Published Nov 2, 2021


Google Scholar
Search GoogleScholar

Eduard Alexander Gañán-Cárdenas, MSc

Jorge Isaac Pemberthy-Ruiz, MSc

Juan Carlos Rivera-Agudelo, PhD

Maria Clara Mendoza- Arango, PhD



Objective: The objective of this work is to build a prediction model for Operating Room Time (ORT) to be used in an intelligent scheduling system. This prediction is a complex exercise due to its high variability and multiple influential variables. Materials and methods: We assessed a new strategy using Latent Class Analysis (LCA) and clustering methods to identify subgroups of procedures and surgeries that are combined with prediction models to improve ORT estimates. Three tree-based models are assessed, Classification and Regression Trees (CART), Conditional Random Forest (CFOREST) and Gradient Boosting Machine (GBM), under two scenarios: (i) basic dataset of predictors and (ii) complete dataset with binary procedures. To evaluate the model, we use a test dataset and a training dataset to tune parameters. Results and discussion: The best results are obtained with GBM model using the complete dataset and the grouping variables, with an operational accuracy of 57.3% in the test set. Conclusion: The results indicate the GBM model outperforms other models and it improves with the inclusion of the procedures as binary variables and the addition of the grouping variables obtained with LCA and hierarchical clustering that perform the identification of homogeneous groups of procedures and surgeries.


Operating room time prediction, Latent Class Analysis, Clustering, Conditional Random Forest, Gradient Boosting Machine, Machine Learning, Operations ResearchPredicción del tiempo de quirófano, Latent Class Analysis, Clustering, Conditional Random Forest, Gradient Boosting Machine, Machine Learning, Investigación de operaciones

[1] World Health Organization, “World Health Statistics,” pp. 1-79, 2016, [Online]. Available:
[2] P. A. Velásquez-Restrepo, A. K. Rodríguez-Quintero, and J. S. Jaén-Posada, “Aproximación metodológica a la planificación y a la programación de las salas de cirugía: una revisión de la literatura,” Revista Gerencia y Políticas de Salud, vol. 12, no. 24, pp. 249-266, 2013.
[3] WHO Regional Office for Europe, “European Health Information Gateway, Inpatient surgical procedures per year per 100 000,” 2018. Accessed on: Nov. 02, 2018. Available:
[4] DANE, “En el día mundial de la población el DANE le cuenta,” 2018. Accessed on: Nov. 09, 2018. [Online]. Available:
[5] K. Guzmán Finol and Banco de la República de Colombia, “Radiografía de la oferta de servicios de salud en Colombia,” 202, 2014. [Online]. Available:
[6] N. Bahou, C. Fenwick, G. Anderson, R. van der Meer, and T. Vassalos, “Modeling the critical care pathway for cardiothoracic surgery,” Health Care Management Science, vol. 21, no. 2, pp. 192-203, 2018.
[7] S. A. Erdogan and B. T. Denton, “Surgery Planning and Scheduling: A Literature Review,” In Wiley Encyclopedia of operations research and management science, J. J. Cochran, Ed. New York: John Wiley & Sons, 2010. Available:
[8] Z. Shahabikargar, S. Khanna, A. Sattar, and J. Lind, “Improved prediction of procedure duration for elective surgery,” Studies in Health Technology and Informatics, vol. 239, pp. 133-138, 2017.
[9] G. Sagnol et al., “Robust allocation of operating rooms: A cutting plane approach to handle lognormal case durations,” European Journal of Operational Research, vol. 271, no. 2, pp. 420-435, 2018.
[10] D. Duma and R. Aringhieri, “An online optimization approach for the Real Time Management of operating rooms,” Operations Research for Health Care, vol. 7, pp. 40-51, 2015.
[11] T. Knoeff, E. W. Hans, and J. L. Hurink, “Operating room scheduling an evaluation of alternative scheduling approaches to improve OR efficiency and minimize peak demands for ward beds at SKB Winterswijk,” M.S. thesis, Dept. Operational Methods for Production and Logistics, Twente Univ., Enschede, Netherlands, 2010. Available:
[12] J.-S. Tancrez, B. Roland, J.-P. Cordier, and F. Riane, “Assessing the impact of stochasticity for operating theater sizing,” Decision Support Systems, vol. 55, no. 2, pp. 616-628, May 2013.
[13] J. M. van Oostrum, T. Parlevliet, A. P. M. Wagelmans, and G. Kazemier, “A method for clustering surgical cases to allow master surgical scheduling,” INFOR, vol. 49, no. 4, p. 37, 2008.
[14] J. Jang, H. H. Lim, G. Bae, S. U. Choi, and C. H. Lim, “Operation room management in Korea: Results of a survey,” Korean Journal of Anesthesiology, vol. 69, no. 5, pp. 487-491, 2016.
[15] D. P. Strum, A. R. Sampson, J. H. May, and L. G. Vargas, “Surgeon and Type of Anesthesia Predict Variability in Surgical Procedure Times,” Anesthesiology, vol. 92, no. 5, pp. 145-1466, 2000.
[16] M. J. C. Eijkemans, M. van Houdenhoven, N. Tien, E. Boersma, E. W. Steyerberg, and G. Kazemier, “Predicting the Unpredictable. A New Prediction Model for Operating Room Times Using Individual Characteristics andt he Surgeon’s Estimate,” American Society of Anesthesiologists, vol. 112, no. 1, pp. 41-49, 2010.
[17] V. Bellini, M. Guzzon, B. Bigliardi, M. Mordonini, S. Filippelli, and E. Bignami, “Artificial Intelligence: A New Tool in Operating Room Management. Role of Machine Learning Models in Operating Room Optimization,” Journal of Medical Systems, vol. 44, no. 1, pp. 1-10, 2020.
[18] E. Kayis et al., “Improving prediction of surgery duration using operational and temporal factors,” AMIA Annual Symposium Proceedings, vol. 2012, pp. 456-62, 2012.
[19] P. S. Stepaniak, C. Heij, and G. de Vries, “Modeling and prediction of surgical procedure times,” Statistica Neerlandica, vol. 64, no. 1, pp. 1-18, February 2010.
[20] A. Wu, D. E. Rinewalt, R. W. Lekowski, and R. D. Urman, “Use of Historical Surgical Times to Predict Duration of Primary Aortic Valve Replacement,” Journal of Cardiothoracic and Vascular Anesthesia, vol. 31, no. 3, pp. 810-815, 2017.
[21] E. C. Lorenzi, S. L. Brown, and K. Heller, “Predictive Hierarchical Clustering: Learning clusters of CPT codes for improving surgical outcomes,” Machine Learning for Healthcare, vol. 68, 2017 [Online]. Available:
[22] N. Spangenberg, M. Wilke, and B. Franczyk, “A Big Data architecture for intra-surgical remaining time predictions,” Procedia Computer Science, vol. 113, pp. 310-317, 2017.
[23] J. P. Tuwatananurak et al., “Machine Learning Can Improve Estimation of Surgical Case Duration: A Pilot Study,” Journal of Medical Systems, vol. 43, no. 3, pp. 1-7, March 2019.
[24] M. A. Bartek et al., “Improving Operating Room Efficiency: Machine Learning Approach to Predict Case-Time Duration,” Journal of the American College of Surgeons, vol. 229, no. 4, pp. 346-354, 2019.
[25] J. K. Vermunt and J. Magidson, “Latent class cluster analysis,” in Applied latent class analysis, Cambridge, MA: Cambridge University Press, Ed. 2002, pp. 89-106.
[26] J. K. Vermunt and J. Magidson, “Latent class analysis,” in The Sage Encyclopedia of Social Sciences Research Methods, M. Lewis-Beck, A. Bryman and T. F. Liao, Eds. Thousand Oakes: Sage, 2004, pp. 549-553.

[27] I. C. Wurpts and C. Geiser, “Is adding more indicators to a latent class analysis beneficial or detrimental? Results of a Monte-Carlo study,” Frontiers in Psychology, vol. 5, p. 920, 2014.
[28] D. A. Linzer and J. B. Lewis, “poLCA: An R Package for Polytomous Variable Latent Class Analysis,” Journal of Statistical Software, vol. 42, no. 10, pp. 1-29, 2011.
[29] M. von Davier, “Bootstrapping Goodness-of-Fit Statistics for Sparse Categorical Data,” Methods of Psychological Research Online, vol. 2, no. 2, pp. 29-48, 1997.
[30] S. Trivedi, Z. A. Pardos, and N. T. Heffernan, “The Utility of Clustering in Prediction Tasks,” arXiv, no. September, pp. 1-11, 2015.
[31] M. Maechler, P. Rousseeuw, A. Struyf, M. Hubert, and K. Hornik, “Cluster Analysis Basics and Extensions,” pp. 29-31, 2017.
[32] T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Second Edition Learning: Data Mining, Inference, and Prediction, Second Ed. Berlin: Springer Science+Business Media, 2009.
[33] J. Han, M. Kamber, and J. Pei, Data mining: concepts and tecniques, Third Ed. Amsterdam, Netherlands: Elsevier Inc., 2012.
[34] M. Maechler, P. Rousseeuw, A. Struyf, M. Hubert, and K. Hornik, “Cluster Analysis Basics and Extensions. R package version 2.0.7-1”, 2018 [Online]. Available:
[35] J. Handl, J. Knowles, and D. B. Kell, “Computational cluster validation in post-genomic data analysis,” Reverse Complement, vol. 21, no. 15, pp. 3201-3212, 2005.
[36] P. J. Rousseeuw, “Silhouettes: A graphical aid to the interpretation and validation of cluster analysis,” Journal of Computational and Applied Mathematics, vol. 20, pp. 5-65, November 1987,
[37] T. Therneau, B. Atkinson, and B. Ripley, “rpart: Recursive Partitioning and Regression Trees. R package version 4.1-11.” 2017,[Online]. Available:
[38] L. Breiman, “Random Forests,” 2001. Accessed: Dec. 02, 2018 [Online]. Available:
[39] T. Hothorn, P. Buehlmann, S. Dudoit, A. Molinaro, and M. Van Der Laan, “Survival Ensembles,” Biostatistics, vol. 7, no. 3, pp. 355-373, 2006.
[40] T. Hothorn, K. Hornik, and A. Zeileis, “Unbiased recursive partitioning: A conditional inference framework,” Journal of Computational and Graphical Statistics, vol 15, no. 3, pp. 651-674, 2006.
[41] C. Strobl, A. L. Boulesteix, A. Zeileis, and T. Hothorn, “Bias in random forest variable importance measures: Illustrations, sources and a solution,” BMC Bioinformatics, vol. 8, no. 25, 2007.
[42] J. H. Friedman, “Greedy Function Approximation : A Gradient Boosting Machine,” Institute of Mathematical Statistics, vol. 29, no. 5, pp. 1189-1232, 2001,
[43] B. Greenwell, B. Boehmke, J. Cunningham, and G. Developers, “GBM: Generalized Boosted Regression Models. R package version 2.1.4.” 2018 [Online]. Available:
[44] N. Master, Z. Zhou, D. Miller, D. Scheinker, N. Bambos, and P. Glynn, “Improving predictions of pediatric surgical durations with supervised learning,” Journal Name, International Journal of Data Science and Analytics, vol. 4, no. 1, pp. 35-52, August 2017,
[45] M. Fairley, D. Scheinker, and M. L. Brandeau, “Improving the efficiency of the operating room environment with an optimization and machine learning model,” Health Care Management Science, vol. 22, no. 4, pp. 756-767, December 2019,
[46] M. Kuhn et al., “caret: Classification and Regression Training. R package version 6.0-80.” 2018 [Online]. Available:
[47] F. Dexter and J. Ledolter, “Bayesian Prediction Bounds and Comparisons of Operating Room Times Even for Procedures with Few or No Historic Data,” Anesthesiology, vol. 103, no. 6, pp. 1259–1167, 2005,
How to Cite
Gañán-Cárdenas, E. A., Pemberthy-Ruiz, J. I., Rivera-Agudelo, J. C., & Mendoza- Arango, M. C. (2021). Operating Room Time Prediction: An Application of Latent Class Analysis and Machine Learning. Ingenieria Y Universidad, 26.
Special Section: Health Care Engineering