Censored Time Trees/spl trade/ for predicting time to PSA recurrence

The task of predicting prostate-specific androgen (PSA) recurrence following radical prostatectomy is important for the surveillance of patients with prostate cancer. This regression problem is complicated by the fact that data is censored, and there is no standard measurement of error for censored data. This paper applies modified regression trees, called Censored Time Trees (cTT/spl trade/), to predict time to PSA recurrence. In order to assess the performance of cTT/spl trade/, we explored different error measurements, such as the concordance index, AUC (area under the Receiver Operating Characteristic curve), sensitivity and specificity, and average error. Bagging of Censored Time Trees/spl trade/ improves their performance. Bagging cTT/spl trade/ also performs slightly better than support vector regression and linear programming, both modified for censored data.

[1]  M. LeBlanc,et al.  Relative risk trees for censored survival data. , 1992, Biometrics.

[2]  Aaas News,et al.  Book Reviews , 1893, Buffalo Medical and Surgical Journal.

[3]  F. Harrell,et al.  Evaluating the yield of medical tests. , 1982, JAMA.

[4]  David J. Hand,et al.  A Simple Generalisation of the Area Under the ROC Curve for Multiple Class Classification Problems , 2001, Machine Learning.

[5]  J. Goo,et al.  Receiver Operating Characteristic (ROC) Curve: Practical Review for Radiologists , 2004, Korean journal of radiology.

[6]  Torsten Hothorn,et al.  Bagging survival trees , 2002, Statistics in medicine.

[7]  R. Olshen,et al.  Tree-structured survival analysis. , 1985, Cancer treatment reports.

[8]  David R. Cox,et al.  Regression models and life tables (with discussion , 1972 .

[9]  M. Kattan,et al.  Postoperative nomogram for disease recurrence after radical prostatectomy for prostate cancer. , 1999, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[10]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.

[11]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[12]  P. Bühlmann,et al.  Survival ensembles. , 2006, Biostatistics.

[13]  Tom Fawcett,et al.  Analysis and Visualization of Classifier Performance: Comparison under Imprecise Class and Cost Distributions , 1997, KDD.

[14]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[15]  M. Kenward,et al.  An Introduction to the Bootstrap , 2007 .

[16]  Mark R. Segal,et al.  Regression Trees for Censored Data , 1988 .

[17]  R B Davis,et al.  Exponential survival trees. , 1989, Statistics in medicine.

[18]  Lian Yan,et al.  Predicting prostate cancer recurrence via maximizing the concordance index , 2004, KDD.

[19]  S. Dudoit,et al.  Tree-based multivariate regression and density estimation with right-censored data , 2004 .

[20]  Dustin Boswell,et al.  Introduction to Support Vector Machines , 2002 .

[21]  William Nick Street,et al.  Breast Cancer Diagnosis and Prognosis Via Linear Programming , 1995, Oper. Res..