Predicting Procedure Duration to Improve Scheduling of Elective Surgery

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8862)


The accuracy of surgery schedules depends on precise estimation of surgery duration. Current approaches employed by hospitals include historical averages and surgical team estimates which are not accurate enough. The inherent complexity of surgery duration estimation contributes significantly to increased procedure cancellations and reduced utilisation of already encumbered resources. In this study we employ administrative and perioperative data from a large metropolitan hospital to investigate the performance of different machine learning approaches for improving procedure duration estimation. The predictive modelling approaches applied include linear regression (LR), multivariate adaptive regression splines (MARS), and random forests (RF). Cross validation results reveal that the random forest model outperforms other methods, reducing mean absolute percentage error by 28% when compared to current hospital estimation approaches.


Duration of procedure Operating Room (OR) Random Forest Linear Regression Multivariate Adaptive Regression Splines (MARS) 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Cardoen, B., Demeulemeester, E., Beliën, J.: Operating room planning and scheduling: A literature review. European Journal of Operational Research 201(3), 921–932 (2010)CrossRefzbMATHGoogle Scholar
  2. 2.
    Macario, A., Vitez, T.S., Dunn, B., McDonald, T.: Where are the costs in perioperative care?: Analysis of hospital costs and charges for inpatient surgical care. Anesthesiology 83(6), 1138–1144 (1995)CrossRefGoogle Scholar
  3. 3.
    Pandit, J.J., Carey, A.: Estimating the duration of common elective operations: Implications for operating list management. Anaesthesia 61(8), 768–776 (2006)CrossRefGoogle Scholar
  4. 4.
    Schofield, W.N., Rubin, G.L., Piza, M., Lai, Y.Y., Sindhusake, D., Fearnside, M.R., Klineberg, P.L.: Cancellation of operations on the day of intended surgery at a major Australian referral hospital. Med. J. Aust. 182(12), 612–615 (2005)Google Scholar
  5. 5.
    Kayis, E., Wang, H., Patel, M., Gonzalez, T., Jain, S., Ramamurthi, R., Santos, C., Singhal, S., Suermondt, J., Sylvester, K.: Improving Prediction of Surgery Duration using Operational and Temporal Factors. In: AMIA Annu. Symp. Proc., pp. 456–462 (2012)Google Scholar
  6. 6.
    Eijkemans, M.J.C., Van Houdenhoven, M., Nguyen, T., Boersma, E., Steyerberg, E.W., Kazemier, G.: Predicting the unpredictable: A new prediction model for operating room times using individual characteristics and the surgeon’s estimate. Anesthesiology 112(1), 41–49 (2010)CrossRefGoogle Scholar
  7. 7.
    Dexter, F., Dexter, E.U., Masursky, D., Nussmeier, N.A.: Systematic review of general thoracic surgery articles to identify predictors of operating room case durations. Anesthesia and Analgesia 106(4), 1232–1241 (2008)CrossRefGoogle Scholar
  8. 8.
    Wright, I.H., Kooperberg, C., Bonar, B.A., Bashein, G.: Statistical modeling to predict elective surgery time: Comparison with a computer scheduling system and surgeon-provided estimates. Anesthesiology 85(6), 1235–1245 (1996)CrossRefGoogle Scholar
  9. 9.
    Zhou, J., Dexter, F., Macario, A., Lubarsky, D.A.: Relying solely on historical surgical times to estimate accurately future surgical times is unlikely to reduce the average length of time cases finish late. Journal of Clinical Anesthesia 11(7), 601–605 (1999)CrossRefGoogle Scholar
  10. 10.
    Combes, C., Meskens, N., Rivat, C., Vandamme, J.P.: Using a KDD process to forecast the duration of surgery. International Journal of Production Economics 112(1), 279–293 (2008)CrossRefGoogle Scholar
  11. 11.
    Stepaniak, P.S., Heij, C., De Vries, G.: Modeling and prediction of surgical procedure times. Statistica Neerlandica 64(1), 1–18 (2010)CrossRefGoogle Scholar
  12. 12.
    Li, Y., Zhang, S., Baugh, R.F., Huang, J.Z.: Predicting surgical case durations using ill-conditioned CPT code matrix. IIE Transactions (Institute of Industrial Engineers) 42(2), 121–135 (2010)Google Scholar
  13. 13.
    Dexter, F., Ledolter, J.: Bayesian prediction bounds and comparisons of operating room times even for procedures with few or no historic data. Anesthesiology 103(6), 1259–1267 (2005)CrossRefGoogle Scholar
  14. 14.
    Dexter, F., Ledolter, J., Tiwari, V., Epstein, R.H.: Value of a scheduled duration quantified in terms of equivalent numbers of historical cases. Anesthesia & Analgesia 117(1), 205–210 (2013)CrossRefGoogle Scholar
  15. 15.
    Devi, S.P., Rao, K.S., Sangeetha, S.S.: Prediction of surgery times and scheduling of operation theaters in optholmology department. Journal of Medical Systems 36(2), 415–430 (2012)CrossRefGoogle Scholar
  16. 16.
    Gomes, C., Almada-Lobo, B., Borges, J., Soares, C.: Integrating data mining and optimization techniques on surgery scheduling. In: Zhou, S., Zhang, S., Karypis, G. (eds.) ADMA 2012. LNCS, vol. 7713, pp. 589–602. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  17. 17.
    Charlson, M.E., Pompei, P., Ales, K.L., MacKenzie, C.R.: A new method of classifying prognostic comorbidity in longitudinal studies: Development and validation. J. Chronic Dis. 40(5), 373–383 (1987)CrossRefGoogle Scholar
  18. 18.
    Palmer, P.B., O’Connell, D.G.: Regression Analysis For Prediction: Understanding the process. Cardiopulmonary Physical Therapy Journal 20(3), 23 (2009)Google Scholar
  19. 19.
    Heil, D.P., Freedson, P.S., Ahlquist, L.E., Price, J., Rippe, J.M.: Nonexercise regression models to estimate peak oxygen consumption, pp. 599–606. Williams & Wilkins, Baltimore (1995)Google Scholar
  20. 20.
    Dossey, J., Blum, W., Niss, M.: Using Mathematical Competencies to Predict Item Difficulty in PISA: A MEG Study. In: Research on PISA, pp. 23–37. Springer (2013)Google Scholar
  21. 21.
    Hedley, C.B., Yule, I.J.: A method for spatial prediction of daily soil water status for precise irrigation scheduling. Agricultural Water Management 96(12), 1737–1745 (2009)CrossRefGoogle Scholar
  22. 22.
    Hastie, T., Tibshirani, R., Friedman, J.H.: The elements of statistical learning: Data mining, inference, and prediction. Springer, New York (2001)Google Scholar
  23. 23.
    Strum, D.P., May, J.H., Vargas, L.G.: Modeling the uncertainty of surgical procedure times: Comparison of log- normal and normal models. Anesthesiology 92(4), 1160–1167 (2000)CrossRefGoogle Scholar
  24. 24.
    Friedman, J.H.: Multivariate Adaptive Regression Splines. Annals of Statistics 19(1), 1–141 (1991)CrossRefzbMATHMathSciNetGoogle Scholar
  25. 25.
    Jekabsons, G.: ARESLab: Adaptive Regression Splines toolbox for Matlab/Octave (2011),
  26. 26.
    Breiman, L.: Random Forests. Machine Learning 45(1), 5–32 (2001)CrossRefzbMATHGoogle Scholar
  27. 27.
    Vapnik, V.: Support-vector networks. Machine Learning 20(3), 273–297 (1995)zbMATHGoogle Scholar
  28. 28.
    Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by error propagation, DTIC Document (1985)Google Scholar
  29. 29.
    Liaw, A.: Breiman and Cutler’s random forests for classification and regression (2012),

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  1. 1.Institute for Integrated and Intelligent SystemsGriffith UniversityBrisbaneAustralia
  2. 2.The Australian e-Health Research Centre, CSIROBrisbaneAustralia
  3. 3.Gold Coast HospitalGold CoastAustralia

Personalised recommendations