We consider the cancer post-treatment surveillance to be represented by a discrete observation process with a non-zero false-negative rate. Using a simple stochastic model of cancer recurrence derived within the random minima framework, we obtain parametric estimates of both the time-to-recurrence distribution and the probability of false-negative diagnosis. Then assuming the false-negative rate known, we give a nonparametric maximum likelihood estimator for the tumor latency time distribution. When designing an optimal strategy of post-treatment surveillance, we proceed from the minimum of the expected delay in detecting tumor recurrence as a pertinent criterion of optimality. To solve this problem we give a dynamic programming algorithm. We illustrate the methods by analyzing data on breast cancer recurrence.
%0 Journal Article
%1 Tsodikov.1995.Discretes
%A Tsodikov, A. D.
%A Asselain, B.
%A Fourque, A.
%A Hoang, T.
%A Yakovlev, AYu
%D 1995
%J Biometrics
%K Algorithms Breast_Neoplasms/pathology/therapy False_Negative_Reactions Female Follow-Up_Studies Humans Mathematics Models,_Statistical Probability Recurrence Time_Factors Treatment_Failure
%N 2
%P 437–447
%T Discrete strategies of cancer post-treatment surveillance. Estimation and optimization problems
%V 51
%X We consider the cancer post-treatment surveillance to be represented by a discrete observation process with a non-zero false-negative rate. Using a simple stochastic model of cancer recurrence derived within the random minima framework, we obtain parametric estimates of both the time-to-recurrence distribution and the probability of false-negative diagnosis. Then assuming the false-negative rate known, we give a nonparametric maximum likelihood estimator for the tumor latency time distribution. When designing an optimal strategy of post-treatment surveillance, we proceed from the minimum of the expected delay in detecting tumor recurrence as a pertinent criterion of optimality. To solve this problem we give a dynamic programming algorithm. We illustrate the methods by analyzing data on breast cancer recurrence.
@article{Tsodikov.1995.Discretes,
abstract = {We consider the cancer post-treatment surveillance to be represented by a discrete observation process with a non-zero false-negative rate. Using a simple stochastic model of cancer recurrence derived within the random minima framework, we obtain parametric estimates of both the time-to-recurrence distribution and the probability of false-negative diagnosis. Then assuming the false-negative rate known, we give a nonparametric maximum likelihood estimator for the tumor latency time distribution. When designing an optimal strategy of post-treatment surveillance, we proceed from the minimum of the expected delay in detecting tumor recurrence as a pertinent criterion of optimality. To solve this problem we give a dynamic programming algorithm. We illustrate the methods by analyzing data on breast cancer recurrence.},
added-at = {2014-10-10T19:55:58.000+0200},
author = {Tsodikov, A. D. and Asselain, B. and Fourque, A. and Hoang, T. and Yakovlev, AYu},
biburl = {https://www.bibsonomy.org/bibtex/244b487cd17771990d6deceac2ec38755/drtester},
interhash = {c6be2fda49240544f688c66e58ef3ab5},
intrahash = {44b487cd17771990d6deceac2ec38755},
journal = {Biometrics},
keywords = {Algorithms Breast_Neoplasms/pathology/therapy False_Negative_Reactions Female Follow-Up_Studies Humans Mathematics Models,_Statistical Probability Recurrence Time_Factors Treatment_Failure},
number = 2,
pages = {437–447},
timestamp = {2014-10-10T19:55:58.000+0200},
title = {Discrete strategies of cancer post-treatment surveillance. Estimation and optimization problems},
volume = 51,
year = 1995
}