Abstract
New prognostic models are traditionally evaluated using measures of discrimination and risk reclassification, but these do not take full account of the clinical and health economic context. We propose a framework for comparing prognostic models by quantifying the public health impact (net benefit) of the treatment decisions they support, assuming a set of predetermined clinical treatment guidelines. The change in net benefit is more clinically interpretable than changes in traditional measures and can be used in full health economic evaluations of prognostic models used for screening and allocating risk reduction interventions. We extend previous work in this area by quantifying net benefits in life years, thus linking prognostic performance to health economic measures; by taking full account of the occurrence of events over time; and by considering estimation and cross-validation in a multiple-study setting. The method is illustrated in the context of cardiovascular disease risk prediction using an individual participant data meta-analysis. We estimate the number of cardiovascular-disease-free life years gained when statin treatment is allocated based on a risk prediction model with five established risk factors instead of a model with just age, gender and region. We explore methodological issues associated with the multistudy design and show that cost-effectiveness comparisons based on the proposed methodology are robust against a range of modelling assumptions, including adjusting for competing risks.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 114-130 |
| Number of pages | 17 |
| Journal | Statistics in Medicine |
| Volume | 31 |
| Issue number | 2 |
| DOIs | |
| State | Published - Jan 30 2012 |
Keywords
- Cardiovascular disease
- Competing risks
- Cost-effectiveness
- Meta-analysis
- Net benefit
- Screening strategies
Access
Other files and links
Fingerprint Dive into the research topics of 'A framework for quantifying net benefits of alternative prognostic models'. Together they form a unique fingerprint.
Cite this
- APA
- Standard
- Harvard
- Vancouver
- Author
- BIBTEX
- RIS
A framework for quantifying net benefits of alternative prognostic models. / Rapsomaniki, Eleni; White, Ian R.; Wood, Angela M.; Thompson, Simon G.; Tipping, R. W.; Ford, C. E.; Simpson, L. M.; Folsom, A. R.; Chambless, L. E.; Panagiotakos, D. B.; Pitsavos, C.; Chrysohoou, C.; Stefanadis, C.; Knuiman, M.; Whincup, P. H.; Wannamethee, S. G.; Morris, R. W.; Kiechl, S.; Willeit, J.; Oberhollenzer, F.; Mayr, A.; Wald, N.; Lawlor, D. A.; Yarnell, J. W.; Gallacher, J.; Casiglia, E.; Tikhonoff, V.; Nietert, P. J.; Sutherland, S. E.; Bachman, D. L.; Keil, J. E.; Cushman, M.; Tracy, R.; Tybjærg-Hansen, A.; Nordestgaard, B. G.; Frikke-Schmidt, R.; Giampaoli, S.; Palmieri, L.; Panico, S.; Vanuzzo, D.; Pilotto, L.; Gómez de la Cámara, A.; Gómez Gerique, J. A.; Simons, L.; McCallum, J.; Friedlander, Y.; Lee, A. J.; Taylor, J.; Guralnik, J. M.; Wallace, R.; Guralnik, J. M.; Blazer, D. G.; Guralnik, J. M.; Guralnik, J. M.; Khaw, K. T.; Schöttker, B.; Müller, H.; Rothenbacher, D.; Jansson, J. H.; Wennberg, P.; Nissinen, A.; Donfrancesco, C.; Giampaoli, S.; Salomaa, V.; Harald, K.; Jousilahti, P.; Vartiainen, E.; Woodward, M.; D'Agostino, R. B.; Wolf, P. A.; Vasan, R. S.; Pencina, M. J.; Bladbjerg, E. M.; Jørgensen, T.; Møller, L.; Jespersen, J.; Dankner, R.; Chetrit, A.; Lubin, F.; Rosengren, A.; Lappas, G.; Eriksson, H.; Björkelund, C.; Lissner, L.; Bengtsson, C.; Nagel, D.; Kiyohara, Y.; Arima, H.; Doi, Y.; Ninomiya, T.; Rodriguez, B.; Dekker, J. M.; Nijpels, G.; Stehouwer, C. D A; Iso, H.; Kitamura, A.; Yamagishi, K.; Noda, H.; Goldbourt, U.; Kauhanen, J.; Salonen, J. T.; Cooper, J. A.; Verschuren, W. M M; Blokstra, A.; Cushman, M.; Folsom, A. R.; Shea, S.; Döring, A.; Meisinger, C.; Verschuren, W. M M; Blokstra, A.; Bueno-de-Mesquita, H. B.; Rosengren, A.; Lappas, G.; Kuller, L. H.; Grandits, G.; Gillum, R. F.; Mussolino, M.; Cooper, J. A.; Bauer, K. A.; Kirkland, S.; Shaffer, J.; Korin, M. R.; Kitamura, A.; Iso, H.; Sato, S.; Amouyel, P.; Arveiler, D.; Evans, A.; Ferrières, J.; Schulte, H.; Assmann, G.; Westendorp, R. G.; Buckley, B. M.; Packard, C. J.; Sattar, N.; Cantin, B.; Després, J. P.; Dagenais, G. R.; Barrett-Connor, E.; Wingard, D. L.; Bettencourt, R.; Gudnason, V.; Aspelund, T.; Sigurdsson, G.; Thorsson, B.; Witteman, J.; Kardys, I.; Tiemeier, H.; Hofman, A.; Tunstall-Pedoe, H.; Tavendale, R.; Lowe, G. D O; Woodward, M.; Howard, B. V.; Zhang, Y.; Best, L.; Umans, J.; Ben-Shlomo, Y.; Davey-Smith, G.; Njølstad, I.; Wilsgaard, T.; Ingelsson, E.; Lind, L.; Giedraitis, V.; Lannfelt, L.; Gaziano, J. M.; Stampfer, M.; Ridker, P.; Gaziano, J. M.; Ridker, P.; Wassertheil-Smoller, S.; Manson, J. E.; Marmot, M.; Clarke, R.; Fletcher, A.; Brunner, E.; Shipley, M.; Ridker, P.; Buring, J.; Shepherd, J.; Cobbe, S. M.; Ford, I.; Robertson, M.; Marín Ibañez, A.; Feskens, E. J M; Kromhout, D.
In: Statistics in Medicine, Vol. 31, No. 2, 30.01.2012, p. 114-130.Research output: Contribution to journal › Article › peer-review
}
TY - JOUR
T1 - A framework for quantifying net benefits of alternative prognostic models
AU - Rapsomaniki, Eleni
AU - White, Ian R.
AU - Wood, Angela M.
AU - Thompson, Simon G.
AU - Tipping, R. W.
AU - Ford, C. E.
AU - Simpson, L. M.
AU - Folsom, A. R.
AU - Chambless, L. E.
AU - Panagiotakos, D. B.
AU - Pitsavos, C.
AU - Chrysohoou, C.
AU - Stefanadis, C.
AU - Knuiman, M.
AU - Whincup, P. H.
AU - Wannamethee, S. G.
AU - Morris, R. W.
AU - Kiechl, S.
AU - Willeit, J.
AU - Oberhollenzer, F.
AU - Mayr, A.
AU - Wald, N.
AU - Lawlor, D. A.
AU - Yarnell, J. W.
AU - Gallacher, J.
AU - Casiglia, E.
AU - Tikhonoff, V.
AU - Nietert, P. J.
AU - Sutherland, S. E.
AU - Bachman, D. L.
AU - Keil, J. E.
AU - Cushman, M.
AU - Tracy, R.
AU - Tybjærg-Hansen, A.
AU - Nordestgaard, B. G.
AU - Frikke-Schmidt, R.
AU - Giampaoli, S.
AU - Palmieri, L.
AU - Panico, S.
AU - Vanuzzo, D.
AU - Pilotto, L.
AU - Gómez de la Cámara, A.
AU - Gómez Gerique, J. A.
AU - Simons, L.
AU - McCallum, J.
AU - Friedlander, Y.
AU - Lee, A. J.
AU - Taylor, J.
AU - Guralnik, J. M.
AU - Wallace, R.
AU - Guralnik, J. M.
AU - Blazer, D. G.
AU - Guralnik, J. M.
AU - Guralnik, J. M.
AU - Khaw, K. T.
AU - Schöttker, B.
AU - Müller, H.
AU - Rothenbacher, D.
AU - Jansson, J. H.
AU - Wennberg, P.
AU - Nissinen, A.
AU - Donfrancesco, C.
AU - Giampaoli, S.
AU - Salomaa, V.
AU - Harald, K.
AU - Jousilahti, P.
AU - Vartiainen, E.
AU - Woodward, M.
AU - D'Agostino, R. B.
AU - Wolf, P. A.
AU - Vasan, R. S.
AU - Pencina, M. J.
AU - Bladbjerg, E. M.
AU - Jørgensen, T.
AU - Møller, L.
AU - Jespersen, J.
AU - Dankner, R.
AU - Chetrit, A.
AU - Lubin, F.
AU - Rosengren, A.
AU - Lappas, G.
AU - Eriksson, H.
AU - Björkelund, C.
AU - Lissner, L.
AU - Bengtsson, C.
AU - Nagel, D.
AU - Kiyohara, Y.
AU - Arima, H.
AU - Doi, Y.
AU - Ninomiya, T.
AU - Rodriguez, B.
AU - Dekker, J. M.
AU - Nijpels, G.
AU - Stehouwer, C. D A
AU - Iso, H.
AU - Kitamura, A.
AU - Yamagishi, K.
AU - Noda, H.
AU - Goldbourt, U.
AU - Kauhanen, J.
AU - Salonen, J. T.
AU - Cooper, J. A.
AU - Verschuren, W. M M
AU - Blokstra, A.
AU - Cushman, M.
AU - Folsom, A. R.
AU - Shea, S.
AU - Döring, A.
AU - Meisinger, C.
AU - Verschuren, W. M M
AU - Blokstra, A.
AU - Bueno-de-Mesquita, H. B.
AU - Rosengren, A.
AU - Lappas, G.
AU - Kuller, L. H.
AU - Grandits, G.
AU - Gillum, R. F.
AU - Mussolino, M.
AU - Cooper, J. A.
AU - Bauer, K. A.
AU - Kirkland, S.
AU - Shaffer, J.
AU - Korin, M. R.
AU - Kitamura, A.
AU - Iso, H.
AU - Sato, S.
AU - Amouyel, P.
AU - Arveiler, D.
AU - Evans, A.
AU - Ferrières, J.
AU - Schulte, H.
AU - Assmann, G.
AU - Westendorp, R. G.
AU - Buckley, B. M.
AU - Packard, C. J.
AU - Sattar, N.
AU - Cantin, B.
AU - Després, J. P.
AU - Dagenais, G. R.
AU - Barrett-Connor, E.
AU - Wingard, D. L.
AU - Bettencourt, R.
AU - Gudnason, V.
AU - Aspelund, T.
AU - Sigurdsson, G.
AU - Thorsson, B.
AU - Witteman, J.
AU - Kardys, I.
AU - Tiemeier, H.
AU - Hofman, A.
AU - Tunstall-Pedoe, H.
AU - Tavendale, R.
AU - Lowe, G. D O
AU - Woodward, M.
AU - Howard, B. V.
AU - Zhang, Y.
AU - Best, L.
AU - Umans, J.
AU - Ben-Shlomo, Y.
AU - Davey-Smith, G.
AU - Njølstad, I.
AU - Wilsgaard, T.
AU - Ingelsson, E.
AU - Lind, L.
AU - Giedraitis, V.
AU - Lannfelt, L.
AU - Gaziano, J. M.
AU - Stampfer, M.
AU - Ridker, P.
AU - Gaziano, J. M.
AU - Ridker, P.
AU - Wassertheil-Smoller, S.
AU - Manson, J. E.
AU - Marmot, M.
AU - Clarke, R.
AU - Fletcher, A.
AU - Brunner, E.
AU - Shipley, M.
AU - Ridker, P.
AU - Buring, J.
AU - Shepherd, J.
AU - Cobbe, S. M.
AU - Ford, I.
AU - Robertson, M.
AU - Marín Ibañez, A.
AU - Feskens, E. J M
AU - Kromhout, D.
N1 - Copyright: Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2012/1/30
Y1 - 2012/1/30
N2 - New prognostic models are traditionally evaluated using measures of discrimination and risk reclassification, but these do not take full account of the clinical and health economic context. We propose a framework for comparing prognostic models by quantifying the public health impact (net benefit) of the treatment decisions they support, assuming a set of predetermined clinical treatment guidelines. The change in net benefit is more clinically interpretable than changes in traditional measures and can be used in full health economic evaluations of prognostic models used for screening and allocating risk reduction interventions. We extend previous work in this area by quantifying net benefits in life years, thus linking prognostic performance to health economic measures; by taking full account of the occurrence of events over time; and by considering estimation and cross-validation in a multiple-study setting. The method is illustrated in the context of cardiovascular disease risk prediction using an individual participant data meta-analysis. We estimate the number of cardiovascular-disease-free life years gained when statin treatment is allocated based on a risk prediction model with five established risk factors instead of a model with just age, gender and region. We explore methodological issues associated with the multistudy design and show that cost-effectiveness comparisons based on the proposed methodology are robust against a range of modelling assumptions, including adjusting for competing risks.
AB - New prognostic models are traditionally evaluated using measures of discrimination and risk reclassification, but these do not take full account of the clinical and health economic context. We propose a framework for comparing prognostic models by quantifying the public health impact (net benefit) of the treatment decisions they support, assuming a set of predetermined clinical treatment guidelines. The change in net benefit is more clinically interpretable than changes in traditional measures and can be used in full health economic evaluations of prognostic models used for screening and allocating risk reduction interventions. We extend previous work in this area by quantifying net benefits in life years, thus linking prognostic performance to health economic measures; by taking full account of the occurrence of events over time; and by considering estimation and cross-validation in a multiple-study setting. The method is illustrated in the context of cardiovascular disease risk prediction using an individual participant data meta-analysis. We estimate the number of cardiovascular-disease-free life years gained when statin treatment is allocated based on a risk prediction model with five established risk factors instead of a model with just age, gender and region. We explore methodological issues associated with the multistudy design and show that cost-effectiveness comparisons based on the proposed methodology are robust against a range of modelling assumptions, including adjusting for competing risks.
KW - Cardiovascular disease
KW - Competing risks
KW - Cost-effectiveness
KW - Meta-analysis
KW - Net benefit
KW - Screening strategies
UR - http://www.scopus.com/inward/record.url?scp=84855240264&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84855240264&partnerID=8YFLogxK
U2 - 10.1002/sim.4362
DO - 10.1002/sim.4362
M3 - Article
C2 - 21905066
AN - SCOPUS:84855240264
VL - 31
SP - 114
EP - 130
JO - Statistics in Medicine
JF - Statistics in Medicine
SN - 0277-6715
IS - 2
ER -