Abstract
BackgroundPREDICT is a widely used online prognostication and treatment benefit tool for patients with early stage breast cancer. The aim of this study was to conduct an independent validation exercise of the most up-to-date version of the PREDICT algorithm (version 2) using real-world outcomes from the Scottish population of women with breast cancer.MethodsPatient data were obtained for all Scottish Cancer Registry (SCR) records with a diagnosis of primary invasive breast cancer diagnosed in the period between January 2001 and December 2015. Prognostic scores were calculated using the PREDICT version 2 algorithm. External validity was assessed by statistical analysis of discrimination and calibration. Discrimination was assessed by area under the receiver-operator curve (AUC). Calibration was assessed by comparing the predicted number of deaths to the observed number of deaths across relevant sub-groups.ResultsA total of 45,789 eligible cases were selected from 61,437 individual records. AUC statistics ranged from 0.74 to 0.77. Calibration results showed relatively close agreement between predicted and observed deaths. The 5-year complete follow-up sample reported some overestimation (11.5%), while the 10-year complete follow-up sample displayed more limited overestimation (1.7%).ConclusionsValidation results suggest that the PREDICT tool remains essentially relevant for contemporary patients with early stage breast cancer.
Highlights
PREDICT is a widely used online prognostication and treatment benefit tool for patients with early stage breast cancer
In relation to breast cancerspecific mortality (Table S12-S14) there was underestimation of 12% in the first cohort and overestimation of 14.9% and 22.4% in the second and third cohorts. In this validation exercise of the PREDICT prognostication tool using an external dataset good performance was demonstrated with regards to both discrimination and calibration, comparable to that reported in the derivation and previous validation data
The large sample size drawn from the population-based Scottish Cancer Registry (SCR), which is eight times the previous validation samples combined, improves the precision of the results considerably and allows an assessment of the generalisability of the model to the full population in whom it may be applied
Summary
PREDICT is a widely used online prognostication and treatment benefit tool for patients with early stage breast cancer. The algorithm behind the online tool was derived primarily from data obtained from the Eastern Cancer Registration and Information Centre (ECRIC) registry in the United Kingdom (east of England).Treatment effectiveness estimates are taken from the Early Breast Cancer Trialists’ Collaborative Group (EBCTCG) metaanalyses of clinical trials.[3] The first online version of the tool was published in 20101 (v1). The most recent update, in 2017, refined the model by including age at diagnosis in the breast cancer-specific death prediction as well as recoding tumour size and nodal status variables (v2).[2] The aim of our study is to conduct an independent validation exercise of the most up-to-date version of the PREDICT algorithm available (v2) using real-world outcomes from the Scottish population of women with breast cancer
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
