Statistical-learning strategies generate only modestly performing predictive models for urinary symptoms following external beam radiotherapy of the prostate: A comparison of conventional and machine-learning methods

Medical Physics

Volumn 43, Issue 5, 2016, Pages 2040-2052

  Yahya, Noorazrul ^a,b   Ebert, Martin A ^a,c   Bulsara, Max ^d   House, Michael J ^a   Kennedy, Angel ^b   Joseph, David J ^a,b   Denham, James W ^e  

^a UNIVERSITY OF WESTERN AUSTRALIA   (Australia)

^b UNIVERSITI KEBANGSAAN MALAYSIA   (Malaysia)

^c SIR CHARLES GAIRDNER HOSPITAL   (Australia)

^d UNIVERSITY OF NOTRE DAME   (Australia)

^e UNIVERSITY OF NEWCASTLE   (Australia)

Author keywords

elastic net; neural network; normal tissue complications; random forest; support vector machine

Indexed keywords

DECISION TREES; FORECASTING; NEURAL NETWORKS; RADIOTHERAPY; REGRESSION ANALYSIS; UROLOGY; VECTORS;

ELASTIC NET; MULTIVARIATE ADAPTIVE REGRESSION SPLINES; NEURAL-NETWORKS; NORMAL TISSUE; NORMAL TISSUE COMPLICATION; RANDOM FORESTS; SUPPORT VECTORS MACHINE; TISSUE COMPLICATIONS; URINARY SYMPTOMS;

SUPPORT VECTOR MACHINES;

ARTICLE; DISEASE SEVERITY; DYSURIA; EXTERNAL BEAM RADIOTHERAPY; HEMATURIA; HUMAN; MACHINE LEARNING; MAJOR CLINICAL STUDY; PROSTATE; URINARY FREQUENCY; URINARY TRACT DISEASE; URINE INCONTINENCE; ADVERSE EFFECTS; AGED; AREA UNDER THE CURVE; ARTIFICIAL NEURAL NETWORK; BIOLOGICAL MODEL; COMORBIDITY; COMPARATIVE STUDY; COMPLICATION; FOLLOW UP; MALE; MIDDLE AGED; MULTIVARIATE ANALYSIS; PROCEDURES; PROGNOSIS; PROSTATIC NEOPLASMS; RADIATION RESPONSE; RECEIVER OPERATING CHARACTERISTIC; SEVERITY OF ILLNESS INDEX; STATISTICAL MODEL; URINATION DISORDERS; VERY ELDERLY;

AGED; AGED, 80 AND OVER; AREA UNDER CURVE; COMORBIDITY; FOLLOW-UP STUDIES; HUMANS; LOGISTIC MODELS; MACHINE LEARNING; MALE; MIDDLE AGED; MODELS, BIOLOGICAL; MULTIVARIATE ANALYSIS; NEURAL NETWORKS (COMPUTER); PROGNOSIS; PROSTATE; PROSTATIC NEOPLASMS; RADIOTHERAPY; ROC CURVE; SEVERITY OF ILLNESS INDEX; URINATION DISORDERS;

EID: 84964329141     PISSN: 00942405     EISSN: 24734209     Source Type: Journal    
DOI: 10.1118/1.4944738     Document Type: Article

References (55)

1. S. L. Gulliford, S. Webb, C. G. Rowbottom, D. W. Corne, and D. P. Dearnaley, "Use of artificial neural networks to predict biological outcomes for patients receiving radical radiotherapy of the prostate," Radiother. Oncol. 71, 3-12 (2004). 10.1016/j.radonc.2003.03.001
2. A. Pella, R. Cambria, M. Riboldi, B. A. Jereczek-Fossa, C. Fodor, D. Zerini, A. E. Torshabi, F. Cattani, C. Garibaldi, G. Pedroli, G. Baroni, and R. Orecchia, "Use of machine learning methods for prediction of acute toxicity in organs at risk following prostate radiotherapy," Med. Phys. 38, 2859-2867 (2011). 10.1118/1.3582947
3. S. Tomatis, T. Rancati, C. Fiorino, V. Vavassori, G. Fellin, E. Cagna, F. A. Mauro, G. Girelli, A. Monti, M. Baccolini, G. Naldi, C. Bianchi, L. Menegotti, M. Pasquino, M. Stasi, and R. Valdagni, "Late rectal bleeding after 3D-CRT for prostate cancer: Development of a neural-network-based predictive model," Phys. Med. Biol. 57, 1399-1412 (2012). 10.1088/0031-9155/57/5/1399
4. F. Buettner, S. L. Gulliford, S. Webb, and M. Partridge, "Using dose-surface maps to predict radiation-induced rectal bleeding: A neural network approach," Phys. Med. Biol. 54, 5139-5153 (2009). 10.1088/0031-9155/54/17/005
5. I. El Naqa, J. D. Bradley, P. E. Lindsay, A. J. Hope, and J. O. Deasy, "Predicting radiotherapy outcomes using statistical learning techniques," Phys. Med. Biol. 54, S9-S30 (2009). 10.1088/0031-9155/54/18/S02
6. S. Chen, S. Zhou, J. Zhang, F. F. Yin, L. B. Marks, and S. K. Das, "A neural network model to predict lung radiation-induced pneumonitis," Med. Phys. 34, 3420-3427 (2007). 10.1118/1.2759601
7. S. Chen, S. Zhou, F. F. Yin, L. B. Marks, and S. K. Das, "Investigation of the support vector machine algorithm to predict lung radiation-induced pneumonitis," Med. Phys. 34, 3808-3814 (2007). 10.1118/1.2776669
8. S. K. Das, S. M. Zhou, J. Zhang, F. F. Yin, M. W. Dewhirst, and L. B. Marks, "Predicting lung radiotherapy-induced pneumonitis using a model combining parametric lyman probit with nonparametric decision trees," Int. J. Radiat. Oncol., Biol., Phys. 68, 1212-1221 (2007). 10.1016/j.ijrobp.2007.03.064
9. S. F. Chen, S. M. Zhou, F. F. Yin, L. B. Marks, and S. K. Das, "Using patient data similarities to predict radiation pneumonitis via a self-organizing map," Phys. Med. Biol. 53, 203-216 (2008). 10.1088/0031-9155/53/1/014
10. S. K. Das, S. F. Chen, J. O. Deasy, S. M. Zhou, F. F. Yin, and L. B. Marks, "Combining multiple models to generate consensus: Application to radiation-induced pneumonitis prediction," Med. Phys. 35, 5098-5109 (2008). 10.1118/1.2996012
11. T. W. Schiller, Y. X. Chen, I. El Naga, and J. O. Deasy, "Modeling radiation-induced lung injury risk with an ensemble of support vector machines," Neurocomputing 73, 1861-1867 (2010). 10.1016/j.neucom.2009.09.023
12. J. D. Ospina, J. Zhu, C. Chira, A. Bossi, J. B. Delobel, V. Beckendorf, B. Dubray, J. L. Lagrange, J. C. Correa, A. Simon, O. Acosta, and R. de Crevoisier, "Random forests to predict rectal toxicity following prostate cancer radiation therapy," Int. J. Radiat. Oncol., Biol., Phys. 89, 1024-1031 (2014). 10.1016/j.ijrobp.2014.04.027
13. O. Gayou, S. K. Das, S. M. Zhou, L. B. Marks, D. S. Parda, and M. Miften, "A genetic algorithm for variable selection in logistic regression analysis of radiotherapy treatment outcomes," Med. Phys. 35, 5426-5433 (2008). 10.1118/1.3005974
14. K. Wopken, H. P. Bijl, A. van der Schaaf, M. E. Christianen, O. Chouvalova, S. F. Oosting, B. F. van der Laan, J. L. Roodenburg, C. R. Leemans, B. J. Slotman, P. Doornaert, R. J. Steenbakkers, I. M. Verdonck-de Leeuw, and J. A. Langendijk, "Development and validation of a prediction model for tube feeding dependence after curative (chemo-) radiation in head and neck cancer," PLoS One 9, e94879 (2014). 10.1371/journal.pone.0094879
15. T. F. Lee, M. H. Liou, Y. J. Huang, P. J. Chao, H. M. Ting, H. Y. Lee, and F. M. Fang, "LASSO NTCP predictors for the incidence of xerostomia in patients with head and neck squamous cell carcinoma and nasopharyngeal carcinoma," Sci. Rep. 4, no. 6217 (2014). 10.1038/srep06217
16. P. Lambin, R. G. P. M. van Stiphout, M. H. W. Starmans, E. Rios-Velazquez, G. Nalbantov, H. J. W. L. Aerts, E. Roelofs, W. van Elmpt, P. C. Boutros, P. Granone, V. Valentini, A. C. Begg, D. De Ruysscher, and A. Dekker, "Predicting outcomes in radiation oncology-multifactorial decision support systems," Nat. Rev. Clin. Oncol. 10, 27-40 (2013). 10.1038/nrclinonc.2012.196
17. M. J. Zelefsky, E. J. Levin, M. Hunt, Y. Yamada, A. M. Shippy, A. Jackson, and H. I. Amols, "Incidence of late rectal and urinary toxicities after three-dimensional conformal radiotherapy and intensity-modulated radiotherapy for localized prostate cancer," Int. J. Radiat. Oncol., Biol., Phys. 70, 1124-1129 (2008). 10.1016/j.ijrobp.2007.11.044
18. M. J. Zelefsky, M. Kollmeier, B. Cox, A. Fidaleo, D. Sperling, X. Pei, B. Carver, J. Coleman, M. Lovelock, and M. Hunt, "Improved clinical outcomes with high-dose image guided radiotherapy compared with non-IGRT for the treatment of clinically localized prostate cancer," Int. J. Radiat. Oncol., Biol., Phys. 84, 125-129 (2012). 10.1016/j.ijrobp.2011.11.047
19. H. Yamazaki, S. Nakamura, T. Nishimura, K. Yoshida, Y. Yoshioka, M. Koizumi, and K. Ogawa, "Transitioning from conventional radiotherapy to intensity-modulated radiotherapy for localized prostate cancer: Changing focus from rectal bleeding to detailed quality of life analysis," J. Radiat. Res. 55, 1033-1047 (2014). 10.1093/jrr/rru061
20. T. F. Lee, P. J. Chao, H. M. Ting, L. Y. Chang, Y. J. Huang, J. M. Wu, H. Y. Wang, M. F. Horng, C. M. Chang, J. H. Lan, Y. Y. Huang, F. M. Fang, and S. W. Leung, "Using multivariate regression model with least absolute shrinkage and selection operator (lasso) to predict the incidence of xerostomia after intensity-modulated radiotherapy for head and neck cancer," PLoS One 9, e89700 (2014). 10.1371/journal.pone.0089700
21. A. L. Boulesteix, "Ten simple rules for reducing overoptimistic reporting in methodological computational research," PLoS Comput. Biol. 11, e1004191 (2015). 10.1371/journal.pcbi.1004191
22. J. W. Denham, C. Wilcox, D. Joseph, N. A. Spry, D. S. Lamb, K.-H. Tai, J. Matthews, C. Atkinson, S. Turner, D. Christie, N. K. Gogna, L. Kenny, G. Duchesne, B. Delahunt, and P. McElduff, "Quality of life in men with locally advanced prostate cancer treated with leuprorelin and radiotherapy with or without zoledronic acid (TROG 03.04 RADAR): Secondary endpoints from a randomised phase 3 factorial trial," Lancet Oncol. 13, 1260-1270 (2012). 10.1016/S1470-2045(12)70423-0
23. J. W. Denham, D. Joseph, D. S. Lamb, N. A. Spry, G. Duchesne, J. Matthews, C. Atkinson, K. H. Tai, D. Christie, L. Kenny, S. Turner, N. K. Gogna, T. Diamond, B. Delahunt, C. Oldmeadow, J. Attia, and A. Steigler, "Short-term androgen suppression and radiotherapy versus intermediate-term androgen suppression and radiotherapy, with or without zoledronic acid, in men with locally advanced prostate cancer (TROG 03.04 RADAR): An open-label, randomised, phase 3 factorial trial," Lancet Oncol. 15, 1076-1089 (2014). 10.1016/S1470-2045(14)70328-6
24. J. W. Denham, A. Steigler, D. Joseph, D. S. Lamb, N. A. Spry, G. Duchesne, C. Atkinson, J. Matthews, S. Turner, L. Kenny, K. H. Tai, N. K. Gogna, S. Gill, H. Tan, R. Kearvell, J. Murray, M. Ebert, A. Haworth, A. Kennedy, B. Delahunt, C. Oldmeadow, E. G. Holliday, and J. Attia, "Radiation dose escalation or longer androgen suppression for locally advanced prostate cancer? Data from the TROG 03.04 RADAR trial," Radiother. Oncol. 115, 301-307 (2015). 10.1016/j.radonc.2015.05.016
25. J. W. Denham, C. Wilcox, D. S. Lamb, N. A. Spry, G. Duchesne, C. Atkinson, J. Matthews, S. Turner, L. Kenny, K. H. Tai, N. K. Gogna, M. Ebert, B. Delahunt, P. McElduff, and D. Joseph, "Rectal and urinary dysfunction in the TROG 03.04 RADAR trial for locally advanced prostate cancer," Radiother. Oncol. 105, 184-192 (2012). 10.1016/j.radonc.2012.09.018
26. A. Haworth, R. Kearvell, P. B. Greer, B. Hooton, J. W. Denham, D. Lamb, G. Duchesne, J. Murray, and D. Joseph, "Assuring high quality treatment delivery in clinical trials-Results from the Trans-Tasman radiation oncology group (TROG) study 03.04 'RADAR' set-up accuracy study," Radiother. Oncol. 90, 299-306 (2009). 10.1016/j.radonc.2008.10.011
27. R. Kearvell, A. Haworth, M. A. Ebert, J. Murray, B. Hooton, S. Richardson, D. J. Joseph, D. Lamb, N. A. Spry, G. Duchesne, and J. W. Denham, "Quality improvements in prostate radiotherapy: Outcomes and impact of comprehensive quality assurance during the TROG 03.04 'RADAR' trial," J. Med. Imaging Radiat. Oncol. 57, 247-257 (2013). 10.1111/1754-9485.12025
28. "Lent soma scales for all anatomic sites," Int. J. Radiat. Oncol., Biol., Phys. 31, 1049-1091 (1995). 10.1016/0360-3016(95)90159-0
29. M. A. Ebert, A. Haworth, R. Kearvell, B. Hooton, R. Coleman, N. Spry, S. Bydder, and D. Joseph, "Detailed review and analysis of complex radiotherapy clinical trial planning data: Evaluation and initial experience with the SWAN software system," Radiother. Oncol. 86, 200-210 (2008). 10.1016/j.radonc.2007.11.013
30. A. N. Viswanathan, E. D. Yorke, L. B. Marks, P. J. Eifel, and W. U. Shipley, "Radiation dose-volume effects of the urinary bladder," Int. J. Radiat. Oncol., Biol., Phys. 76, S116-S122 (2010). 10.1016/j.ijrobp.2009.02.090
31. S. M. Bentzen, W. Dorr, R. Gahbauer, R. W. Howell, M. C. Joiner, B. Jones, D. T. Jones, A. J. van der Kogel, A. Wambersie, and G. Whitmore, "Bioeffect modeling and equieffective dose concepts in radiation oncology-terminology, quantities and units," Radiother. Oncol. 105, 266-268 (2012). 10.1016/j.radonc.2012.10.006
32. A. Niemierko, "Reporting and analyzing dose distributions: A concept of equivalent uniform dose," Med. Phys. 24, 103-110 (1997). 10.1118/1.598063
33. N. Yahya, M. A. Ebert, M. Bulsara, A. Haworth, A. Kennedy, D. J. Joseph, and J. W. Denham, "Dosimetry, clinical factors and medication intake influencing urinary symptoms after prostate radiotherapy: An analysis of data from the RADAR prostate radiotherapy trial," Radiother. Oncol. 116, 112-118 (2015). 10.1016/j.radonc.2015.06.011
34. N. Yahya, M. A. Ebert, M. Bulsara, M. J. House, A. Kennedy, D. J. Joseph, and J. W. Denham, "Urinary symptoms following external beam radiotherapy of the prostate: Dose-symptom correlates with multiple-event and event-count models," Radiother. Oncol. 117, 277-282 (2015). 10.1016/j.radonc.2015.10.003
35. H. Zou and T. Hastie, "Regularization and variable selection via the elastic net," J. R. Stat. Soc. B 67, 301-320 (2005). 10.1111/j.1467-9868.2005.00503.x
36. L. Breiman, "Random forests," Mach. Learn. 45, 5-32 (2001). 10.1023/A:1010933404324
37. W. N. Venables and B. D. Ripley, Modern Applied Statistics with S, 4th ed. (Springer, New York, NY, 2002).
38. J. H. Friedman, "Multivariate adaptive regression splines," Ann. Stat. 19, 1-67 (1991). 10.1214/aos/1176347963
39. C. J. Xu, A. van der Schaaf, A. A. Van't Veld, J. A. Langendijk, and C. Schilstra, "Statistical validation of normal tissue complication probability models," Int. J. Radiat. Oncol., Biol., Phys. 84, e123-e129 (2012). 10.1016/j.ijrobp.2012.02.022
40. N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, "SMOTE: Synthetic minority over-sampling technique," J. Artif. Intell. Res. 16, 321-357 (2002).
41. L. Breiman, J. Friedman, C. J. Stone, and R. A. Olshen, Classification and Regression Trees (Wadsworth International Group, Belmont, CA, 1984).
42. M. Kuhn, "Building predictive models in R using the caret package," J. Stat. Software 28, 1-26 (2008). 10.18637/jss.v028.i05
43. R Development Core Team, R: A Language and Environment for Statistical Computing (R Foundation for Statistical Computing, Vienna, Austria, 2013).
44. J. Friedman, T. Hastie, and R. Tibshirani, "Regularization paths for generalized linear models via coordinate descent," J. Stat. Software 33, 1-22 (2010). 10.18637/jss.v033.i01
45. A. Karatzoglou, K. Hornik, A. Smola, and A. Zeileis, "Kernlab-An S4 package for kernel methods in R," J. Stat. Software 11, 1-20 (2004). 10.18637/jss.v011.i09
46. A. Liaw and M. Wiener, "Classification and regression by randomForest," R. News 2, 18-22 (2002).
47. J. N. Cooper, L. Wei, S. A. Fernandez, P. C. Minneci, and K. J. Deans, "Pre-operative prediction of surgical morbidity in children: Comparison of five statistical models," Comput. Biol. Med. 57, 54-65 (2015). 10.1016/j.compbiomed.2014.11.009
48. P. Gao, X. Zhou, Z. N. Wang, Y. X. Song, L. L. Tong, Y. Y. Xu, Z. Y. Yue, and H. M. Xu, "Which is a more accurate predictor in colorectal survival analysis? Nine data mining algorithms vs. the TNM staging system," PLoS One 7, e42015 (2012). 10.1371/journal.pone.0042015
49. T. G. Dietterich, "Ensemble methods in machine learning," Lect. Notes Comput. Sci. 1857, 1-15 (2000). 10.1007/3-540-45014-9_1
50. M. Fernndez-Delgado, E. Cernadas, S. Barro, and D. Amorim, "Do we need hundreds of classifiers to solve real world classification problems?," J. Mach. Learn. Res. 15, 3133-3181 (2014).
51. T. Hastie, R. Tibshirani, and J. H. Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd ed. (Springer, New York, NY, 2009).
52. A. L. Boulesteix, S. Lauer, and M. J. Eugster, "A plea for neutral comparison studies in computational sciences," PLoS One 8, e61562 (2013). 10.1371/journal.pone.0061562
53. T. Rosewall, C. Catton, G. Currie, A. Bayley, P. Chung, J. Wheat, and M. Milosevic, "The relationship between external beam radiotherapy dose and chronic urinary dysfunction-a methodological critique," Radiother. Oncol. 97, 40-47 (2010). 10.1016/j.radonc.2010.08.002
54. C. Seiffert, T. M. Khoshgoftaar, J. Van Hulse, and A. Napolitano, "Rusboost: A hybrid approach to alleviating class imbalance," IEEE Trans. Syst., Man., Cybernetics 40, 185-197 (2010). 10.1109/TSMCA.2009.2029559
55. F. Palorini, C. Cozzarini, S. Gianolini, T. Rancati, V. Carillo, A. Botti, C. Iotti, R. Valdagni, and C. Fiorino, "Bladder dose-surface maps show evidence of spatial effects for the risk of acute urinary toxicity after moderate hypofractionated radiation for prostate cancer," Int. J. Radiat. Oncol., Biol., Phys. 90, S42-S43 (2014). 10.1016/j.ijrobp.2014.05.165