Improving patient prostate cancer risk assessment

Moving from static, globally-applied to dynamic, practice-specific risk calculators

Andreas N. Strobl, Andrew J. Vickers, Ben Van Calster, Ewout Steyerberg, Robin J Leach, Ian M. Thompson, Donna P Ankerst

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Clinical risk calculators are now widely available but have generally been implemented in a static and one-size-fits-all fashion. The objective of this study was to challenge these notions and show via a case study concerning risk-based screening for prostate cancer how calculators can be dynamically and locally tailored to improve on-site patient accuracy. Yearly data from five international prostate biopsy cohorts (3 in the US, 1 in Austria, 1 in England) were used to compare 6 methods for annual risk prediction: static use of the online US-developed Prostate Cancer Prevention Trial Risk Calculator (PCPTRC); recalibration of the PCPTRC; revision of the PCPTRC; building a new model each year using logistic regression, Bayesian prior-to-posterior updating, or random forests. All methods performed similarly with respect to discrimination, except for random forests, which were worse. All methods except for random forests greatly improved calibration over the static PCPTRC in all cohorts except for Austria, where the PCPTRC had the best calibration followed closely by recalibration. The case study shows that a simple annual recalibration of a general online risk tool for prostate cancer can improve its accuracy with respect to the local patient practice at hand.

Original languageEnglish (US)
Pages (from-to)87-93
Number of pages7
JournalJournal of Biomedical Informatics
Volume56
DOIs
StatePublished - Aug 1 2015

Fingerprint

Risk assessment
Prostatic Neoplasms
Austria
Calibration
Biopsy
England
Logistics
Prostate
Screening
Hand
Logistic Models
Forests

Keywords

  • Calibration
  • Discrimination
  • Logistic regression
  • Prediction
  • Prostate cancer
  • Revision

ASJC Scopus subject areas

  • Computer Science Applications
  • Health Informatics

Cite this

Improving patient prostate cancer risk assessment : Moving from static, globally-applied to dynamic, practice-specific risk calculators. / Strobl, Andreas N.; Vickers, Andrew J.; Van Calster, Ben; Steyerberg, Ewout; Leach, Robin J; Thompson, Ian M.; Ankerst, Donna P.

In: Journal of Biomedical Informatics, Vol. 56, 01.08.2015, p. 87-93.

Research output: Contribution to journalArticle

Strobl, Andreas N. ; Vickers, Andrew J. ; Van Calster, Ben ; Steyerberg, Ewout ; Leach, Robin J ; Thompson, Ian M. ; Ankerst, Donna P. / Improving patient prostate cancer risk assessment : Moving from static, globally-applied to dynamic, practice-specific risk calculators. In: Journal of Biomedical Informatics. 2015 ; Vol. 56. pp. 87-93.
@article{baa1c793eb8a415ca8c696a45c05b0b7,
title = "Improving patient prostate cancer risk assessment: Moving from static, globally-applied to dynamic, practice-specific risk calculators",
abstract = "Clinical risk calculators are now widely available but have generally been implemented in a static and one-size-fits-all fashion. The objective of this study was to challenge these notions and show via a case study concerning risk-based screening for prostate cancer how calculators can be dynamically and locally tailored to improve on-site patient accuracy. Yearly data from five international prostate biopsy cohorts (3 in the US, 1 in Austria, 1 in England) were used to compare 6 methods for annual risk prediction: static use of the online US-developed Prostate Cancer Prevention Trial Risk Calculator (PCPTRC); recalibration of the PCPTRC; revision of the PCPTRC; building a new model each year using logistic regression, Bayesian prior-to-posterior updating, or random forests. All methods performed similarly with respect to discrimination, except for random forests, which were worse. All methods except for random forests greatly improved calibration over the static PCPTRC in all cohorts except for Austria, where the PCPTRC had the best calibration followed closely by recalibration. The case study shows that a simple annual recalibration of a general online risk tool for prostate cancer can improve its accuracy with respect to the local patient practice at hand.",
keywords = "Calibration, Discrimination, Logistic regression, Prediction, Prostate cancer, Revision",
author = "Strobl, {Andreas N.} and Vickers, {Andrew J.} and {Van Calster}, Ben and Ewout Steyerberg and Leach, {Robin J} and Thompson, {Ian M.} and Ankerst, {Donna P}",
year = "2015",
month = "8",
day = "1",
doi = "10.1016/j.jbi.2015.05.001",
language = "English (US)",
volume = "56",
pages = "87--93",
journal = "Journal of Biomedical Informatics",
issn = "1532-0464",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Improving patient prostate cancer risk assessment

T2 - Moving from static, globally-applied to dynamic, practice-specific risk calculators

AU - Strobl, Andreas N.

AU - Vickers, Andrew J.

AU - Van Calster, Ben

AU - Steyerberg, Ewout

AU - Leach, Robin J

AU - Thompson, Ian M.

AU - Ankerst, Donna P

PY - 2015/8/1

Y1 - 2015/8/1

N2 - Clinical risk calculators are now widely available but have generally been implemented in a static and one-size-fits-all fashion. The objective of this study was to challenge these notions and show via a case study concerning risk-based screening for prostate cancer how calculators can be dynamically and locally tailored to improve on-site patient accuracy. Yearly data from five international prostate biopsy cohorts (3 in the US, 1 in Austria, 1 in England) were used to compare 6 methods for annual risk prediction: static use of the online US-developed Prostate Cancer Prevention Trial Risk Calculator (PCPTRC); recalibration of the PCPTRC; revision of the PCPTRC; building a new model each year using logistic regression, Bayesian prior-to-posterior updating, or random forests. All methods performed similarly with respect to discrimination, except for random forests, which were worse. All methods except for random forests greatly improved calibration over the static PCPTRC in all cohorts except for Austria, where the PCPTRC had the best calibration followed closely by recalibration. The case study shows that a simple annual recalibration of a general online risk tool for prostate cancer can improve its accuracy with respect to the local patient practice at hand.

AB - Clinical risk calculators are now widely available but have generally been implemented in a static and one-size-fits-all fashion. The objective of this study was to challenge these notions and show via a case study concerning risk-based screening for prostate cancer how calculators can be dynamically and locally tailored to improve on-site patient accuracy. Yearly data from five international prostate biopsy cohorts (3 in the US, 1 in Austria, 1 in England) were used to compare 6 methods for annual risk prediction: static use of the online US-developed Prostate Cancer Prevention Trial Risk Calculator (PCPTRC); recalibration of the PCPTRC; revision of the PCPTRC; building a new model each year using logistic regression, Bayesian prior-to-posterior updating, or random forests. All methods performed similarly with respect to discrimination, except for random forests, which were worse. All methods except for random forests greatly improved calibration over the static PCPTRC in all cohorts except for Austria, where the PCPTRC had the best calibration followed closely by recalibration. The case study shows that a simple annual recalibration of a general online risk tool for prostate cancer can improve its accuracy with respect to the local patient practice at hand.

KW - Calibration

KW - Discrimination

KW - Logistic regression

KW - Prediction

KW - Prostate cancer

KW - Revision

UR - http://www.scopus.com/inward/record.url?scp=84938573721&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84938573721&partnerID=8YFLogxK

U2 - 10.1016/j.jbi.2015.05.001

DO - 10.1016/j.jbi.2015.05.001

M3 - Article

VL - 56

SP - 87

EP - 93

JO - Journal of Biomedical Informatics

JF - Journal of Biomedical Informatics

SN - 1532-0464

ER -