A Rough Set and Cellular Genetic Fusion Algorithm for Acute Critical Disease Prediction

  • Hongxin Wang
  • Lijing Jia
  • Heng Zhuang
  • Xueyan Li
  • Yuzhuo Zhao
  • Shuxiao Pan
  • Kainan Wu
  • Jing Li Department of School of Economics and Management, Beijing Jiaotong University
  • Tanshi Li

Abstract

This study is to solve the problems of an overly-broad scale of medical indicators, lack of retrospective research samples, insufficient depth of data mining, and low disease prediction accuracy. In this paper, we propose an intelligent screening algorithm that combines a genetic algorithm, cellular automata, and rough set theory. This algorithm can achieve high accuracy in predicting patient outcomes with a small number of indicators. And we compare it with the traditional genetic algorithm. We built the prediction model with 64 indicators based on the logistic regression (AUC 0.8628), support vector machine (AUC 0.5319), Naïve Bayes (AUC 0.7102), and AdaBoost algorithms (AUC 0.9095). Using the cellular genetic algorithm for attribute screening not only effectively reduces the number of indicators but also achieve almost the same accuracy of prediction with 8 indicators based on the logistic regression (AUC 0.8782), support vector machine (AUC 0.8525), Naïve Bayes (AUC 0.8408), and AdaBoost algorithms (AUC 0.8770). Compared with the traditional scoring system, the predictive model established in this paper can more accurately predict rebleeding accidents based on physiological test indicators and continuous patient indicators.

Author Biographies

Hongxin Wang
Department of Emergency,Armed Police Characteristic Medical Center, Tianjin, China
Lijing Jia
Department of Emergency,Chinese PLA General Hospital, Beijing, China
Heng Zhuang
Department of Emergency,Chinese PLA General Hospital, Beijing, China
Xueyan Li
Management SchoolBeijing Union University, Beijing, China
Yuzhuo Zhao
Department of Emergency,Chinese PLA General Hospital, Beijing, China
Shuxiao Pan
Department of School of Economics and ManagementBeijing Jiaotong University, Beijing, China
Kainan Wu
Department of School of Economics and ManagementUniversity of Chinese Academy of Sciences, Beijing, China
Tanshi Li
Department of Emergency,Chinese PLA General Hospital, Beijing, China

References

[1] Alba, E.; Dorronsoro, B. (2005). The exploration/exploitation tradeoff in dynamic cellular genetic algorithms. IEEE Transactions on Evolutionary Computation, 9(2), 126-142, 2005.
https://doi.org/10.1109/TEVC.2005.843751

[2] Ali, R.; Hussain J.; Siddiqi, M. H. et al. (2015). H2RM: A Hybrid Rough Set Reasoning Model for Prediction and Management of Diabetes Mellitus. Sensors, 15(7), 15921-15951, 2015.
https://doi.org/10.3390/s150715921

[3] Bazan, J. ; Kruczek, P.; Bazan-Socha, S. et al. (2006). Risk Pattern Identi cation in the Treatment of Infants with Respiratory Failure through Rough Set modeling, Proceedings of IPMU, 2-7, 2006.
https://doi.org/10.1007/11908029_44

[4] Bazan, J. ; Kruczek, P.; Bazan-Socha, S. et al. (2006). Automatic Planning of Treatment of Infants with Respiratory Failure through Rough Set modeling, International Conference on Rough Sets and Current Trends in Computing, Springer, Berlin, Heidelberg, 418-427, 2006.
https://doi.org/10.1007/11908029_44

[5] Budimir, I.; Gradišer, M.; Nikolic, M. et al. (2016). Glasgow Blatchford, pre-endoscopic Rockall and AIMS65 scores show no difference in predicting rebleeding rate and mortality in variceal bleeding. Scandinavian Journal of Gastroenterology, 51(11), 1375-1379, 2016.
https://doi.org/10.1080/00365521.2016.1200138

[6] Chowdhary, C.L.; Acharjya, D.P. (2016). A hybrid scheme for breast cancer detection using intuitionistic fuzzy rough set technique, Int. J. Healthc. Inf. Syst. Inform., 11 (2), 38-61, 2016.
https://doi.org/10.4018/IJHISI.2016040103

[7] Direkvand-Moghadam, A.; Khosravi, A.; Sayehmiri, K. (2012). Predictive factors for preeclampsia in pregnant women: a unvariate and multivariate logistic regression analysis, Acta Biochimica Polonica, 59(4), 2012.
https://doi.org/10.18388/abp.2012_2109

[8] Dorronsoro, B. (2013). Cellular genetic algorithms without additional parameters. Journal of Supercomputing, 63(3), 816-835, 2013.
https://doi.org/10.1007/s11227-012-0773-y

[9] Fogel, D.B. (1994). An introduction to simulated evolutionary optimization, IEEE Trans Neural Netw., 5(1), 3-14, 1994.
https://doi.org/10.1109/72.265956

[10] Gil-Herrera, E.; Yalcin, A.; Tsalatsanis, A. et al. (2011). Rough Set Theory based prognostication of life expectancy for terminally ill patients/ Engineering in Medicine and Biology Society, Embc, 2011 International Conference of the IEEE, 6438-6441, 2011.
https://doi.org/10.1109/IEMBS.2011.6091589

[11] Grzymala-Busse, J W. (2008). Three Approaches to Missing Attribute Values: A Rough Set Perspective. In: Lin T.Y., Xie Y., Wasilewska A., Liau CJ. (eds) Data Mining: Foundations and Practice. Studies in Computational Intelligence, Springer, Berlin, Heidelberg, 118, 139-152, 2008.
https://doi.org/10.1007/978-3-540-78488-3_8

[12] Inbaran, H.H.; Azar, A.T.; Jothi, G. (2014). Supervised hybrid feature selection based on PSO and rough sets for medical diagnosis, Comput. Methods Progr. Biomed., 113(1), 175-185, 2014.
https://doi.org/10.1016/j.cmpb.2013.10.007

[13] Hadzikadic, M.; Hakenewerth, A.; Bohren, B. et al. (1996). Concept formation vs. logistic regression: predicting death in trauma patients, Artif. Intell. Med., 8(5), 493-504, 1996.
https://doi.org/10.1016/S0933-3657(96)00356-9

[14] Hamilton, S.L.; Hamilton, J. R. (2012). Predicting in-hospital-death and mortality percentage using logistic regression, 2012 Computing in Cardiology, Krakow, 489-492, 2012.

[15] Holland, J.H. (1975). Adaptation in natural and artificial systems. Ann Arbor, 6(2), 126-137, 1975.

[16] Holland, J.H. (1992). Adaptation in natural and artificial systems, MIT Press, 1992.
https://doi.org/10.7551/mitpress/1090.001.0001

[17] Hu, Y. H.; Tai, C. T.; Chen, C. C. et al. (2017). Predicting return visits to the emergency department for pediatric patients: Applying supervised learning techniques to the Taiwan National Health Insurance Research Database. Computer Methods and Programs in Biomedicine, 144, 105-112, 2017.
https://doi.org/10.1016/j.cmpb.2017.03.022

[18] Ip, W.C.; Hu, B.Q.; Wong, H. et al. (2009). Applications of grey relational method to river environment quality evaluation in China. Journal of Hydrology, 379(3), 284-290, 2009.
https://doi.org/10.1016/j.jhydrol.2009.10.013

[19] Kim, B. J.; Park, M. K.; Kim, S. J. et al. (2009). Comparison of Scoring Systems for the Prediction of Outcomes in Patients with Nonvariceal Upper Gastrointestinal Bleeding: A Prospective Study. Digestive Diseases & Sciences, 54(11), 2523-2529, 2009.
https://doi.org/10.1007/s10620-008-0654-7

[20] Lee, H. H.; Park, J. M.; Lee, S. W. et al. (2015). C-reactive protein as a prognostic indicator for rebleeding in patients with nonvariceal upper gastrointestinal bleeding. Digestive & Liver Disease, 47(5), 378-383, 2015.
https://doi.org/10.1016/j.dld.2015.02.008

[21] Kusiak, A.(2000). Evolutionary Computation and Data Mining, Proceedings of the SPIE Conference on Intelligent Systems and Advanced Manufacturing, B.Gopalakrishnan and A. Gunasekaran (Eds), 4192, 1-10, 2000.
https://doi.org/10.1117/12.403636

[22] Li, T.S.; Li, Z.Y.; Zhao, W. et al. (2020). Analysis of medical rescue strategies based on a rough set and genetic algorithm: A disaster classification perspective. International Journal of Disaster Risk Reduction, 42(C), 2020
https://doi.org/10.1016/j.ijdrr.2019.101325

[23] Lim, K.; Lee, B.M.; Kang, U.; Lee, Y. (2018). An Optimized DBN-based Coronary Heart Disease Risk Prediction, International Journal of Computers Communications & Control, 13(4), 492-502, 2018.
https://doi.org/10.15837/ijccc.2018.4.3269

[24] Li, J.D.; Cheng, K.W.; Wng, S.H. et al. (2017). Feature selection: a data perspective. ACM Computing Surveys, 50(6): 1-45, 2017.
https://doi.org/10.1145/3136625

[25] Liu, H.; Dzitac, I.; Guo, S.(2018). Factors Space and its Relationship with Formal Conceptual Analysis: A General View. International Journal of Computers Communications & Control, 13(1), 83-98, 2018.
https://doi.org/10.15837/ijccc.2018.1.3033

[26] Najarian, K.; Hakimzadeh, R.; Ward, K. et al. (2009). Combining predictive capabilities of transcranial doppler with electrocardiogram to predict hemorrhagic shock, 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE, 2621-2624, 2009.
https://doi.org/10.1109/IEMBS.2009.5335394

[27] Øhrn, A.; Komorowski, J.(1999). Diagnosing Acute Appendicitis with Very Simple Classification Rules, Principles of Data Mining and Knowledge Discovery. Springer Berlin Heidelberg, 462-467, 1999.
https://doi.org/10.1007/978-3-540-48247-5_59

[28] Pawlak, Z. (1982). Rough set, International Journal of Computer & Information Sciences, 11(5), 1982.
https://doi.org/10.1007/BF01001956

[29] Pawlak, Z. (1991). Rough Sets, Kluwer Academic Publishers, 1991.
https://doi.org/10.1007/978-94-011-3534-4

[30] Romagnuolo, J.; Barkun, A.N.; Enns, R. et al. (2007). Simple clinical predictors may obviate urgent endoscopy in selected patients with nonvariceal upper gastrointestinal tract bleeding. Archives of Internal Medicine, 167(3), 265-270, 2007.
https://doi.org/10.1001/archinte.167.3.265

[31] Sabita Mahapatra, Sreekumar, Mahapatra, S.S. (2010). Attribute selection in marketing: A rough set approach. IIMB Management Review, 22(1-2), 16-24, 2010.
https://doi.org/10.1016/j.iimb.2010.03.001

[32] Sanders, D. S.; Perry, M. J.; Jones, S. G. et al. (2004). Effectiveness of an upper-gastrointestinal haemorrhage unit: a prospective analysis of 900 consecutive cases using the Rockall score as a method of risk standardisation. European Journal of Gastroenterology & Hepatology, 16(5),487, 2004.
https://doi.org/10.1097/00042737-200405000-00009

[33] Sherman, R E.; Anderson, S A.; Dal Pan, G. J. et al. (2016). Real-World Evidence - What Is It and What Can It Tell Us?. N Engl J Med, 375(23), 2293-2297,2016.
https://doi.org/10.1056/NEJMsb1609216

[34] Son, C.S.; Kim, Y.N.; Kim, H.S. et al. (2012). Decision-making model for early diagnosis of congestive heart failure using rough set and decision tree approaches, J. Biomed. Inform., 45(5), 999-1008, 2012.
https://doi.org/10.1016/j.jbi.2012.04.013

[35] Tsumoto, S.; Tanaka, H. (1994). Induction of Medical Expert System Rules Based on Rough Sets and Resampling methods, Proceedings of the Annual Symposium on Computer Application in Medical Care, American Medical Informatics Association, 1066,1994.

[36] Tsumoto, S.; Tanaka, H. (1995). Induction of expert system rules based on rough sets and resampling methods, Medinfo. MEDINFO 8, 861-865, 1995.

[37] Tsumoto, S.; Tanaka, H. (1996). Automated Discovery of Medical Expert System Rules from Clinical Databases Based on Rough Sets, KDD, 63-69, 1996.

[38] Tao, Z.; Huiling, L.; Wenwen, W. et al. (2019). GA-SVM based feature selection and parameter optimization in hospitalization expense modeling. Applied Soft Computing, 75, 323-332, 2019.
https://doi.org/10.1016/j.asoc.2018.11.001

[39] Von Neumann, J.; Burks, A.W. (1965). Theory of self-reproducing automata. IEEE Transactions on Neural Networks, 5(1): 3-14.

[40] Von Neumann, J. (1948). The general and logical theory of automata. Papers of John Von Neumann on Computing & Computer Theory, 1-41, 1948.

[41] Vreeburg, E M.; Terwee, C B.; Snel, P. et al. (1999). Validation of the Rockall risk scoring system in upper gastrointestinal bleeding. Gut, 44(3), 331-335, 1999.
https://doi.org/10.1136/gut.44.3.331

[42] Wang, C. Y.; Qin, J.; Wang, J. et al. (2013). Rockall score in predicting outcomes of elderly patients with acute upper gastrointestinal bleeding. World Journal of Gastroenterology, 19(22),3466- 3472, 2013.
https://doi.org/10.3748/wjg.v19.i22.3466

[43] Wang, X.; Yang, J.; Jensen, R. et al. (2006). Rough set feature selection and rule induction for prediction of malignancy degree in brain glioma. Computer Methods & Programs in Biomedicine, 83(2):147, 2006.
https://doi.org/10.1016/j.cmpb.2006.06.007

[44] Wei, Z.; Li, J.; Li, X. et al. (2019). Prediction and feature selection for fatal gastrointestinal bleeding recurrence in hospital via machine learning, Chinese Critical Care Medicine, 31(3), 359- 362, 2019.

[45] Whitley, D. (1993). Cellular genetic algorithms, Proceedings of the 5th International Conference on Genetic Algorithms, Morgan Kauffmann, 658-662, 1993.

[46] Wu, T. T.; Li, H. (2016). Research progress of early warning scoring system for cardiac arrest in hospital. Chinese Journal of Nursing, 051(009), 1118-1123, 2016.

[47] Xu, F.F.; Miao, D.Q.; Wei, L.(2009). Fuzzy-rough attribute reduction via mutual information with an application to cancer classification, Comput. Math. Appl., 57 (6), 1010-1017, 2009.
https://doi.org/10.1016/j.camwa.2008.10.027

[48] Zhang, Y.; Liu, Z.; Zhang, H. et al. (2012). A Crowding Niche Cellular Genetic Algorithm. Advanced Materials Research, 482-484:1933-1936, 2012.
https://doi.org/10.4028/www.scientific.net/AMR.482-484.1933

[49] Zhao, S. F.; Qu, Q. Y.; Feng, K. et al. (2017). Comparison of the AIMS65 and Glasgow Blatchford score for risk stratification in elderly patients with upper gastrointestinal bleeding. European Geriatric Medicine, 8(1), 37-41, 2017. .
https://doi.org/10.1016/j.eurger.2016.10.002

[50] Zhou, T.; Lu H.L.; Wang W. W. et al. (2019). GA-SVM based feature selection and parameter optimization in hospitalization expense modeling. Applied Soft Computing, 75, 323-332, 2019.
https://doi.org/10.1016/j.asoc.2018.11.001

[51] Zhu, X. Z.; Zhu, W.; Fan, X. N.(2017). Rough set methods in feature selection via submodular function. Soft Computing, 21(13), 3699-3711, 2017.
https://doi.org/10.1007/s00500-015-2024-7
Published
2020-11-20
How to Cite
WANG, Hongxin et al. A Rough Set and Cellular Genetic Fusion Algorithm for Acute Critical Disease Prediction. INTERNATIONAL JOURNAL OF COMPUTERS COMMUNICATIONS & CONTROL, [S.l.], v. 15, n. 6, nov. 2020. ISSN 1841-9844. Available at: <http://univagora.ro/jour/index.php/ijccc/article/view/3894>. Date accessed: 30 nov. 2020. doi: https://doi.org/10.15837/ijccc.2020.6.3894.