Palabras clave
Latent Class Analysis
Clustering
Conditional Random Forest
Gradient Boosting Machine
Machine Learning
Investigación de operaciones
Cómo citar
Resumen
Objetivo: El objetivo de este trabajo es construir un modelo de predicción del tiempo de quirófano (ORT) para ser usado en un sistema de programación inteligente. Esta predicción es un ejercicio complejo debido a su alta variabilidad y a las múltiples variables influyentes. Materiales y métodos: Evaluamos una nueva estrategia utilizando Latent Class Analysis (LCA) y métodos de agrupación para identificar subgrupos de procedimientos y cirugías que luego se combinan con modelos de predicción de ensamblaje para mejorar las estimaciones de ORT. Se evalúan tres modelos basados en árboles, Classification and Regression Trees (CART), Conditional Random Forest (CFOREST) y Gradient Boosting Machine (GBM), bajo dos escenarios: i) conjunto de datos básicos de predictores y ii) conjunto de datos completo con procedimientos binarios. Para evaluar el modelo, utilizamos un conjunto de datos de prueba y un conjunto de datos de entrenamiento para ajustar los parámetros. Resultados y discusión: Los mejores resultados se obtienen con el modelo GBM utilizando el conjunto de datos completo y las variables de agrupación, con una precisión operacional del 57,3% en el conjunto de pruebas. Conclusión: Los resultados indican que el modelo GBM supera a los otros modelos y mejora con la inclusión de los procedimientos como variables binarias y la adición de las variables de agrupación obtenidas con LCA y la agrupación jerárquica, que identifican grupos homogéneos de procedimientos y cirugías.
World Health Organization, “World Health Statistics,” pp. 1-79, 2016, [Online]. Available: http://www.who.int/gho/publications/world_health_statistics/EN_WHS08_Full.pdf.
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. https://doi.org/10.11144/Javeriana.rgsp12-24.ampp
WHO Regional Office for Europe, “European Health Information Gateway, Inpatient surgical procedures per year per 100 000,” 2018. Accessed on: Nov. 02, 2018. Available: https://gateway.euro.who.int/en/hfa-explorer/).
DANE, “En el día mundial de la población el DANE le cuenta,” 2018. Accessed on: Nov. 09, 2018. [Online]. Available: https://www.dane.gov.co/files/comunicados/Dia_mundial_poblacion.pdf.
K. Guzmán Finol and Banco de la República de Colombia, “Radiografía de la oferta de servicios de salud en Colombia,” 202, 2014. [Online]. Available: http://www.banrep.gov.co/docum/Lectura_finanzas/pdf/dtser_202.pdf.
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. https://doi.org/10.1007/s10729-017-9401-y.
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: https://www.researchgate.net/profile/Brian-Denton-2/publication/241142977_Surgery_Planning_and_Scheduling_A_Literature_Review/links/55ede81d08aef559dc438308/Surgery-Planning-and-Scheduling-A-Literature-Review.pdf
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. https://doi.org/10.3233/978-1-61499-783-2-133
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. https://doi.org/10.1016/j.ejor.2018.05.022.
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. https://doi.org/10.1016/j.orhc.2015.08.006.
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: essay.utwente.nl/60822/1/MSc_Thijs_Knoeff.pdf.
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. https://doi.org/10.1016/J.DSS.2012.10.021
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. https://doi.org/10.3138/infor.49.4.254.
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. https://doi.org/10.4097/kjae.2016.69.5.487.
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.
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. https://doi.org/10.1016/j.jacc.2015.12.063.
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. https://doi.org/10.1007/s10916-019-1512-1
E. Kayis et al., “Improving prediction of surgery duration using operational and temporal factors,” AMIA Annual Symposium Proceedings, vol. 2012, pp. 456-62, 2012. https://pubmed.ncbi.nlm.nih.gov/23304316/
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. https://doi.org/10.1111/j.1467-9574.2009.00440.x
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. https://doi.org/10.1053/j.jvca.2016.11.023
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: http://mucmd.org/CameraReadySubmissions/52%5CCameraReadySubmission%5CMLHC_2017_FINAL_cameraready.pdf.
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. https://doi.org/10.1016/j.procs.2017.08.332
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. https://doi.org/10.1007/s10916-019-1160-5.
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. https://doi.org/10.1016/j.jamcollsurg.2019.05.029
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.
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.
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. https://doi.org/10.3389/fpsyg.2014.00920
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. https://doi.org/10.1037/a0037069
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. https://psycnet.apa.org/record/2002-14070-002
S. Trivedi, Z. A. Pardos, and N. T. Heffernan, “The Utility of Clustering in Prediction Tasks,” arXiv, no. September, pp. 1-11, 2015.
M. Maechler, P. Rousseeuw, A. Struyf, M. Hubert, and K. Hornik, “Cluster Analysis Basics and Extensions,” pp. 29-31, 2017.
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.
J. Han, M. Kamber, and J. Pei, Data mining: concepts and tecniques, Third Ed. Amsterdam, Netherlands: Elsevier Inc., 2012.
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: https://cran.r-project.org/web/packages/cluster/cluster.pdf
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. https://doi.org/10.1093/bioinformatics/bti517
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, https://doi.org/10.1016/0377-0427(87)90125-7
T. Therneau, B. Atkinson, and B. Ripley, “rpart: Recursive Partitioning and Regression Trees. R package version 4.1-11.” 2017,[Online]. Available: https://cran.r-project.org/package=rpart.
L. Breiman, “Random Forests,” 2001. Accessed: Dec. 02, 2018 [Online]. Available: https://link.springer.com/content/pdf/10.1023%2FA%3A1010933404324.pdf.
T. Hothorn, P. Buehlmann, S. Dudoit, A. Molinaro, and M. Van Der Laan, “Survival Ensembles,” Biostatistics, vol. 7, no. 3, pp. 355-373, 2006.
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. https://doi.org/10.1198/106186006X133933
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. https://doi.org/10.1186/1471-2105-8-25.
J. H. Friedman, “Greedy Function Approximation : A Gradient Boosting Machine,” Institute of Mathematical Statistics, vol. 29, no. 5, pp. 1189-1232, 2001, https://doi.org/10.1214/009053606000000795
B. Greenwell, B. Boehmke, J. Cunningham, and G. Developers, “GBM: Generalized Boosted Regression Models. R package version 2.1.4.” 2018 [Online]. Available: https://cran.r-project.org/package=gbm.
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, https://doi.org/10.1007/s41060-017-0055-0.
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, https://doi.org/10.1007/s10729-018-9457-3.
M. Kuhn et al., “caret: Classification and Regression Training. R package version 6.0-80.” 2018 [Online]. Available: https://cran.r-project.org/package=caret
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,https://doi.org/10.1097/00000542-200512000-00023.
Esta obra está bajo una licencia internacional Creative Commons Atribución 4.0.
Derechos de autor 2021 Eduard Alexander Gañán-Cárdenas, MSc, Jorge Isaac Pemberthy-Ruiz, MSc, Juan Carlos Rivera-Agudelo, PhD, Maria Clara Mendoza- Arango, PhD