Probability Modeling and Statistical Inference in Cancer Screening.
- Boca Raton, FL 33431, U.S.A | CRC Press | 2024.
- 286 Pages Includes Index
Cancer screening has been carried out for six decades – however, there are many unsolved problems: how to estimate key parameters involved in screenings, such as sensitivity, the time duration in the preclinical state (i.e., sojourn time), and time duration in the disease-free state; how to estimate the distribution of lead time, the diagnosis time advanced by screening; how to evaluate the long-term outcomes of screening, including the probability of overdiagnosis among the screen-detected; when to schedule the first exam based on one’s current age and risk tolerance; and when to schedule the upcoming exam based on one’s screening history, age, and risk tolerance. These problems need proper probability models and statistical methods in order to be dealt with.
Features:
This book gives a concise account of the analysis of cancer screening data, using probability models and statistical methods. Real data sets are provided so that cancer researchers and statisticians can apply the methods in the learning process. It develops statistical methods in the commonly used disease progressive model. It provides solutions to practical problems and introduces open problems. It provides a framework for the most recent developments based on the author’s research.
The book is primarily aimed at researchers and practitioners from biostatistics and cancer research. Readers should have the prerequisite knowledge of calculus, probability, and statistical inference. The book could be used as a one-semester textbook on the topic of cancer screening methodology for a graduate-level course.
978-1-032-51330-0 (hbk) 978-1-032-51831-2 (pbk) 978-1-003-40412-5 (ebk)
= Adapted from Figure Adapted from Table age groups asymptomatic b₁ Bayesian inference bo breast cancer calculate colorectal cancer conditional probability credible interval current age tK1 density curve disease disease-free Dongfeng Wu enters the preclinical female heavy smokers fL(z future screening interval gender HIP data HPD interval increases initial screening age lead time density lead time distribution lifetime likelihood function long-term outcomes lung cancer male heavy smokers Markov Chain mean s.e. mean sojourn median MLE mo mode MST mutually exclusive events NLST NLST-CT data no-early-detection o² onset P(Case P(IK P(OverD P(TrueED past screening interval PDF PDF Curve posterior mean posterior samples preclinical state Sp probability density function probability of incidence probability of overdiagnosis probability of true-early-detection random variable screen-detected screening age t0 screening data screening exam screening history screening program screening sensitivity simulation sputum cytology ẞ standard deviation t₁ three key parameters tk tk₁ x)dx yr απ β βι µ Ρ Σ