PREDICT breast v4.0: An update to the PREDICT breast prognostic model

PREDICT breast v4.0: An update to the PREDICT breast prognostic model | medRxiv /* */ /* */ <!-- <!-- /*! * yepnope1.5.4 * (c) WTFPL, GPLv2 */ (function(a,b,c){function d(a){return"[object Function]"==o.call(a)}function e(a){return"string"==typeof a}function f(){}function g(a){return!a||"loaded"==a||"complete"==a||"uninitialized"==a}function h(){var a=p.shift();q=1,a?a.t?m(function(){("c"==a.t?B.injectCss:B.injectJs)(a.s,0,a.a,a.x,a.e,1)},0):(a(),h()):q=0}function i(a,c,d,e,f,i,j){function k(b){if(!o&&g(l.readyState)&&(u.r=o=1,!q&&h(),l.onload=l.onreadystatechange=null,b)){"img"!=a&&m(function(){t.removeChild(l)},50);for(var d in y[c])y[c].hasOwnProperty(d)&&y[c][d].onload()}}var j=j||B.errorTimeout,l=b.createElement(a),o=0,r=0,u={t:d,s:c,e:f,a:i,x:j};1===y[c]&&(r=1,y[c]=[]),"object"==a?l.data=c:(l.src=c,l.type=a),l.width=l.height="0",l.onerror=l.onload=l.onreadystatechange=function(){k.call(this,r)},p.splice(e,0,u),"img"!=a&&(r||2===y[c]?(t.insertBefore(l,s?null:n),m(k,j)):y[c].push(l))}function j(a,b,c,d,f){return q=0,b=b||"j",e(a)?i("c"==b?v:u,a,b,this.i++,c,d,f):(p.splice(this.i++,0,a),1==p.length&&h()),this}function k(){var a=B;return a.loader={load:j,i:0},a}var l=b.documentElement,m=a.setTimeout,n=b.getElementsByTagName("script")[0],o={}.toString,p=[],q=0,r="MozAppearance"in l.style,s=r&&!!b.createRange().compareNode,t=s?l:n.parentNode,l=a.opera&&"[object Opera]"==o.call(a.opera),l=!!b.attachEvent&&!l,u=r?"object":l?"script":"img",v=l?"script":u,w=Array.isArray||function(a){return"[object Array]"==o.call(a)},x=[],y={},z={timeout:function(a,b){return b.length&&(a.timeout=b[0]),a}},A,B;B=function(a){function b(a){var a=a.split("!"),b=x.length,c=a.pop(),d=a.length,c={url:c,origUrl:c,prefixes:a},e,f,g;for(f=0;f<d;f++)g=a[f].split("="),(e=z[g.shift()])&&(c=e(c,g));for(f=0;f<b;f++)c=x[f](c);return c}function g(a,e,f,g,h){var i=b(a),j=i.autoCallback;i.url.split(".").pop().split("?").shift(),i.bypass||(e&&(e=d(e)?e:e[a]||e[g]||e[a.split("/").pop().split("?")[0]]),i.instead?i.instead(a,e,f,g,h):(y[i.url]?i.noexec=!0:y[i.url]=1,f.load(i.url,i.forceCSS||!i.forceJS&&"css"==i.url.split(".").pop().split("?").shift()?"c":c,i.noexec,i.attrs,i.timeout),(d(e)||d(j))&&f.load(function(){k(),e&&e(i.origUrl,h,g),j&&j(i.origUrl,h,g),y[i.url]=2})))}function h(a,b){function c(a,c){if(a){if(e(a))c||(j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}),g(a,j,b,0,h);else if(Object(a)===a)for(n in m=function(){var b=0,c;for(c in a)a.hasOwnProperty(c)&&b++;return b}(),a)a.hasOwnProperty(n)&&(!c&&!--m&&(d(j)?j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}:j[n]=function(a){return function(){var b=[].slice.call(arguments);a&&a.apply(this,b),l()}}(k[n])),g(a[n],j,b,n,h))}else!c&&l()}var h=!!a.test,i=a.load||a.both,j=a.callback||f,k=j,l=a.complete||f,m,n;c(h?a.yep:a.nope,!!i),i&&c(i)}var i,j,l=this.yepnope.loader;if(e(a))g(a,0,l,0);else if(w(a))for(i=0;i (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0];var j=d.createElement(s);var dl=l!='dataLayer'?'&l='+l:'';j.src='//www.googletagmanager.com/gtm.js?id='+i+dl;j.type='text/javascript';j.async=true;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-P4HH5NV'); Skip to main content Home About Submit ALERTS / RSS Search for this keyword Advanced Search PREDICT breast v4.0: An update to the PREDICT breast prognostic model View ORCID Profile Paul D.P. Pharoah , Yi-Wen Hsiao , View ORCID Profile Gordon C. Wishart , View ORCID Profile Pei-Chen Peng doi: https://doi.org/10.1101/2025.08.28.25334663 Paul D.P. Pharoah 1 Department of Computational Biomedicine, Cedars-Sinai Medical Center , Los Angeles, CA Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Paul D.P. Pharoah For correspondence: paul.pharoah{at}cshs.org Yi-Wen Hsiao 1 Department of Computational Biomedicine, Cedars-Sinai Medical Center , Los Angeles, CA Find this author on Google Scholar Find this author on PubMed Search for this author on this site Gordon C. Wishart 2 School of Medicine, Anglia Ruskin University , Cambridge, United Kingdom Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Gordon C. Wishart Pei-Chen Peng 1 Department of Computational Biomedicine, Cedars-Sinai Medical Center , Los Angeles, CA Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Pei-Chen Peng Abstract Full Text Info/History Metrics Preview PDF Abstract The PREDICT breast prognostic and treatment benefit model has undergone several revisions since its first release. The most recent version (v3.1) was developed using a data set of 35,474 cases diagnosed between 2000 and 2017 in a single region of England. PREDICT breast provides predicted outcomes at 5, 10 and 15 years, but most clinicians use the 10-year outcomes for decision making. The purpose of this study was to reparameterize the model using a larger data set from across the UK and to compare the performance of v4.0 with that of v3.1. There were 172,208 eligible cases randomly split 50:50 into model development and validation data sets. Cox proportional hazards models were derived for estrogen receptor negative and estrogen receptor positive cancer for breast cancer specific mortality with a third model for non-breast cancer mortality. In cases with at least five years follow-up and censored at ten years, the model was well-calibrated with a less than 5% difference between observed and predicted breast cancer deaths. Model discrimination was also good with AUCs in the validation data of 0.735 and 0.794 for ER negative and ER positive cases respectively. Calibration and discrimination were slightly improved compared to PREDICT breast v3.1. Introduction The PREDICT breast cancer prognostication and treatment benefit prediction model (v1) was developed in 2010 using data from the UK East Anglia Cancer Registration and Information Centre (ECRIC) for model fitting and data from the West Midlands Cancer Intelligence Unit for model validation 1 - 3 . PREDICT v1 was implemented as a web-based tool for clinicians in January 2011 ( www.breast.predict.nhs.uk ), and since then the use of the tool has increased steadily around the world. The model was refitted in 2017 using the original cohort of cases from East Anglia with updated survival time in order to take into account age at diagnosis and to smooth out the hazard ratio functions for tumour size and node status (v2) 4 and the website was redesigned (now at https://breast.predict.cam ). A further update using a larger, more contemporary data set was published in 2023 (v3). PREDICT breast v3 was developed using data from 4,644 ER-negative and 30,830 ER-positive breast cancer cases diagnosed from 2000 to 2017 in the region served by the Eastern Cancer Registry in the UK (available at https://breast.v3.predict.cam ). PREDICT has been independently validated in cohorts from Canada 5 , India 6 , Japan 7 , Malaysia 8 , the Netherlands 9 - 11 , New Zealand 12 , Spain 13 , the UK 14 15 and the USA 16 - 18 and has generally been shown to have good discrimination and calibration. PREDICT breast provides predicted outcomes at 5, 10 and 15 years after diagnosis, but for clinical decision making most clinicians use the 10-year outcomes. The purpose of this analysis was to use a larger data set to re-parameterize the model to optimize performance in the most recently diagnosed cases. Methods Patient data All analyses were carried out on anonymized data from the National Cancer Registration and Analysis Service for all women diagnosed in England with non-metastatic invasive breast cancer from 2000 to 2017 inclusive. The use of these data complies with all relevant ethical and data governance regulations. Patient information is collected by NCRAS without the need for patient consent under Section 251 of the National Health Service Act 2006 and its current Regulations, the Health Service (Control of Patient Information) Regulations 2002. Ethical approval by the National Research Ethics Service was not required because all analyses were carried out on an anonymized data set. Information on all cases included age at diagnosis, year of diagnosis, tumour size, histological grade, tumour stage at diagnosis, number of lymph nodes sampled, number of lymph nodes positive, ER status, HER2 status, mode of detection (clinically detected vs. screen detected), and whether the patient had undergone chemotherapy, hormone therapy and/or radiotherapy within 6 months of diagnosis. Patients younger than 25 or older than 85 at diagnosis, patients with a tumour larger than 20 centimetres, or with more than 20 positive lymph nodes were excluded from the analysis. Of 372,110 cases, complete data for age at diagnosis, year of diagnosis, tumour size, histological grade, tumour stage at diagnosis, number of lymph nodes sampled, number of lymph nodes positive, ER status were available for 172,708 (46%). These were randomly split 50:50 into a model training data set and a model testing data set. The sample sizeof the training data was more than sufficient (compared with the ∼35,000 cases used in the original v3 development cohort) to derive stable parameter estimates, while preserving a similarly large independent validation set for unbiased performance assessment. Details of the specific regimen used for radiotherapy, chemotherapy, duration of hormonal therapy, or use of trastuzumab or bisphosphonates were not available. We assumed that all patients that underwent chemotherapy were treated with an anthracycline-based regimen and that all women received hormonal therapy for five years. The benefits of radiotherapy were applied to all patients who received it including those who had lumpectomy and those who had mastectomy as the primary surgical treatment. Death certificate flagging through the Office for National Statistics provides the registries with notification of deaths. The lag times for these are a few weeks for cancer deaths and 2 months to 1 year for non-cancer deaths. Vital status was ascertained at the end of December 2019, and so all analyses were censored on 31 December 2018 to allow for delay in reporting of vital status. Breast cancer-specific mortality was defined as deaths where breast cancer was listed as the cause of death on part 1a, 1b or 1c of the death certificate. Statistical methods The general approach to model development was similar to that use for the development of v2 and v3. Multivariable Cox proportional hazards models were used to estimate the prognostic effect of each variable. In all models follow up time was defined as the time from breast cancer diagnosis to last follow up, death or 15 years after diagnosis, whichever came first. The outcome of interest was either breast cancer-specific mortality or mortality from other causes. Separate models were derived for breast cancer-specific mortality in ER-negative and ER-positive cases. Multivariable fractional polynomials were used to model non-linear effects between the continuous risk factors (age at diagnosis, tumour size and number of positive nodes) and breast cancer-specific mortality to improve the fit to the data in the presence of non-linearity. Sequential backward elimination with a maximum of 4 degrees of freedom for a single continuous predictor was used to estimate the continuous variable transformations. Age at diagnosis was transformed to age at diagnosis minus 24 so that the baseline hazard corresponds to that of a case diagnosed age 24. Year of diagnosis was grouped into before 2011 and 2011 and later; the latter was used as the baseline category so that the baseline hazard function will be that for more contemporary patients. Parameter estimates for HER2 2 , KI67 3 and PR 12 for previous versions of PREDICT breast were derived from external data. There was a substantial proportion of missing data for these variables and so the same parameter estimates were used for version 4.0. The relative treatment benefits for chemotherapy, hormone therapy and radiotherapy were constrained to the estimates of benefit from the randomised controlled trial meta-analyses of the Early Breast Cancer Trialists Collaborative Group (adjuvant hormone therapy log hazard ratio -0.386 19 , adjuvant chemotherapy log hazard ratio -0.248 20 , radiotherapy log hazard ratio -0.180 21 ) by adding them as an offset in the breast cancer specific mortality analyses. The relative harms of chemotherapy and radiotherapy were constrained to the estimates of benefit reported by Kerr and colleagues (adjuvant chemotherapy log hazard ratio 0.183) 22 and Taylor and colleagues (radiotherapy log hazard ratio 0.078 per Gray whole-heart dose) 23 by adding them as an offset in the analysis of other mortality. After fitting the Cox proportional hazards models to ER-negative and ER-positive cases, a multiple fractional polynomial model with a Gaussian distribution was fit to the baseline hazards according to the method of Sauberei and colleagues to derive smoothed baseline hazard functions for breast cancer-specific mortality and non-breast cancer specific mortality. Results A total of 172,708 cases were included in the analyses. The characteristics of the cases in the training and validation data sets by ER status are shown in Table 1 . Cox proportional hazards models were built using multi-variable fractional polynomials. The fractional polynomial functions for the variables of interest are shown in Table 2 together with the associated hazard ratios and 95% confidence limits. The hazard ratio as a function of the fractional polynomials for age at diagnosis, tumour size and number of positive nodes are shown in Figure 1 . The observed baseline hazards and the fitted curve for the corresponding multi-variable fractional polynomial regression models are shown in Figure 2 . View this table: View inline View popup Download powerpoint Table 1: Characteristics of female breast cancer cases by ER status View this table: View inline View popup Download powerpoint Table 2: Fractional polynomial functions for variables in the Cox proportional hazards regression models with associated hazard ratios and 95% confidence limits. Download figure Open in new tab Figure 1. Fractional polynomial hazard ratio functions for age at diagnosis (A), tumour size (B) and number of positive lymph nodes (C). Blue line ER positive cases, red line ER negative cases. Download figure Open in new tab Figure 2. Observed baseline hazards (grey dots) and multi-variable fractional polynomial fit (blue line) for breast cancer specific mortality in ER negative cases and ER positive cases and other mortality in all cases The model, designated PREDICT breast v4.0, based on the coefficients from the Cox proportional hazards model and the derived baseline hazard functions was applied to the subset of 56,357 cases (training data 28,010 cases; validation data 28,347 cases) diagnosed after 2010 with at least 5 years potential follow-up to obtain the expected breast mortality at 10 years. Breast cancer mortality and non-breast cancer mortality are treated as competing risks in the model. Expected breast mortality was then compared with the observed breast cancer mortality and the expected mortality based on v3.1 ( Table 3 ). Calibration was excellent in both training and validation data with less than 5% difference between the observed and predicted deaths from breast cancer. Goodness-of-fit was evaluated by comparing observed and predicted breast deaths in tenths of predicted risk. Figure 3 shows that there was good calibration of predicted deaths across all levels of risk. Discrimination was calculated as the area under the receiver operator characteristic curve. Discrimination of the ER positive model was somewhat better than that of the ER negative model. There was a small improvement in both calibration and discrimination for v4.0 compared to v3.1. View this table: View inline View popup Download powerpoint Table 3: Model calibration and discrimination for PREDICT breast v4.0 compared to v3.1 Download figure Open in new tab Figure 3. Observed deaths from breast cancer compared to predicted in tenths of predicted risk. A. ER negative cases. B. ER positive cases. Discussion The PREDICT breast prognostic model has been refined and improved over a continuous programme of model development followed by deployment of the model to the PREDICT breast web tool. The major limitations of this study were the incompleteness of data on tumour markers HER2, KI67 and PR and the incomplete data on type of systemic treatment and duration of hormone therapy received by patients. However, the same limitations affected the development of previous versions of the model. Further development and refinement of the model might include the incorporation of tumour genomic risk scores and prognostic scores based on novel artificial intelligence algorithms applied to routing heamatoxylin and eosin stained pathology sections. PREDICT breast v4.0 provides a small improvement compared to v3.1 in a contemporary cohort of female breast cancer cases representative of the population in England. Given the good performance of earlier versions of PREDICT breast in other populations we expect v4.0 to perform equally well. Data availability The data used for these analyses cannot be shared by the authors for reasons of confidentiality. They are available on request from the England National Disease Registration Service at https://digital.nhs.uk/services/national-disease-registration-service#requests-for-access-to-ndrs-data . Code Availability All analyses were carried out using the mfp 24 , patchwork 25 , pROC , 26 survival 27 , tableone 28 and tidyverse 29 packages for the R software 30 implemented in R Studio 31 . The R markdown script used to analyse the data and draw the figures are available at https://github.com/paul-pharoah/predict . Author contributions PDPP conceived the project carried out the data analysis and wrote the first draft of the manuscript Y-WH provided feedback on the analyses and edited the manuscript GCW conceived the project and edited the manuscript. P-CP provided feedback on the analyses and edited the manuscript All authors approved the final version of the manuscript. Competing Interests Gordon Wishart and Paul Pharoah each receive a share of the fees received by Cambridge Enterprise for the licensing of PREDICT Breast to commercial partners. The other authors have no non-financial conflicts of interest to declare. References 1. ↵ Wishart GC , Azzato EM , Greenberg DC , Rashbass J , Kearins O , Lawrence G , et al. PREDICT: a new UK prognostic model that predicts survival following surgery for invasive breast cancer . Breast Cancer Res 2010 ; 12 ( 1 ): R1 . OpenUrl CrossRef PubMed 2. ↵ Wishart GC , Bajdik CD , Dicks E , Provenzano E , Schmidt MK , Sherman M , et al. PREDICT Plus: development and validation of a prognostic model for early breast cancer that includes HER2 . Br J Cancer 2012 ; 107 ( 5 ): 800 – 7 . OpenUrl CrossRef PubMed Web of Science 3. ↵ Wishart GC , Rakha E , Green A , Ellis I , Ali HR , Provenzano E , et al. Inclusion of KI67 significantly improves performance of the PREDICT prognostication and prediction model for early breast cancer . BMC Cancer 2014 ; 14 : 908 . OpenUrl CrossRef PubMed 4. ↵ Candido Dos Reis FJ , Wishart GC , Dicks EM , Greenberg D , Rashbass J , Schmidt MK , et al. An updated PREDICT breast cancer prognostication and treatment benefit prediction model with independent validation . Breast Cancer Res 2017 ; 19 ( 1 ): 58 . OpenUrl PubMed 5. ↵ Wishart GC , Bajdik CD , Azzato EM , Dicks E , Greenberg DC , Rashbass J , et al. A population-based validation of the prognostic model PREDICT for early breast cancer . Eur J Surg Oncol 2011 ; 37 ( 5 ): 411 – 7 . OpenUrl CrossRef PubMed 6. ↵ Nair NS , Kothari B , Gupta S , Kanann S , Vanmali V , Hawaldar R , et al. Validation of PREDICT Version 2.2 in a Retrospective Cohort of Indian Women With Operable Breast Cancer . JCO Glob Oncol 2023 ; 9 : e2300114 . OpenUrl 7. ↵ Zaguirre K , Kai M , Kubo M , Yamada M , Kurata K , Kawaji H , et al. Validity of the prognostication tool PREDICT version 2.2 in Japanese breast cancer patients . Cancer Med 2021 ; 10 ( 5 ): 1605 – 13 . OpenUrl PubMed 8. ↵ Wong HS , Subramaniam S , Alias Z , Taib NA , Ho GF , Ng CH , et al. The predictive accuracy of PREDICT: a personalized decision-making tool for Southeast Asian women with breast cancer . Medicine (Baltimore) 2015 ; 94 ( 8 ): e593 . OpenUrl CrossRef PubMed 9. ↵ de Glas NA , Bastiaannet E , Engels CC , de Craen AJ , Putter H , van de Velde CJ , et al. Validity of the online PREDICT tool in older patients with breast cancer: a population-based study . Br J Cancer 2016 ; 114 ( 4 ): 395 – 400 . OpenUrl CrossRef PubMed 10. Engelhardt EG , van den Broek AJ , Linn SC , Wishart GC , Rutgers EJT , van de Velde AO , et al. Accuracy of the online prognostication tools PREDICT and Adjuvant! for early-stage breast cancer patients younger than 50 years . Eur J Cancer 2017 ; 78 : 37 – 44 . OpenUrl CrossRef PubMed 11. ↵ van Maaren MC , van Steenbeek CD , Pharoah PDP , Witteveen A , Sonke GS , Strobbe LJA , et al. Validation of the online prediction tool PREDICT v. 2.0 in the Dutch breast cancer population . Eur J Cancer 2017 ; 86 : 364 – 72 . OpenUrl CrossRef PubMed 12. ↵ Grootes I , Keeman R , Blows FM , Milne RL , Giles GG , Swerdlow AJ , et al. Incorporating progesterone receptor expression into the PREDICT breast prognostic model . Eur J Cancer 2022 ; 173 : 178 – 93 . OpenUrl CrossRef PubMed 13. ↵ Aguirre U , Garcia-Gutierrez S , Romero A , Domingo L , Castells X , Sala M , et al. External validation of the PREDICT tool in Spanish women with breast cancer participating in population-based screening programmes . J Eval Clin Pract 2019 ; 25 ( 5 ): 873 – 80 . OpenUrl CrossRef PubMed 14. Maishman T , Copson E , Stanton L , Gerty S , Dicks E , Durcan L , et al. An evaluation of the prognostic model PREDICT using the POSH cohort of women aged 40 years at breast cancer diagnosis . Br J Cancer 2015 ; 112 ( 6 ): 983 – 91 . OpenUrl CrossRef PubMed 15. Gray E , Marti J , Brewster DH , Wyatt JC , Hall PS , Group SA . Independent validation of the PREDICT breast cancer prognosis prediction tool in 45,789 patients using Scottish Cancer Registry data . Br J Cancer 2018 ; 119 ( 7 ): 808 – 14 . OpenUrl CrossRef PubMed 16. ↵ Hsiao YW , Wishart GC , Pharoah PDP , Peng PC . Assessing the Performance of the PREDICT Breast Version 3.0 Prognostic Tool in Patients With Breast Cancer in the United States . J Natl Compr Canc Netw 2025 ; 23 ( 6 ): 227 – 33 . OpenUrl PubMed 17. Stabellini N , Cao L , Towe CW , Miller ME , Sousa-Santos AH , Amin AL , et al. Validation of the PREDICT Prognostication Tool in US Patients With Breast Cancer . J Natl Compr Canc Netw 2023 ; 21 ( 10 ): 1011 – 19 e6 . OpenUrl PubMed 18. ↵ Deng Z , Jones MR , Wolff AC , Visvanathan K. Evaluation of Predict, a prognostic risk tool, after diagnosis of a second breast cancer . JNCI Cancer Spectr 2023 ; 7 ( 6 ). 19. ↵ Early Breast Cancer Trialists’ Collaborative Group , Davies C , Godwin J , Gray R , Clarke M , Cutter D , et al. Relevance of breast cancer hormone receptors and other factors to the efficacy of adjuvant tamoxifen: patient-level meta-analysis of randomised trials . Lancet 2011 ; 378 ( 9793 ): 771 – 84 . OpenUrl CrossRef PubMed Web of Science 20. ↵ Early Breast Cancer Trialists Collaborative Group . Comparisons between different polychemotherapy regimens for early breast cancer: meta-analyses of long-term outcome among 100,000 women in 123 randomised trials . Lancet 2012 ; 379 ( 9814 ): 432 – 44 . OpenUrl CrossRef PubMed Web of Science 21. ↵ Early Breast Cancer Trialists’ Collaborative Group , Darby S , McGale P , Correa C , Taylor C , Arriagada R , et al. Effect of radiotherapy after breast-conserving surgery on 10-year recurrence and 15-year breast cancer death: meta-analysis of individual patient data for 10,801 women in 17 randomised trials . Lancet 2011 ; 378 ( 9804 ): 1707 – 16 . OpenUrl CrossRef PubMed Web of Science 22. ↵ Kerr AJ , Dodwell D , McGale P , Holt F , Duane F , Mannu G , et al. Adjuvant and neoadjuvant breast cancer treatments: A systematic review of their effects on mortality . Cancer Treat Rev 2022 ; 105 : 102375 . OpenUrl CrossRef PubMed 23. ↵ Taylor C , Correa C , Duane FK , Aznar MC , Anderson SJ , Bergh J , et al. Estimating the Risks of Breast Cancer Radiotherapy: Evidence From Modern Radiation Doses to the Lungs and Heart and From Previous Randomized Trials . J Clin Oncol 2017 ; 35 ( 15 ): 1641 – 49 . OpenUrl CrossRef PubMed 24. ↵ mfp: Multivariable Fractional Polynomials [program] . R package version 1.5.2.2 version , 2022 . https://CRAN.R-project.org/package=mfp . 25. ↵ patchwork: The Composer of Plots [program] . R package version 1.1.2 version , 2022 . https://CRAN.R-project.org/package=patchwork . 26. ↵ Robin X , Turck N , Hainard A , Tiberti N , Lisacek F , Sanchez JC , et al. pROC: an open-source package for R and S+ to analyze and compare ROC curves . BMC Bioinformatics 2011 ; 12 : 77 . OpenUrl CrossRef PubMed 27. ↵ A Package for Survival Analysis in R [program] . R package version 3.5-3 version , 2023 . https://CRAN.R-project.org/package=survival . 28. ↵ tableone: Create ‘Table 1’ to Describe Baseline Characteristics with or without Propensity Score Weights [program] . R package version 0.13.2 version , 2022 . https://CRAN.R-project.org/package=tableone . 29. ↵ Wickham H , Averick M , Bryan J , Chang W , McGowan LD , François R , et al. Welcome to the tidyverse . Journal of Open Source Software 2019 ; 4 : 1686 . OpenUrl 30. ↵ R: A language and environment for statistical computing [program] : R Foundation for Statistical Computing , Vienna, Austria , 2021 . https://www.R-project.org/ . 31. ↵ R Studio: Integrated Development for R [program] . RStudio, PBC, Boston, MA , 2020 . http://www.rstudio.com/ . View the discussion thread. Back to top Previous Next Posted August 29, 2025. Download PDF Email Thank you for your interest in spreading the word about medRxiv. NOTE: Your email address is requested solely to identify you as the sender of this article. Your Email * Your Name * Send To * Enter multiple addresses on separate lines or separate them with commas. You are going to email the following PREDICT breast v4.0: An update to the PREDICT breast prognostic model Message Subject (Your Name) has forwarded a page to you from medRxiv Message Body (Your Name) thought you would like to see this page from the medRxiv website. Your Personal Message CAPTCHA This question is for testing whether or not you are a human visitor and to prevent automated spam submissions. Share PREDICT breast v4.0: An update to the PREDICT breast prognostic model Paul D.P. Pharoah , Yi-Wen Hsiao , Gordon C. Wishart , Pei-Chen Peng medRxiv 2025.08.28.25334663; doi: https://doi.org/10.1101/2025.08.28.25334663 Share This Article: Copy Citation Tools PREDICT breast v4.0: An update to the PREDICT breast prognostic model Paul D.P. Pharoah , Yi-Wen Hsiao , Gordon C. Wishart , Pei-Chen Peng medRxiv 2025.08.28.25334663; doi: https://doi.org/10.1101/2025.08.28.25334663 Citation Manager Formats BibTeX Bookends EasyBib EndNote (tagged) EndNote 8 (xml) Medlars Mendeley Papers RefWorks Tagged Ref Manager RIS Zotero Tweet Widget Facebook Like Google Plus One Subject Area Oncology Subject Areas All Articles Addiction Medicine (567) Allergy and Immunology (863) Anesthesia (296) Cardiovascular Medicine (4409) Dentistry and Oral Medicine (443) Dermatology (380) Emergency Medicine (606) Endocrinology (including Diabetes Mellitus and Metabolic Disease) (1505) Epidemiology (15203) Forensic Medicine (30) Gastroenterology (1119) Genetic and Genomic Medicine (6570) Geriatric Medicine (666) Health Economics (994) Health Informatics (4510) Health Policy (1365) Health Systems and Quality Improvement (1608) Hematology (537) HIV/AIDS (1263) Infectious Diseases (except HIV/AIDS) (15902) Intensive Care and Critical Care Medicine (1103) Medical Education (620) Medical Ethics (144) Nephrology (665) Neurology (6572) Nursing (345) Nutrition (998) Obstetrics and Gynecology (1139) Occupational and Environmental Health (954) Oncology (3319) Ophthalmology (967) Orthopedics (369) Otolaryngology (420) Pain Medicine (435) Palliative Medicine (129) Pathology (662) Pediatrics (1689) Pharmacology and Therapeutics (691) Primary Care Research (710) Psychiatry and Clinical Psychology (5421) Public and Global Health (9205) Radiology and Imaging (2190) Rehabilitation Medicine and Physical Therapy (1367) Respiratory Medicine (1191) Rheumatology (593) Sexual and Reproductive Health (709) Sports Medicine (529) Surgery (709) Toxicology (99) Transplantation (288) Urology (265) (function(){function c(){var b=a.contentDocument||a.contentWindow.document;if(b){var d=b.createElement('script');d.innerHTML="window.__CF$cv$params={r:'9fe8e87f1e03df88',t:'MTc3OTI1NDU5NA=='};var a=document.createElement('script');a.src='/cdn-cgi/challenge-platform/scripts/jsd/main.js';document.getElementsByTagName('head')[0].appendChild(a);";b.getElementsByTagName('head')[0].appendChild(d)}}if(document.body){var a=document.createElement('iframe');a.height=1;a.width=1;a.style.position='absolute';a.style.top=0;a.style.left=0;a.style.border='none';a.style.visibility='hidden';document.body.appendChild(a);if('loading'!==document.readyState)c();else if(window.addEventListener)document.addEventListener('DOMContentLoaded',c);else{var e=document.onreadystatechange||function(){};document.onreadystatechange=function(b){e(b);'loading'!==document.readyState&&(document.onreadystatechange=e,c())}}}})();