TY - JOUR
T1 - Inverse decision theory
T2 - Characterizing losses for a decision rule with applications in cervical cancer screening
AU - Swartz, Richard J.
AU - Cox, Dennis D.
AU - Cantor, Scott B.
AU - Davies, Kalatu
AU - Follen, Michele
N1 - Funding Information:
Richard J. Swartz is Instructor, Department of Biostatistics and Applied Mathematics and Department of Behavioral Science, The University of Texas M. D. Anderson Cancer Center, Houston, TX 77030 (E-mail: rswartz@mdanderson.org). Dennis D. Cox is Professor, Department of Statistics, Rice University, Houston, TX 77005 (E-mail: dcox@stat.rice.edu). Scott B. Cantor is Associate Professor, Department of Biostatistics and Applied Mathematics, The University of Texas M. D. Anderson Cancer Center, Houston, TX 77030. Kalatu Davies is Vigre Postdoctoral Fellow and Pffeifer Lecturer, Department of Statistics, Rice University, Houston, TX 77005. Michele Follen is Professor, Department of Gynecologic Oncology and Director, Biomedical Engineering Center, The University of Texas M. D. Anderson Cancer Center, Houston, TX 77030, and Professor, Department of Obstetrics and Gynecology, The University of Texas Health Science Center, Houston, TX 77030. This research was supported in part by National Cancer Institute grant 2PO1-CA82710 and in part by a cancer prevention fellowship supported by National Cancer Institute grant R25 CA57730.
PY - 2006/3
Y1 - 2006/3
N2 - Identifying an optimal decision rule using Bayesian decision theory requires priors, likelihoods, and losses. In many medical settings, we can develop priors and likelihoods, but specifying losses can be difficult, especially when considering both patient outcomes and economic costs. If there is a widely accepted treatment strategy, then we can consider the inverse problem and find a region in the space of losses where the procedure is optimal. We call this approach inverse decision theory (IDT). We apply IDT to the standard of care for diagnosis and treatment of precancerous lesions of the cervix, and consider an alternative procedure that has been proposed. We use a Bayesian approach to estimate the probabilities associated with the diagnostic tests and make inferences about the region in loss space where these medical procedures are optimal. In particular, we find evidence supporting the current standard of care.
AB - Identifying an optimal decision rule using Bayesian decision theory requires priors, likelihoods, and losses. In many medical settings, we can develop priors and likelihoods, but specifying losses can be difficult, especially when considering both patient outcomes and economic costs. If there is a widely accepted treatment strategy, then we can consider the inverse problem and find a region in the space of losses where the procedure is optimal. We call this approach inverse decision theory (IDT). We apply IDT to the standard of care for diagnosis and treatment of precancerous lesions of the cervix, and consider an alternative procedure that has been proposed. We use a Bayesian approach to estimate the probabilities associated with the diagnostic tests and make inferences about the region in loss space where these medical procedures are optimal. In particular, we find evidence supporting the current standard of care.
KW - Bayesian decision theory
KW - Cervical intraepithelial neoplasia
KW - Cost-benefit ratio
KW - Medical decision making
KW - Squamous intraepithelial neoplasia
UR - http://www.scopus.com/inward/record.url?scp=33645512674&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=33645512674&partnerID=8YFLogxK
U2 - 10.1198/016214505000000998
DO - 10.1198/016214505000000998
M3 - Article
AN - SCOPUS:33645512674
SN - 0162-1459
VL - 101
SP - 1
EP - 8
JO - Journal of the American Statistical Association
JF - Journal of the American Statistical Association
IS - 473
ER -