Targeted validation: validating clinical prediction models in their intended population and setting
Clinical prediction models must be appropriately validated before they can be used. While validation studies are sometimes carefully designed to match an intended population/setting of the model, it is common for validation studies to take place with arbitrary datasets, chosen for convenience rather...
| Main Authors: | , , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
BioMed Central
2022
|
| _version_ | 1797112143428976640 |
|---|---|
| author | Sperrin, M Riley, RD Collins, GS Martin, GP |
| author_facet | Sperrin, M Riley, RD Collins, GS Martin, GP |
| author_sort | Sperrin, M |
| collection | OXFORD |
| description | Clinical prediction models must be appropriately validated before they can be used. While validation studies are sometimes carefully designed to match an intended population/setting of the model, it is common for validation studies to take place with arbitrary datasets, chosen for convenience rather than relevance. We call estimating how well a model performs within the intended population/setting "targeted validation". Use of this term sharpens the focus on the intended use of a model, which may increase the applicability of developed models, avoid misleading conclusions, and reduce research waste. It also exposes that external validation may not be required when the intended population for the model matches the population used to develop the model; here, a robust internal validation may be sufficient, especially if the development dataset was large. |
| first_indexed | 2024-03-07T08:20:02Z |
| format | Journal article |
| id | oxford-uuid:5565d714-58d0-4982-a8dc-3090ffde9b24 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T08:20:02Z |
| publishDate | 2022 |
| publisher | BioMed Central |
| record_format | dspace |
| spelling | oxford-uuid:5565d714-58d0-4982-a8dc-3090ffde9b242024-01-29T06:29:37ZTargeted validation: validating clinical prediction models in their intended population and settingJournal articlehttp://purl.org/coar/resource_type/c_545buuid:5565d714-58d0-4982-a8dc-3090ffde9b24EnglishSymplectic ElementsBioMed Central2022Sperrin, MRiley, RDCollins, GSMartin, GPClinical prediction models must be appropriately validated before they can be used. While validation studies are sometimes carefully designed to match an intended population/setting of the model, it is common for validation studies to take place with arbitrary datasets, chosen for convenience rather than relevance. We call estimating how well a model performs within the intended population/setting "targeted validation". Use of this term sharpens the focus on the intended use of a model, which may increase the applicability of developed models, avoid misleading conclusions, and reduce research waste. It also exposes that external validation may not be required when the intended population for the model matches the population used to develop the model; here, a robust internal validation may be sufficient, especially if the development dataset was large. |
| spellingShingle | Sperrin, M Riley, RD Collins, GS Martin, GP Targeted validation: validating clinical prediction models in their intended population and setting |
| title | Targeted validation: validating clinical prediction models in their intended population and setting |
| title_full | Targeted validation: validating clinical prediction models in their intended population and setting |
| title_fullStr | Targeted validation: validating clinical prediction models in their intended population and setting |
| title_full_unstemmed | Targeted validation: validating clinical prediction models in their intended population and setting |
| title_short | Targeted validation: validating clinical prediction models in their intended population and setting |
| title_sort | targeted validation validating clinical prediction models in their intended population and setting |
| work_keys_str_mv | AT sperrinm targetedvalidationvalidatingclinicalpredictionmodelsintheirintendedpopulationandsetting AT rileyrd targetedvalidationvalidatingclinicalpredictionmodelsintheirintendedpopulationandsetting AT collinsgs targetedvalidationvalidatingclinicalpredictionmodelsintheirintendedpopulationandsetting AT martingp targetedvalidationvalidatingclinicalpredictionmodelsintheirintendedpopulationandsetting |