The majority of 922 prediction models supporting breast cancer decision-making are at high risk of bias

Tom A. Hueting, Marissa C. van Maaren, Mathijs P. Hendriks, Hendrik Koffijberg, Sabine Siesling*

*Corresponding author for this work

Research output: Contribution to journalReview articleAcademicpeer-review

4 Citations (Scopus)
51 Downloads (Pure)


Objectives: To systematically review the currently available prediction models that may support treatment decision-making in breast cancer.

Study Design and Setting: Literature was systematically searched to identify studies reporting on development of prediction models aiming to support breast cancer treatment decision-making, published between January 2010 and December 2020. Quality and risk of bias were assessed using the Prediction model Risk Of Bias (ROB) Assessment Tool (PROBAST).

Results: After screening 20,460 studies, 534 studies were included, reporting on 922 models. The 922 models predicted: mortality (n = 417 45%), recurrence (n = 217, 24%), lymph node involvement (n = 141, 15%), adverse events (n = 58, 6%), treatment response (n = 56, 6%), or other outcomes (n = 33, 4%). In total, 285 models (31%) lacked a complete description of the final model and could not be applied to new patients. Most models (n = 878, 95%) were considered to contain high ROB.

Conclusion: A substantial overlap in predictor variables and outcomes between the models was observed. Most models were not reported according to established reporting guidelines or showed methodological flaws during the development and/or validation of the model. Further development of prediction models with thorough quality and validity assessment is an essential first step for future clinical application.
Original languageEnglish
Pages (from-to)238-247
Number of pages10
JournalJournal of clinical epidemiology
Early online date22 Nov 2022
Publication statusPublished - 1 Dec 2022


  • UT-Hybrid-D


Dive into the research topics of 'The majority of 922 prediction models supporting breast cancer decision-making are at high risk of bias'. Together they form a unique fingerprint.

Cite this