Explicit inclusion of treatment in prognostic modelling was recommended in observational and randomised settings
<p xmlns:etd="http://www.ouls.ox.ac.uk/ora/modsextensions">Objectives: To compare different methods to handle treatment when developing a prognostic model that aims to produce accurate probabilities of the outcome of individuals if left untreated.</p> <p xmlns:etd="http...
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Journal article |
| Pubblicazione: |
Elsevier
2016
|
| _version_ | 1826277150114709504 |
|---|---|
| author | Groenwold, R Moons, K Pajouheshnia, R Altman, D Collins, G Debray, T Reitsma, J Riley, R Peelen, L |
| author_facet | Groenwold, R Moons, K Pajouheshnia, R Altman, D Collins, G Debray, T Reitsma, J Riley, R Peelen, L |
| author_sort | Groenwold, R |
| collection | OXFORD |
| description | <p xmlns:etd="http://www.ouls.ox.ac.uk/ora/modsextensions">Objectives: To compare different methods to handle treatment when developing a prognostic model that aims to produce accurate probabilities of the outcome of individuals if left untreated.</p> <p xmlns:etd="http://www.ouls.ox.ac.uk/ora/modsextensions">Study Design and Setting: Simulations were performed based on two normally distributed predictors, a binary outcome, and a binary treatment, mimicking a randomized trial or an observational study. Comparison was made between simply ignoring treatment (SIT), restricting the analytical data set to untreated individuals (AUT), inverse probability weighting (IPW), and explicit modeling of treatment (MT). Methods were compared in terms of predictive performance of the model and the proportion of incorrect treatment decisions.</p> <p xmlns:etd="http://www.ouls.ox.ac.uk/ora/modsextensions">Results: Omitting a genuine predictor of the outcome from the prognostic model decreased model performance, in both an observational study and a randomized trial. In randomized trials, the proportion of incorrect treatment decisions was smaller when applying AUT or MT, compared to SIT and IPW. In observational studies, MT was superior to all other methods regarding the proportion of incorrect treatment decisions.</p> <p xmlns:etd="http://www.ouls.ox.ac.uk/ora/modsextensions">Conclusion: If a prognostic model aims to produce correct probabilities of the outcome in the absence of treatment, ignoring treatments that affect that outcome can lead to suboptimal model performance and incorrect treatment decisions. Explicitly, modeling treatment is recommended.</p> |
| first_indexed | 2024-03-06T23:24:34Z |
| format | Journal article |
| id | oxford-uuid:69ea7aad-d500-4d7e-bf06-f82cccbedd45 |
| institution | University of Oxford |
| last_indexed | 2024-03-06T23:24:34Z |
| publishDate | 2016 |
| publisher | Elsevier |
| record_format | dspace |
| spelling | oxford-uuid:69ea7aad-d500-4d7e-bf06-f82cccbedd452022-03-26T18:54:09ZExplicit inclusion of treatment in prognostic modelling was recommended in observational and randomised settingsJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:69ea7aad-d500-4d7e-bf06-f82cccbedd45Symplectic Elements at OxfordElsevier2016Groenwold, RMoons, KPajouheshnia, RAltman, DCollins, GDebray, TReitsma, JRiley, RPeelen, L<p xmlns:etd="http://www.ouls.ox.ac.uk/ora/modsextensions">Objectives: To compare different methods to handle treatment when developing a prognostic model that aims to produce accurate probabilities of the outcome of individuals if left untreated.</p> <p xmlns:etd="http://www.ouls.ox.ac.uk/ora/modsextensions">Study Design and Setting: Simulations were performed based on two normally distributed predictors, a binary outcome, and a binary treatment, mimicking a randomized trial or an observational study. Comparison was made between simply ignoring treatment (SIT), restricting the analytical data set to untreated individuals (AUT), inverse probability weighting (IPW), and explicit modeling of treatment (MT). Methods were compared in terms of predictive performance of the model and the proportion of incorrect treatment decisions.</p> <p xmlns:etd="http://www.ouls.ox.ac.uk/ora/modsextensions">Results: Omitting a genuine predictor of the outcome from the prognostic model decreased model performance, in both an observational study and a randomized trial. In randomized trials, the proportion of incorrect treatment decisions was smaller when applying AUT or MT, compared to SIT and IPW. In observational studies, MT was superior to all other methods regarding the proportion of incorrect treatment decisions.</p> <p xmlns:etd="http://www.ouls.ox.ac.uk/ora/modsextensions">Conclusion: If a prognostic model aims to produce correct probabilities of the outcome in the absence of treatment, ignoring treatments that affect that outcome can lead to suboptimal model performance and incorrect treatment decisions. Explicitly, modeling treatment is recommended.</p> |
| spellingShingle | Groenwold, R Moons, K Pajouheshnia, R Altman, D Collins, G Debray, T Reitsma, J Riley, R Peelen, L Explicit inclusion of treatment in prognostic modelling was recommended in observational and randomised settings |
| title | Explicit inclusion of treatment in prognostic modelling was recommended in observational and randomised settings |
| title_full | Explicit inclusion of treatment in prognostic modelling was recommended in observational and randomised settings |
| title_fullStr | Explicit inclusion of treatment in prognostic modelling was recommended in observational and randomised settings |
| title_full_unstemmed | Explicit inclusion of treatment in prognostic modelling was recommended in observational and randomised settings |
| title_short | Explicit inclusion of treatment in prognostic modelling was recommended in observational and randomised settings |
| title_sort | explicit inclusion of treatment in prognostic modelling was recommended in observational and randomised settings |
| work_keys_str_mv | AT groenwoldr explicitinclusionoftreatmentinprognosticmodellingwasrecommendedinobservationalandrandomisedsettings AT moonsk explicitinclusionoftreatmentinprognosticmodellingwasrecommendedinobservationalandrandomisedsettings AT pajouheshniar explicitinclusionoftreatmentinprognosticmodellingwasrecommendedinobservationalandrandomisedsettings AT altmand explicitinclusionoftreatmentinprognosticmodellingwasrecommendedinobservationalandrandomisedsettings AT collinsg explicitinclusionoftreatmentinprognosticmodellingwasrecommendedinobservationalandrandomisedsettings AT debrayt explicitinclusionoftreatmentinprognosticmodellingwasrecommendedinobservationalandrandomisedsettings AT reitsmaj explicitinclusionoftreatmentinprognosticmodellingwasrecommendedinobservationalandrandomisedsettings AT rileyr explicitinclusionoftreatmentinprognosticmodellingwasrecommendedinobservationalandrandomisedsettings AT peelenl explicitinclusionoftreatmentinprognosticmodellingwasrecommendedinobservationalandrandomisedsettings |