Machine learning for improved pathological staging of prostate cancer: A performance comparison on a range of classifiers

Artificial Intelligence in Medicine

Volumn 55, Issue 1, 2012, Pages 25-35

  Regnier Coudert, Olivier ^a   McCall, John ^a   Lothian, Robert ^a   Lam, Thomas ^b   McClinton, Sam ^b   N'Dow, James ^b  

^a ROBERT GORDON UNIVERSITY   (United Kingdom)

^b UNIVERSITY OF ABERDEEN   (United Kingdom)

Author keywords

Bayesian networks; Logistic regression; Partin tables; Predictive modeling; Prostate cancer staging

Indexed keywords

ABERDEEN; AREA UNDER THE ROC CURVE; BAYESIAN NETWORKS (BNS); CLASS LABELS; CONCORDANCE INDEX; DATA SETS; EXTRA VARIABLES; HEURISTIC SEARCH; LOGISTIC REGRESSION; LOGISTIC REGRESSIONS; NAIVE BAYES; PARTIN TABLES; PERFORMANCE COMPARISON; PREDICTIVE METHODS; PREDICTIVE MODELING; PREDICTIVE PERFORMANCE; PREDICTIVE VARIABLES; PROSTATE CANCERS; QUALITY OF LIFE; STAGE PREDICTION; STRUCTURE-LEARNING;

BAYESIAN NETWORKS; DISEASES; FORECASTING; HEURISTIC METHODS; LOGISTICS; NEURAL NETWORKS; PATIENT MONITORING; REGRESSION ANALYSIS; UROLOGY;

PATIENT TREATMENT;

AREA UNDER THE CURVE; ARTICLE; ARTIFICIAL NEURAL NETWORK; CANCER CLASSIFICATION; CANCER STAGING; CLASSIFICATION; COMPARATIVE STUDY; DISEASE MODEL; HOSPITAL; HUMAN; INFORMATION PROCESSING; MACHINE LEARNING; METHODOLOGY; POPULATION; PRIORITY JOURNAL; PROSTATE CANCER; PROSTATECTOMY; QUALITY OF LIFE; UNITED KINGDOM; UNITED STATES;

ALGORITHMS; AREA UNDER CURVE; ARTIFICIAL INTELLIGENCE; BAYES THEOREM; HUMANS; LOGISTIC MODELS; MALE; MODELS, BIOLOGICAL; NEOPLASM STAGING; NEURAL NETWORKS (COMPUTER); NOMOGRAMS; PREDICTIVE VALUE OF TESTS; PROSTATE-SPECIFIC ANTIGEN; PROSTATIC NEOPLASMS; ROC CURVE;

EID: 84858859611     PISSN: 09333657     EISSN: 18732860     Source Type: Journal    
DOI: 10.1016/j.artmed.2011.11.003     Document Type: Article

References (61)

1. International Agency for Research on Cancer-GLOBOCAN. http://globocan.iarc.fr/; 2008 [accessed: 21.09.10].
2. Hayward J., Alvarez S., Ruiz C., Sullivan M., Tseng J., Whalen G. Machine learning of clinical performance in a pancreatic cancer database. Artificial Intelligence in Medicine 2010, 49(3):187-195.
3. Delen D., Walker G., Kadam A. Predicting breast cancer survivability: a comparison of three data mining methods. Artificial Intelligence in Medicine 2005, 34(2):113-127.
4. Partin A., Yoo J., Carter H., Pearson J., Chan D., Epstein J., et al. The use of prostate specific antigen, clinical stage and Gleason score to predict pathological stage in men with localized prostate cancer. The Journal of Urology 1993, 150(1):110-114.
5. Hosmer D., Lemeshow S. Applied logistic regression 2000, Wiley-Interscience, New York, NY, USA.
6. Partin A., Kattan M., Subong E., Walsh P., Wojno K., Oesterling J. Combination of prostate-specific antigen, clinical stage, and Gleason score to predict pathological stage of localized prostate cancer: a multi-institutional update. Journal of the American Medical Association 1997, 277(18):1445-1451.
7. Partin A., Mangold L., Lamm D., Walsh P., Epstein J., Pearson J. Contemporary update of prostate cancer staging nomograms (Partin tables) for the new millennium. Urology 2001, 58(6):843-848.
8. Makarov D., Trock B., Humphreys E., Mangold L., Walsh P., Epstein J. Updated nomogram to predict pathologic stage of prostate cancer given prostate-specific antigen level, clinical stage, and biopsy Gleason score (Partin tables) based on cases from 2000 to 2005. Urology 2007, 69(6):1095-1101.
9. Kattan M., Stapleton A., Wheeler T., Scardino P. Evaluation of a nomogram used to predict the pathologic stage of clinically localized prostate carcinoma. Cancer 1997, 79(3):528-537.
10. Blute M., Bergstralh E., Partin A., Walsh P., Kattan M., Scardino P., et al. Validation of Partin tables for predicting pathological stage of clinically localized prostate cancer. The Journal of Urology 2000, 164(5):1591-1595.
11. Penson D., Grossfeld G., Li Y., Henning J., Lubeck D., Carroll P. How well does the Partin nomogram predict pathological stage after radical prostatectomy in a community based population? Results of the cancer of the prostate strategic urological research endeavor. The Journal of Urology 2002, 167(4):1653-1658.
12. Graefen M., Augustin H., Karakiewicz P., Hammerer P., Haese A., Palisaar J., et al. Can predictive models for prostate cancer patients derived in the United States of America be utilized in European patients? A validation study of the Partin tables. European Urology 2003, 43(1):6-11.
13. Augustin H., Eggert T., Wenske S., Karakiewicz P., Palisaar J., Daghofer F., et al. Comparison of accuracy between the Partin tables of 1997 and 2001 to predict final pathological stage in clinically localized prostate cancer. The Journal of Urology 2004, 171(1):177-181.
14. Eskicorapci S., Karabulut E., Turkeri L., Baltaci S., Cal C., Toktas G., et al. Validation of 2001 Partin tables in Turkey: a multicenter study. European Urology 2005, 47(2):185-189.
15. Karakiewicz P., Lattouf J., Perrotte P., Valiquette L., Benard F., McCormack M., et al. Validation of 1997 Partin tables lymph node invasion predictions in men treated with radical prostatectomy in Montreal Quebec. The Canadian Journal of Urology 2005, 12(2):2588-2592.
16. Song C., Kang T., Ro J., Lee M., Kim C., Ahn H. Nomograms for the prediction of pathologic stage of clinically localized prostate cancer in Korean men. Journal of Korean Medical Science 2005, 20(2):262-266.
17. Gao X., Ren S., Lu X., Xu C., Sun Y. The newer the better? Comparison of the 1997 and 2001 Partin tables for pathologic stage prediction of prostate cancer in China. Urology 2008, 72(5):1096-1101.
18. Bhojani N., Ahyai S., Graefen M., Capitanio U., Suardi N., Shariat S., et al. Partin tables cannot accurately predict the pathological stage at radical prostatectomy. European Journal of Surgical Oncology 2009, 35(2):123-128.
19. Bhojani N., Salomon L., Capitanio U., Suardi N., Shariat S., Jeldres C., et al. External validation of the updated partin tables in a cohort of French and Italian men. International Journal of Radiation Oncology, Biology, Physics 2009, 73(2):347-352.
20. Cruz J., Wishart D. Applications of machine learning in cancer prediction and prognosis. Cancer Informatics 2006, 2:59-77.
21. Jensen F., Nielsen T. Bayesian networks and decision graphs 2007, Springer Verlag, New York, NY, USA.
22. Sobin L. TNM classification of malignant tumours 2009, Wiley-Blackwell, New York, NY, USA.
23. Kirby R. The prostate: small gland, big problem 2002, Prostate Research Campaign UK, Northwood, UK.
24. Shaida N., Malone P. Controversial topics in surgery. open versus laparoscopic radical prostatectomy: the case for open radical prostatectomy. Annals of the Royal College of Surgeons of England 2007, 89:108-110.
25. Brain D., Webb G., Richards D., Beydoun G., Hoffmann A., Compton P. On the effect of data set size on bias and variance in classification learning. Proceedings of the fourth Australian knowledge acquisition workshop 1999, 117-128. University of New South Wales, Sydney, Australia. D. Richards, G. Beydoun, P. Compton, A. Hoffman (Eds.).
26. Hall J., Frank E., Holmes G., Pfahringer B., Reutemann P., Witten I. The weka data mining software: an update. SIGKDD Explorations 2009, 11(1):11-18.
27. Breiman L. Random forests. Machine Learning 2001, 45(1):5-32.
28. Aha D., Kibler D., Albert M. Instance-based learning algorithms. Machine Learning 1991, 6(1):37-66.
29. Platt J. Fast training of support vector machines using sequential minimal optimization. Advances in Kernel methods 1999, 185-208. MIT Press, Cambridge, MA, USA.
30. Rumelhart D, Hinton G, Williams R. Learning internal representations by error propagation. Tech. Rep., California University; 1985.
31. Broomhead D, Lowe D, Signals R, Malvern R. Radial basis functions, multi-variable functional interpolation and adaptive networks. Tech. Rep., Royal Signals and Radar Establishment Malvern; 1988.
32. Han M., Snow P., Brandt J., Partin A. Evaluation of artificial neural networks for the prediction of pathological stage in prostate carcinoma. American Cancer Society 2001, 91(8):1661-1666.
33. Matsui Y., Egawa S., Tsukayama C., Terai A., Kuwao S., Baba S., et al. Artificial neural network analysis for predicting pathological stage of clinically localized prostate cancer in the Japanese population. Japanese Journal of Clinical Oncolology 2002, 32(12):530-535.
34. Veltri R., Chaudhari M., Miller M., Poole E., ÓDowd G., Partin A. Comparison of logistic regression and neural net modeling for prediction of prostate cancer pathologic stage. Clinical Chemistry 2002, 48(10):1828-1834.
35. Borque A., Sanz G., Allepuz C., Plaza L., Gil P., Rioja L. The use of neural networks and logistic regression analysis for predicting pathological stage in men undergoing radical prostatectomy: a population based study. The Journal of Urology 2001, 166(5):1672-1678.
36. Anagnostou T., Remzi M., Lykourinas M., Djavan B. Artificial neural networks for decision-making in urologic oncology. European Urology 2003, 43(6):596-603.
37. Kawakami S., Numao N., Okubo Y., Koga F., Yamamoto S., Saito K., et al. Development, validation, and head-to-head comparison of logistic regression-based nomograms and artificial neural network models predicting prostate cancer on initial extended biopsy. European Urology 2008, 54(3):601-611.
38. Pearl J. Probabilistic reasoning in intelligent systems: networks of plausible inference 1988, Morgan Kaufmann, San Francisco, CA, USA.
39. Robinson R. Counting unlabeled acyclic digraphs. Proceedings of the fifth Australian conference on combinatorial mathematics 1977, 28-43. Springer-Verlag, New York, NY, USA. C. Little (Ed.).
40. Cooper G., Herskovits E. A Bayesian method for the induction of probabilistic networks from data. Machine Learning 1992, 9(4):309-347.
41. Wu Y., McCall J., Corne D. Two novel ant colony optimization approaches for Bayesian network structure learning. Proceedings of the 2010 world congress on computational intelligence 2010, 4473-4479. IEEE Press, Piscataway, NJ, USA. P. Sobrevilla, J. Aranda, S. Xambo (Eds.).
42. Fournier F., McCall J., Petrovski A., Barclay P. Evolved Bayesian network models of rig operations in the Gulf of Mexico. Proceedings of the 2010 world congress on computational intelligence 2010, 1-7. IEEE Press, Piscataway, NJ, USA. P. Sobrevilla, J. Aranda, S. Xambo (Eds.).
43. Langley P., Iba W., Thompson K. An analysis of Bayesian classifiers. Proceedings of the tenth national conference on artificial intelligence 1992, 223-228. AAAI Press, Menlo Park, CA, USA. P. Rosenbloom, P. Szolovits (Eds.).
44. Friedman N., Geiger D., Goldszmidt M. Bayesian network classifiers. Machine Learning 1997, 29(2):131-163.
45. Metz C. Basic principles of ROC analysis. Seminars in Nuclear Medicine 1978, 8:283-298.
46. Harrell F., Califf R., Pryor D., Lee K., Rosati R. Evaluating the yield of medical tests. Journal of the American Medical Association 1982, 247(18):2543-2546.
47. Kohavi R. A study of cross-validation and bootstrap for accuracy estimation and model selection. Proceedings of the fourteenth international joint conference on artificial intelligence, vol. 2 1995, 1137-1145. AAAI Press, Menlo Park, CA, USA. T. Walsh (Ed.).
48. Kabli R., Herrmann F., McCall J. A chain-model genetic algorithm for Bayesian network structure learning. Proceedings of the 9th annual conference on genetic and evolutionary computation 2007, 1271-1278. ACM Press, New York, NY, USA. D. Thierens, H. Beyer, J. Bongard, J. Branke, J. Clark, D. Cliff, A. et (Eds.).
49. Galfano A., Novara G., Iafrate M., Cavalleri S., Martignoni G., Gardiman M., et al. Mathematical models for prognostic prediction in patients with renal cell carcinoma. Urologia Internationalis 2008, 80(2):113-123.
50. Kattan M. Validating a prognostic model. American Cancer Society 2006, 107(11):2523-2524.
51. Deng H., Runger G., Tuv E. Bias of importance measures for multi-valued attributes and solutions. Proceedings of the twenty-first international conference on artificial neural networks 2011, 293-300. Springer, New York, NY, USA. T. Honkela, W. Duch, M. Girolami, S. Kaski (Eds.).
52. Kim S., Moon S., Jung D., Hwang S., Sung C., Cho J., et al. Pre-operative prediction of advanced prostatic cancer using clinical decision support systems: accuracy comparison between support vector machine and artificial neural network. Korean Journal of Radiology 2011, 12(5):588-594.
53. Liu H., Zhang R., Luan F., Yao X., Liu M., Hu Z., et al. Diagnosing breast cancer based on support vector machines. Journal of Chemical Information and Computer Sciences 2003, 43(3):900-907.
54. Byvatov E., Fechner U., Sadowski J., Schneider G. Comparison of support vector machine and artificial neural network systems for drug/nondrug classification. Journal of Chemical Information and Computer Sciences 2003, 43(6):1882-1889.
55. Ramakrishnan N., Hanauer D., Keller B. Mining electronic health records. Computer 2010, 43(10):77-81.
56. Sanchez-Chapado M., Angulo J., Ibarburen C., Aguado F., Ruiz A., Viano J., et al. Comparison of digital rectal examination, transrectal ultrasonography, and multicoil magnetic resonance imaging for preoperative evaluation of prostate cancer. European Urology 1997, 32(2):140-149.
57. Collins G., Lee R., McKelvie G., Rogers A., Hehir M. Relationship between prostate specific antigen, prostate volume and age in the benign prostate. British Journal of Urology 1993, 71(4):445-450.
58. Anastasiadis A., Lichy M., Nagele U., Kuczyk M., Merseburger A., Hennenlotter J., et al. MRI-guided biopsy of the prostate increases diagnostic performance in men with elevated or increasing PSA levels after previous negative TRUS biopsies. European Urology 2006, 50(4):738-749.
59. Antal P., Fannes G., Timmerman D., Moreau Y., De Moor B. Using literature and data to learn Bayesian networks as clinical models of ovarian tumors. Artificial Intelligence in Medicine 2004, 30(3):257-281.
60. Gevaert O., Smet F., Timmerman D., Moreau Y., Moor B. Predicting the prognosis of breast cancer by integrating clinical and microarray data with Bayesian networks. Bioinformatics 2006, 22(14):184-190.
61. Jayasurya K., Fung G., Yu S., Dehing-Oberije C., De Ruysscher D., Hope A., et al. Comparison of Bayesian network and support vector machine models for two-year survival prediction in lung cancer patients treated with radiotherapy. Medical Physics 2010, 37(4):1401-1407.