01%, respectively, using all the classifiers and protocols. The corresponding AUC is 0.98 for SMS data using Multi-Layer Perceptron (MLP) based neural network. All the classifiers, the best accuracy of 91.84 ± 0.04% is shown to be of MLP-based neural network and this is 6% better over previously published. Further we observed that as MRR decreases, the system robustness increases and validated by standard deviations. The overall text system accuracy using all data types, classifiers, protocols is 89%, thereby showing the entire ML system to be novel, robust and unique. The system is also tested for stability and reliability.
Similar content being viewed by others
References
Rico, T. M., dos Santos Machado, K., Fernandes, V. P., Madruga, S. W., Noguez, P. T., Barcelos, C. R. G., and Dumith, S. C., Text messaging (SMS) helping cancer care in patients undergoing chemotherapy treatment: a Pilot study. J. Med. Syst. 41(11):181, 2017.
Lee, K., Agrawal, A., and Choudhary, A., Real-time disease surveillance using twitter data: demonstration on flu and cancer. In Proceedings of the 19th ACM SIGKDD international conference on knowledge discovery and data mining, 1474-1477, 2013.
Rios-Alvarado, A. B., Lopez-Arevalo, I., Tello-Leal, E., and Sosa-Sosa, V. J., An approach for learning expressive ontologies in medical domain. J. Med. Syst. 39(8):75, 2015.
Li, G. Z., Yang, J., Liu, G. P., and Xue, L., Feature selection for multi-class problems using support vector machines. In PRICAI, 292-300, 2004.
Vahdat, S., Hamzehgardeshi, L., Hessam, S., and Hamzehgardeshi, Z., Patient involvement in health care decision making: a review. Iran Red Crescent Med. J. 16(1):1–7, 2014.
Acharya, U. R., Faust, O., Sree, S. V., Molinari, F., Saba, L., Nicolaides, A., and Suri, J. S., An accurate and generalized approach to plaque characterization in 346 carotid ultrasound scans. IEEE Trans. Instrum. Measure. 61(4):1045–1053, 2012.
Acharya, U. R., Sree, S. V., Saba, L., Molinari, F., Guerriero, S., and Suri, J. S., Ovarian tumor characterization and classification using ultrasound—a new online paradigm. J. Digit. Imaging 26(3):544–553, 2013.
Kautz, T., Eskofier, B. M., and Pasluosta, C. F., Generic performance measure for multiclass-classifiers. Pattern Recogn. 68:111–125, 2017.
Japkowicz, N., and Shah, M., Evaluating learning algorithms: a classification perspective. Cambridge University Press. 2011.
Sokolova, M., and Lapalme, G., A systematic analysis of performance measures for classification tasks. Inform. Process. Manag. 45(4):427–437, 2009.
Huang, J., and Ling, C. X., Constructing new and better evaluation measures for machine learning. In IJCAI, 859-864, 2007.
Wong, A. K., Lee, J. W., and Yeung, D. S., Improving text classifier performance based on AUC. In Pattern Recognition, 2006. ICPR 2006. 18 th , 1-4, 2006.
Iwata, T., Tanaka, T., Yamada, T., and Ueda, N., Improving classifier performance using data with different taxonomies. IEEE Trans. Knowledge Data Eng. 23(11):1668–1677, 2011.
Sriram, B., Fuhry, D., Demir, E., Ferhatosmanoglu, H., and Demirbas, M., Short text classification in twitter to improve information filtering. In Proceedings of the33rd international ACM SIGIR conference on Research and development in information retrieval, 841-842, 2010.
Caragea, C., Wu, J., Gollapalli, S. D., and Giles, C. L., Document Type Classification in Online Digital Libraries. AAAI, 3997-4002, 2016.
Shrivastava, V. K., Londhe, N. D., Sonawane, R. S., and Suri, J. S., Reliable and accurate psoriasis disease classification in dermatology images using comprehensive feature space in machine learning paradigm. Expert Syst. Appl. 42(15):6184–6195, 2015.
Shrivastava, V. K., Londhe, N. D., Sonawane, R. S., and Suri, J. S., Computer- aided diagnosis of psoriasis skin images with HOS, texture and color features: a first comparative study of its kind. Comput. Methods Prog. Biomed. 126:98–109, 2016.
Cormack, G. V., Gómez Hidalgo, J. M., and Sánz, E. P., Spam filtering for short messages. In Proceedings of the sixteenth ACM conference on Conference on information and knowledge management, 313-320, 2007.
Liang, J. G., Zhou, X. F., Liu, P., Guo, L., and Bai, S., An EMM-based Approach for Text Classification. Proc. Comput. Sci. 17:506–513, 2013.
Lu, C., Zhang, X., Park, J. R., Hu, X., & He, T., Web clustering based on the information of sibling pages. In Granular Computing, 2008. GrC 2008. IEEE International Conference, 480–485, 2008.
Tuarob, S., Tucker, C. S., Salathe, M., and Ram, N., An ensemble heterogeneous classification methodology for discovering health-related knowledge in social media messages. J. Biomed. Inform. 49:255–268, 2014.
Roesslein, J. (2009). tweepy documentation. Online http://tweepy.readthedocs.io/en/v3 , 5.
Velardi, P., Stilo, G., Tozzi, A. E., and Gesualdo, F., Twitter mining for fine- grained syndromic surveillance. Artif. Intell. Med. 61(3):153–163, 2014.
Srivastava, S. K., and Singh, S. K., Multi-Parameter Based Performance Evaluation Of Classification Algorithms. Int. J. Comput Sci. Inform. Technol. (IJCSIT) 7:115–125, 2015.
Acharya, U. R., Mookiah, M. R. K., Sree, S. V., Afonso, D., Sanches, J., Shafique, S., and Suri, J. S., Atherosclerotic plaque tissue characterization in 2D ultrasound longitudinal carotid scans for automated classification: a paradigm for stroke risk assessment. Med Biol. Eng. Comput. 51(5):513–523, 2013.
Sanchez, A., and V. D., Advanced support vector machines and kernel methods. Neurocomputing 55(1–2):5–20, 2003.
Muller, K. R., Mika, S., Ratsch, G., Tsuda, K., and Scholkopf, B., An introduction to kernel-based learning algorithms. IEEE Trans. Neural Netw. 12(2):181–201, 2001.
Acharya, R. U., Faust, O., Alvin, A. P. C., Sree, S. V., Molinari, F., Saba, L., and Suri, J. S., Symptomatic vs. asymptomatic plaque classification in carotid ultrasound. J. Med. Syst. 36(3):1861–1871, 2012.
Chakravarty, S. (2011). Stochastic Gradient Descent Methods for large scale pattern classification.
Martineau, J., and Finin, T., Delta TFIDF: an improved feature space for sentiment analysis. Icwsm 9:106, 2009.
Robert, M. H., & Linda, G. S., Computer and robot vision. Vol. I, Addison-Wesley, 28–48, 1992.
Suri, J. S., Haralick, R. M., and Sheehan, F.H., Left ventricle longitudinal axis fitting and its apex estimation using a robust algorithm and its performance: a parametric apex model. In Image Processing, 1997. Proceedings., International Conference on (Vol. 3, pp. 118-121). IEEE, 1997.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Declaration of Conflicting Interests
The author(s) declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.
Additional information
This article is part of the Topical Collection on Education & Training
Appendices
Appendix A: Types of Dataset used in the study
A.1. TwitterA Dataset
A.2. WebKB4 Dataset
A.3. Disease Dataset
A.4. Reuters (R8) Dataset
A.5. SMS Dataset
Appendix B: Labels used in different text data types
Appendix C: ROC Curves
C1: ROC curves for K2 protocol using five classifier
C2: ROC curves for K4 protocol using five classifier
C3: ROC curves for K5 protocol using five classifier
C4: ROC curves for K10 protocol using five classifier
C5: ROC curves for JK protocol using five classifier
Appendix D: AUC Tables
Appendix E: Postive Predictive Value Tables
Appendix F: Sensitivity Tables
Appendix G: Specificity Tables
Appendix H: List of Abbreviations/Symbols
Rights and permissions
About this article
Cite this article
Srivastava, S.K., Singh, S.K. & Suri, J.S. Healthcare Text Classification System and its Performance Evaluation: A Source of Better Intelligence by Characterizing Healthcare Text. J Med Syst 42, 97 (2018). https://doi.org/10.1007/s10916-018-0941-6
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10916-018-0941-6