A utility/cost analysis of breast cancer risk prediction algorithms

Craig K. Abbey, Yirong Wu, Elizabeth S. Burnside, Adam Wunderlich, Frank W. Samuelson, John M Boone

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Breast cancer risk prediction algorithms are used to identify subpopulations that are at increased risk for developing breast cancer. They can be based on many different sources of data such as demographics, relatives with cancer, gene expression, and various phenotypic features such as breast density. Women who are identified as high risk may undergo a more extensive (and expensive) screening process that includes MRI or ultrasound imaging in addition to the standard full-field digital mammography (FFDM) exam. Given that there are many ways that risk prediction may be accomplished, it is of interest to evaluate them in terms of expected cost, which includes the costs of diagnostic outcomes. In this work we perform an expected-cost analysis of risk prediction algorithms that is based on a published model that includes the costs associated with diagnostic outcomes (true-positive, false-positive, etc.). We assume the existence of a standard screening method and an enhanced screening method with higher scan cost, higher sensitivity, and lower specificity. We then assess expected cost of using a risk prediction algorithm to determine who gets the enhanced screening method under the strong assumption that risk and diagnostic performance are independent. We find that if risk prediction leads to a high enough positive predictive value, it will be cost-effective regardless of the size of the subpopulation. Furthermore, in terms of the hit-rate and false-alarm rate of the of the risk prediction algorithm, iso-cost contours are lines with slope determined by properties of the available diagnostic systems for screening.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment
PublisherSPIE
Volume9787
ISBN (Electronic)9781510600225
DOIs
StatePublished - 2016
EventMedical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment - San Diego, United States
Duration: Mar 2 2016Mar 3 2016

Other

OtherMedical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment
CountryUnited States
CitySan Diego
Period3/2/163/3/16

Fingerprint

cost analysis
breast
Cost-Benefit Analysis
cancer
Breast Neoplasms
Costs and Cost Analysis
costs
predictions
Screening
screening
Costs
oncogenes
Mammography
gene expression
Information Storage and Retrieval
Neoplasm Genes
false alarms
Gene expression
Magnetic resonance imaging
Ultrasonography

Keywords

  • Breast cancer screening
  • Diagnostic utility
  • Expected cost
  • Risk prediction

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Abbey, C. K., Wu, Y., Burnside, E. S., Wunderlich, A., Samuelson, F. W., & Boone, J. M. (2016). A utility/cost analysis of breast cancer risk prediction algorithms. In Medical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment (Vol. 9787). [97871J] SPIE. https://doi.org/10.1117/12.2217850

A utility/cost analysis of breast cancer risk prediction algorithms. / Abbey, Craig K.; Wu, Yirong; Burnside, Elizabeth S.; Wunderlich, Adam; Samuelson, Frank W.; Boone, John M.

Medical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment. Vol. 9787 SPIE, 2016. 97871J.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abbey, CK, Wu, Y, Burnside, ES, Wunderlich, A, Samuelson, FW & Boone, JM 2016, A utility/cost analysis of breast cancer risk prediction algorithms. in Medical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment. vol. 9787, 97871J, SPIE, Medical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment, San Diego, United States, 3/2/16. https://doi.org/10.1117/12.2217850
Abbey CK, Wu Y, Burnside ES, Wunderlich A, Samuelson FW, Boone JM. A utility/cost analysis of breast cancer risk prediction algorithms. In Medical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment. Vol. 9787. SPIE. 2016. 97871J https://doi.org/10.1117/12.2217850
Abbey, Craig K. ; Wu, Yirong ; Burnside, Elizabeth S. ; Wunderlich, Adam ; Samuelson, Frank W. ; Boone, John M. / A utility/cost analysis of breast cancer risk prediction algorithms. Medical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment. Vol. 9787 SPIE, 2016.
@inproceedings{23163350742545bfb25d6c61222d3cfb,
title = "A utility/cost analysis of breast cancer risk prediction algorithms",
abstract = "Breast cancer risk prediction algorithms are used to identify subpopulations that are at increased risk for developing breast cancer. They can be based on many different sources of data such as demographics, relatives with cancer, gene expression, and various phenotypic features such as breast density. Women who are identified as high risk may undergo a more extensive (and expensive) screening process that includes MRI or ultrasound imaging in addition to the standard full-field digital mammography (FFDM) exam. Given that there are many ways that risk prediction may be accomplished, it is of interest to evaluate them in terms of expected cost, which includes the costs of diagnostic outcomes. In this work we perform an expected-cost analysis of risk prediction algorithms that is based on a published model that includes the costs associated with diagnostic outcomes (true-positive, false-positive, etc.). We assume the existence of a standard screening method and an enhanced screening method with higher scan cost, higher sensitivity, and lower specificity. We then assess expected cost of using a risk prediction algorithm to determine who gets the enhanced screening method under the strong assumption that risk and diagnostic performance are independent. We find that if risk prediction leads to a high enough positive predictive value, it will be cost-effective regardless of the size of the subpopulation. Furthermore, in terms of the hit-rate and false-alarm rate of the of the risk prediction algorithm, iso-cost contours are lines with slope determined by properties of the available diagnostic systems for screening.",
keywords = "Breast cancer screening, Diagnostic utility, Expected cost, Risk prediction",
author = "Abbey, {Craig K.} and Yirong Wu and Burnside, {Elizabeth S.} and Adam Wunderlich and Samuelson, {Frank W.} and Boone, {John M}",
year = "2016",
doi = "10.1117/12.2217850",
language = "English (US)",
volume = "9787",
booktitle = "Medical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment",
publisher = "SPIE",

}

TY - GEN

T1 - A utility/cost analysis of breast cancer risk prediction algorithms

AU - Abbey, Craig K.

AU - Wu, Yirong

AU - Burnside, Elizabeth S.

AU - Wunderlich, Adam

AU - Samuelson, Frank W.

AU - Boone, John M

PY - 2016

Y1 - 2016

N2 - Breast cancer risk prediction algorithms are used to identify subpopulations that are at increased risk for developing breast cancer. They can be based on many different sources of data such as demographics, relatives with cancer, gene expression, and various phenotypic features such as breast density. Women who are identified as high risk may undergo a more extensive (and expensive) screening process that includes MRI or ultrasound imaging in addition to the standard full-field digital mammography (FFDM) exam. Given that there are many ways that risk prediction may be accomplished, it is of interest to evaluate them in terms of expected cost, which includes the costs of diagnostic outcomes. In this work we perform an expected-cost analysis of risk prediction algorithms that is based on a published model that includes the costs associated with diagnostic outcomes (true-positive, false-positive, etc.). We assume the existence of a standard screening method and an enhanced screening method with higher scan cost, higher sensitivity, and lower specificity. We then assess expected cost of using a risk prediction algorithm to determine who gets the enhanced screening method under the strong assumption that risk and diagnostic performance are independent. We find that if risk prediction leads to a high enough positive predictive value, it will be cost-effective regardless of the size of the subpopulation. Furthermore, in terms of the hit-rate and false-alarm rate of the of the risk prediction algorithm, iso-cost contours are lines with slope determined by properties of the available diagnostic systems for screening.

AB - Breast cancer risk prediction algorithms are used to identify subpopulations that are at increased risk for developing breast cancer. They can be based on many different sources of data such as demographics, relatives with cancer, gene expression, and various phenotypic features such as breast density. Women who are identified as high risk may undergo a more extensive (and expensive) screening process that includes MRI or ultrasound imaging in addition to the standard full-field digital mammography (FFDM) exam. Given that there are many ways that risk prediction may be accomplished, it is of interest to evaluate them in terms of expected cost, which includes the costs of diagnostic outcomes. In this work we perform an expected-cost analysis of risk prediction algorithms that is based on a published model that includes the costs associated with diagnostic outcomes (true-positive, false-positive, etc.). We assume the existence of a standard screening method and an enhanced screening method with higher scan cost, higher sensitivity, and lower specificity. We then assess expected cost of using a risk prediction algorithm to determine who gets the enhanced screening method under the strong assumption that risk and diagnostic performance are independent. We find that if risk prediction leads to a high enough positive predictive value, it will be cost-effective regardless of the size of the subpopulation. Furthermore, in terms of the hit-rate and false-alarm rate of the of the risk prediction algorithm, iso-cost contours are lines with slope determined by properties of the available diagnostic systems for screening.

KW - Breast cancer screening

KW - Diagnostic utility

KW - Expected cost

KW - Risk prediction

UR - http://www.scopus.com/inward/record.url?scp=84976311646&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84976311646&partnerID=8YFLogxK

U2 - 10.1117/12.2217850

DO - 10.1117/12.2217850

M3 - Conference contribution

AN - SCOPUS:84976311646

VL - 9787

BT - Medical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment

PB - SPIE

ER -