Abstract
A precise estimation of patient length of stay is important for systematically managing both hospital unit resources (medication, equipment, beds) and the distribution of personnel. This is true for hospitalization following any disease, however the particularities of each trigger a different observation/recovery period. The current study investigates this problem in the context of cancer of the colorectal type on a discrete data set. Several classifiers from distinct conceptual families provide an estimation or even further information on the length of stay of patients that had been operated of cancer in certain stages and invasion at various parts of the colon or rectum. Support vector machines and neural networks give a black box prediction of the hospitalization period, while decision trees and evolutionary algorithms additionally offer the underlying rules of decision. Results are also compared to those of ensemble state-of-the-art techniques: bagging, boosting and random forests. A Wilcoxon rank-sum test demonstrates that the support vector machines, the decision trees and the ensembles are significantly better than the neural networks and the evolutionary algorithms. They also show substantial agreement following Cohen’s kappa coefficient to the original outputs. The highest agreement is between the results of support vector machines (SVM)–bagging (0.84) and decision trees (DT)–bagging (0.87). A potential SVM–EA tandem is also investigated, as a more collaborative means towards supporting decision making; its accuracy came similar to that of the plain EA. Faced with the results of each, the professional is given a manner of how to interpret the amalgam of computational opinions and justifications given in support of his/her decision.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11063-017-9585-7/MediaObjects/11063_2017_9585_Fig1_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11063-017-9585-7/MediaObjects/11063_2017_9585_Fig2_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11063-017-9585-7/MediaObjects/11063_2017_9585_Fig3_HTML.gif)
Similar content being viewed by others
References
Arizmendi C, Sierra DA, Vellido A, Romero E (2014) Automated classification of brain tumours from short echo time in vivo MRS data using Gaussian decomposition and Bayesian neural networks. Expert Syst Appl 41(11):5296–5307. doi:10.1016/j.eswa.2014.02.031. http://www.sciencedirect.com/science/article/pii/S0957417414001079
Belciug S, Gorunescu F (2015) Improving hospital bed occupancy and resource utilization through queuing modeling and evolutionary computation. J Biomed Inform 53:261–269
Bhattacharjee P, Ray PK (2014) Patient flow modelling and performance analysis of healthcare delivery processes in hospitals: a review and reflections. Comput Ind Eng 78:299–312
Breiman L (1996) Bagging predictors. Mach Learn 24(2):123–140. doi:10.1023/A:1018054314350
Breiman L (2001) Random forests. Mach Learn 45(1):5–32. doi:10.1023/A:1010933404324
Czibula G, Crişan GC, Pintea CM, Czibula IG (2013) Soft computing approaches on the bandwidth problem. Informatica 24(2):169–180. http://dl.acm.org/citation.cfm?id=2773202.2773203
De Jong KA, Spears WM, Gordon DF (1993) Using genetic algorithms for concept learning. Mach Learn 13(2–3):161–188. doi:10.1007/BF00993042
Eiben AE, Smith JE (2003) Introduction to evolutionary computing. Springer, Berlin
Faiz O, Haji A, Burns E, Bottle A, Kennedy R, Aylin P (2011) Hospital stay amongst patients undergoing major elective colorectal surgery: predicting prolonged stay and readmissions in nhs hospitals. Colorectal Dis 13(7):816–822
Fernández-Delgado M, Cernadas E, Barro S, Amorim D (2014) Do we need hundreds of classifiers to solve real world classification problems? J Mach Learn Res 15(1):3133–3181. http://dl.acm.org/citation.cfm?id=2627435.2697065
Freund Y, Schapire RE (1996) Experiments with a new boosting algorithm. In: Saitta L (ed) Proceedings of the thirteenth international conference on machine learning (ICML 1996). Morgan Kaufmann, pp 148–156
Garca-Garaluz E, Atencia M, Joya G, Garca-Lagos F, Sandoval F (2011) Hopfield networks for identification of delay differential equations with an application to dengue fever epidemics in Cuba. Neurocomputing 74(16):2691–2697. doi:10.1016/j.neucom.2011.03.022. http://www.sciencedirect.com/science/article/pii/S0925231211002402. Advances in extreme learning machine: theory and applications biological inspired systems. computational and ambient intelligence selected papers of the 10th international work-conference on artificial neural networks (IWANN2009)
Gorunescu F (2011) Data mining—concepts, models and techniques, intelligent systems reference library, vol 12. Springer, Berlin
Gorunescu F, Belciug S (2014) Evolutionary strategy to develop learning-based decision systems. Application to breast cancer and liver fibrosis stadialization. J Biomed Inform 49:112–118
Hastie T, Tibshirani R, Friedman J (2001) The elements of statistical learning. Springer series in statistics. Springer, New York
Haykin S (1998) Neural networks: a comprehensive foundation, 2nd edn. Prentice Hall PTR, Englewood Cliffs
Hruschka ER, Campello RJGB, Freitas AA, De Carvalho ACPLF (2009) A survey of evolutionary algorithms for clustering. Trans Syst Man Cybern Part C 39(2):133–155. doi:10.1109/TSMCC.2008.2007252
Hsu CW, Lin CJ (2004) A comparison of methods for multi-class support vector machines. IEEE Trans Neural Netw 13(2):415–425
Kelly M, Sharp L, Dwane F, Kelleher T, Comber H (2012) Factors predicting hospital length-of-stay and readmission after colorectal resection: a population-based study of elective and emergency admissions. BMC Health Serv Res 12(1):77
Kramer O, Gieseke F (2011) Short-term wind energy forecasting using support vector regression. Springer, Berlin. doi:10.1007/978-3-642-19644-7_29
Leung A, Gibbons R, Vu H (2009) Predictors of length of stay following colorectal resection for neoplasms in 183 veterans affairs patients. World J Surg 33(10):2183–2188
Luchian H, Breaban ME, Bautu A (2015) On meta-heuristics in optimization and data analysis. Application to geosciences. Springer, Cham. doi:10.1007/978-3-319-16531-8_2
Martens D, Baesens B, Gestel TV, Vanthienen J (2007) Comprehensible credit scoring models using rule extraction from support vector machines. Eur J Oper Res 183(3):1466–1476
Perng DS, Lu IC, Shi HY, Lin CW, Liu KW, Su YF, Lee KT (2014) Incidence trends and predictors for cost and average lengths of stay in colorectal cancer surgery. World J Gastroenterol 20(2):532–538
Preuss M (2015) Multimodal optimization by means of evolutionary algorithms. Natural computing series. Springer, Berlin. doi:10.1007/978-3-319-07407-8
Quinlan R (1993) C4.5: programs for machine learning. Morgan Kaufmann, Los Altos
Riera-Ledesma J, Salazar-Gonzlez JJ (2005) A heuristic approach for the travelling purchaser problem. Eur J Oper Res 162(1):142–152. doi:10.1016/j.ejor.2003.10.032. http://www.sciencedirect.com/science/article/pii/S037722170300821X. Logistics: from theory to application
Hoffmann F (2004) Combining boosting and evolutionary algorithms for learning of fuzzy classification rules. Fuzzy Sets Syst 141(1):47–58. doi:10.1016/S0165-0114(03)00113-1
Stoean C, Stoean R (2009) Evolution of cooperating classification rules with an archiving strategy to underpin collaboration. In: Teodorescu H-N, Watada J, Jain LC (eds) Intelligent systems and technologies: methods and applications. Springer, Berlin, pp 47–65
Stoean C, Stoean R (2014) Post-evolution of variable-length class prototypes to unlock decision making within support vector machines. Appl Soft Comput 25:159–173. doi:10.1016/j.asoc.2014.09.017. http://www.sciencedirect.com/science/article/pii/S1568494614004694
Stoean R, Preuss M, Stoean C, Dumitrescu D (2007) Concerning the potential of evolutionary support vector machines. Proc IEEE Congr Evol Comput 1:1436–1443
Stoean R, Stoean C, Preuss M, Dumitrescu D (2006) Evolutionary multi-class support vector machines for classification. In: Proceedings of international conference on computers and communications—ICCC 2006, Baile Felix Spa - Oradea, Romania, pp 423–428
Stoean R, Stoean C, Sandita A, Ciobanu D, Mesina C (2015) Ensemble of classifiers for length of stay prediction in colorectal cancer. In: Rojas I, Joya G, Catala A (eds) Advances in computational intelligence lecture notes in computer science, vol 9094. Springer, Berlin, pp 444–457
Vapnik V (1998) Statistical learning theory. Wiley, New York
Zaefferer M, Stork J, Friese M, Fischbach A, Naujoks B, Bartz-Beielstein T (2014) Efficient global optimization for combinatorial problems. In: Proceedings of the 2014 annual conference on genetic and evolutionary computation, GECCO ’14. ACM, New York, pp 871–878. doi:10.1145/2576768.2598282
Zaharie D, Lungeanu D, Zamfirache F (2008) Interactive search of rules in medical data using multiobjective evolutionary algorithms. In: Proceedings of the 10th annual conference companion on genetic and evolutionary computation, GECCO ’08. ACM, New York, pp 2065–2072. doi:10.1145/1388969.1389023
Author information
Authors and Affiliations
Corresponding author
Additional information
The authors acknowledge the support of the research Grant No. 26/2014, code PN-II-PT-PCCA-2013-4-1153, entitled IMEDIATREAT—Intelligent Medical Information System for the Diagnosis and Monitoring of the Treatment of Patients with Colorectal Neoplasm—financed by the Romanian Ministry of National Education (MEN)—Research and the Executive Agency for Higher Education Research Development and Innovation Funding (UEFISCDI).
Rights and permissions
About this article
Cite this article
Stoean, R., Stoean, C., Sandita, A. et al. Interpreting Decision Support from Multiple Classifiers for Predicting Length of Stay in Patients with Colorectal Carcinoma. Neural Process Lett 46, 811–827 (2017). https://doi.org/10.1007/s11063-017-9585-7
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-017-9585-7