Time‐Dependent Predictive Accuracy in the Presence of Competing Risks

Competing risks arise naturally in time-to-event studies. In this article, we propose time-dependent accuracy measures for a marker when we have censored survival times and competing risks. Time-dependent versions of sensitivity or true positive (TP) fraction naturally correspond to consideration of either cumulative (or prevalent) cases that accrue over a fixed time period, or alternatively to incident cases that are observed among event-free subjects at any select time. Time-dependent (dynamic) specificity (1-false positive (FP)) can be based on the marker distribution among event-free subjects. We extend these definitions to incorporate cause of failure for competing risks outcomes. The proposed estimation for cause-specific cumulative TP/dynamic FP is based on the nearest neighbor estimation of bivariate distribution function of the marker and the event time. On the other hand, incident TP/dynamic FP can be estimated using a possibly nonproportional hazards Cox model for the cause-specific hazards and riskset reweighting of the marker distribution. The proposed methods extend the time-dependent predictive accuracy measures of Heagerty, Lumley, and Pepe (2000, Biometrics 56, 337-344) and Heagerty and Zheng (2005, Biometrics 61, 92-105).

[1]  D. Katsaros,et al.  A Multiparametric Panel for Ovarian Cancer Diagnosis, Prognosis, and Response to Chemotherapy , 2007, Clinical Cancer Research.

[2]  Yingye Zheng,et al.  Prospective Accuracy for Longitudinal Markers , 2007, Biometrics.

[3]  Laurence L. George,et al.  The Statistical Analysis of Failure Time Data , 2003, Technometrics.

[4]  John O'Quigley,et al.  Proportional hazards estimate of the conditional survival function , 2000 .

[5]  J. Phair,et al.  The Multicenter AIDS Cohort Study: rationale, organization, and selected characteristics of the participants. , 1987, American journal of epidemiology.

[6]  M. Schumacher,et al.  Consistent Estimation of the Expected Brier Score in General Survival Models with Right‐Censored Event Times , 2006, Biometrical journal. Biometrische Zeitschrift.

[7]  J. Copas,et al.  Overestimation of the receiver operating characteristic curve for logistic regression , 2002 .

[8]  Jens Perch Nielsen,et al.  A framework for consistent prediction rules based on markers , 1993 .

[9]  Torben Martinussen,et al.  On Estimation and Tests of Time‐Varying Effects in the Proportional Hazards Model , 2004 .

[10]  M. Schemper,et al.  Predictive Accuracy and Explained Variation in Cox Regression , 2000, Biometrics.

[11]  L. V. van't Veer,et al.  Validation and clinical utility of a 70-gene prognostic signature for women with node-negative breast cancer. , 2006, Journal of the National Cancer Institute.

[12]  Mei-Jie Zhang,et al.  Predicting cumulative incidence probability by direct binomial regression , 2008 .

[13]  E. Christensen.  Prognostic models including the Child-Pugh, MELD and Mayo risk scores--where are we and where should we go? , 2004, Journal of hepatology.

[14]  Martin A. Tanner,et al.  The Estimation of the Hazard Function from Randomly Censored Data by the Kernel Method , 1983 .

[15]  M. R. Leadbetter,et al.  Hazard Analysis , 2018, System Safety Engineering and Risk Assessment.

[16]  J. Kalbfleisch,et al.  The Statistical Analysis of Failure Time Data: Kalbfleisch/The Statistical , 2002 .

[17]  E Graf,et al.  Quantifying the Predictive Performance of Prognostic Models for Censored Survival Data with Time‐Dependent Covariates , 2008, Biometrics.

[18]  Zongwu Cai,et al.  Local Linear Estimation for Time-Dependent Coefficients in Cox's Regression Models , 2003 .

[19]  T. Lumley,et al.  Time‐Dependent ROC Curves for Censored Survival Data and a Diagnostic Marker , 2000, Biometrics.

[20]  P. Heagerty,et al.  Survival Model Predictive Accuracy and ROC Curves , 2005, Biometrics.

[21]  M. Akritas.  Nearest Neighbor Estimation of a Bivariate Distribution Under Random Censoring , 1994 .

[22]  Gerhard Dikta,et al.  Bootstrap approximation of nearest neighbor regression function estimates , 1990 .

[23]  J Crowley,et al.  Estimation of failure probabilities in the presence of competing risks: new representations of old estimators. , 1999, Statistics in medicine.

[24]  R. Kronmal,et al.  Incidence of Cardiovascular Disease in Older Americans: The Cardiovascular Health Study , 2005, Journal of the American Geriatrics Society.