Facilitating validation of prediction models: a comparison of manual and semi-automated validation using registry-based data of breast cancer patients in the Netherlands
Abstract Background Clinical prediction models are not routinely validated. To facilitate validation procedures, the online Evidencio platform (https://www.evidencio.com) has developed a tool partly automating this process. This study aims to determine whether semi-automated validation can reliably...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2019-06-01
|
| Series: | BMC Medical Research Methodology |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s12874-019-0761-5 |
| _version_ | 1828376518067224576 |
|---|---|
| author | Cornelia D. van Steenbeek Marissa C. van Maaren Sabine Siesling Annemieke Witteveen Xander A. A. M. Verbeek Hendrik Koffijberg |
| author_facet | Cornelia D. van Steenbeek Marissa C. van Maaren Sabine Siesling Annemieke Witteveen Xander A. A. M. Verbeek Hendrik Koffijberg |
| author_sort | Cornelia D. van Steenbeek |
| collection | DOAJ |
| description | Abstract Background Clinical prediction models are not routinely validated. To facilitate validation procedures, the online Evidencio platform (https://www.evidencio.com) has developed a tool partly automating this process. This study aims to determine whether semi-automated validation can reliably substitute manual validation. Methods Four different models used in breast cancer care were selected: CancerMath, INFLUENCE, Predicted Probability of Axillary Metastasis, and PREDICT v.2.0. Data were obtained from the Netherlands Cancer Registry according to the inclusion criteria of the original development population. Calibration (intercepts and slopes) and discrimination (area under the curve (AUC)) were compared between semi-automated and manual validation. Results Differences between intercepts and slopes of all models using semi-automated validation ranged from 0 to 0.03 from manual validation, which was not clinically relevant. AUCs were identical for both validation methods. Conclusions This easy to use semi-automated validation option is a good substitute for manual validation and might increase the number of validations of prediction models used in clinical practice. In addition, the validation tool was considered to be user-friendly and to save a lot of time compared to manual validation. Semi-automated validation will contribute to more accurate outcome predictions and treatment recommendations in the target population. |
| first_indexed | 2024-04-14T08:02:08Z |
| format | Article |
| id | doaj.art-7b7151a8c5224b7caa7fb0e3007c595b |
| institution | Directory Open Access Journal |
| issn | 1471-2288 |
| language | English |
| last_indexed | 2024-04-14T08:02:08Z |
| publishDate | 2019-06-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Research Methodology |
| spelling | doaj.art-7b7151a8c5224b7caa7fb0e3007c595b2022-12-22T02:04:52ZengBMCBMC Medical Research Methodology1471-22882019-06-011911810.1186/s12874-019-0761-5Facilitating validation of prediction models: a comparison of manual and semi-automated validation using registry-based data of breast cancer patients in the NetherlandsCornelia D. van Steenbeek0Marissa C. van Maaren1Sabine Siesling2Annemieke Witteveen3Xander A. A. M. Verbeek4Hendrik Koffijberg5Department of Research, Netherlands Comprehensive Cancer OrganisationDepartment of Research, Netherlands Comprehensive Cancer OrganisationDepartment of Research, Netherlands Comprehensive Cancer OrganisationDepartment of Research, Netherlands Comprehensive Cancer OrganisationDepartment of Research, Netherlands Comprehensive Cancer OrganisationDepartment of Health Technology & Services Research, MIRA Institute for Biomedical Technology and Technical Medicine, University of TwenteAbstract Background Clinical prediction models are not routinely validated. To facilitate validation procedures, the online Evidencio platform (https://www.evidencio.com) has developed a tool partly automating this process. This study aims to determine whether semi-automated validation can reliably substitute manual validation. Methods Four different models used in breast cancer care were selected: CancerMath, INFLUENCE, Predicted Probability of Axillary Metastasis, and PREDICT v.2.0. Data were obtained from the Netherlands Cancer Registry according to the inclusion criteria of the original development population. Calibration (intercepts and slopes) and discrimination (area under the curve (AUC)) were compared between semi-automated and manual validation. Results Differences between intercepts and slopes of all models using semi-automated validation ranged from 0 to 0.03 from manual validation, which was not clinically relevant. AUCs were identical for both validation methods. Conclusions This easy to use semi-automated validation option is a good substitute for manual validation and might increase the number of validations of prediction models used in clinical practice. In addition, the validation tool was considered to be user-friendly and to save a lot of time compared to manual validation. Semi-automated validation will contribute to more accurate outcome predictions and treatment recommendations in the target population.http://link.springer.com/article/10.1186/s12874-019-0761-5Prediction modelsExternal validationSemi-automatedBreast cancer |
| spellingShingle | Cornelia D. van Steenbeek Marissa C. van Maaren Sabine Siesling Annemieke Witteveen Xander A. A. M. Verbeek Hendrik Koffijberg Facilitating validation of prediction models: a comparison of manual and semi-automated validation using registry-based data of breast cancer patients in the Netherlands BMC Medical Research Methodology Prediction models External validation Semi-automated Breast cancer |
| title | Facilitating validation of prediction models: a comparison of manual and semi-automated validation using registry-based data of breast cancer patients in the Netherlands |
| title_full | Facilitating validation of prediction models: a comparison of manual and semi-automated validation using registry-based data of breast cancer patients in the Netherlands |
| title_fullStr | Facilitating validation of prediction models: a comparison of manual and semi-automated validation using registry-based data of breast cancer patients in the Netherlands |
| title_full_unstemmed | Facilitating validation of prediction models: a comparison of manual and semi-automated validation using registry-based data of breast cancer patients in the Netherlands |
| title_short | Facilitating validation of prediction models: a comparison of manual and semi-automated validation using registry-based data of breast cancer patients in the Netherlands |
| title_sort | facilitating validation of prediction models a comparison of manual and semi automated validation using registry based data of breast cancer patients in the netherlands |
| topic | Prediction models External validation Semi-automated Breast cancer |
| url | http://link.springer.com/article/10.1186/s12874-019-0761-5 |
| work_keys_str_mv | AT corneliadvansteenbeek facilitatingvalidationofpredictionmodelsacomparisonofmanualandsemiautomatedvalidationusingregistrybaseddataofbreastcancerpatientsinthenetherlands AT marissacvanmaaren facilitatingvalidationofpredictionmodelsacomparisonofmanualandsemiautomatedvalidationusingregistrybaseddataofbreastcancerpatientsinthenetherlands AT sabinesiesling facilitatingvalidationofpredictionmodelsacomparisonofmanualandsemiautomatedvalidationusingregistrybaseddataofbreastcancerpatientsinthenetherlands AT annemiekewitteveen facilitatingvalidationofpredictionmodelsacomparisonofmanualandsemiautomatedvalidationusingregistrybaseddataofbreastcancerpatientsinthenetherlands AT xanderaamverbeek facilitatingvalidationofpredictionmodelsacomparisonofmanualandsemiautomatedvalidationusingregistrybaseddataofbreastcancerpatientsinthenetherlands AT hendrikkoffijberg facilitatingvalidationofpredictionmodelsacomparisonofmanualandsemiautomatedvalidationusingregistrybaseddataofbreastcancerpatientsinthenetherlands |