Oops, you're using an old version of your browser so some of the features on this page may not be displaying properly.

MINIMAL Requirements: Google Chrome 24+Mozilla Firefox 20+Internet Explorer 11Opera 15–18Apple Safari 7SeaMonkey 2.15-2.23

Lunch and Poster Display session

70P - Development and validation of a machine learning (ML) nomogram to predict RSClin results and guide adjuvant treatment of node-negative (N0) hormone receptor-positive (HR+)/human epidermal growth factor receptor-negative (HER2-) early breast cancer (eBC) in Europe

Date

16 May 2024

Session

Lunch and Poster Display session

Presenters

Flavia Jacobs

Citation

Annals of Oncology (2024) 9 (suppl_4): 1-34. 10.1016/esmoop/esmoop103010

Authors

F. Jacobs1, S. D'Amico2, E. Ferraro3, E. Agostinetto4, C.A. Tondini5, M. Gaudio6, C. Benvenuti6, R. Gerosa6, G. Saltalamacchia6, R. De Sanctis6, M.G. Della Porta6, A. Santoro6, M. Fornier7, E. de Azambuja4, A. Zambelli6

Author affiliations

  • 1 Humanitas University, Milan/IT
  • 2 Humanitas University, Pieve Emanuele/IT
  • 3 Memorial Sloan Kettering Cancer Center, New York/US
  • 4 Université Libre de Bruxelles (ULB), Hôpital Universitaire de Bruxelles (HUB), Institut Jules Bordet, Brussels/BE
  • 5 ASST Papa Giovanni XXIII, Bergamo/IT
  • 6 IRCCS Humanitas Research Hospital, Rozzano/IT
  • 7 Memorial Sloan Kettering Cancer Center, 10021 - New York/US

Resources

Login to get immediate access to this content.

If you do not have an ESMO account, please create one for free.

Abstract 70P

Background

RSClin is a proprietary algorithm that integrates clinical-pathological (CP) factors and genomic risk in patients with N0 HR+/HER2- eBC. RSClin refines the prognosis of distant recurrence (DR) and chemotherapy (CT) benefit more accurately than CP and Recurrence Score (RS) alone. Since RSClin is not available in Europe, we aimed to validate an automated ML-based nomogram able to predict RSClin outcomes with potential clinical impact in European countries.

Methods

We retrospectively collected CP and genomic characteristics of 290 patients with N0 HR+/HER2- eBC from 3 hospitals in Italy and Belgium from 2020 to 2022. Patients were randomly assigned with a 3:1 ratio to either the training or validation cohort. Features with a Pearson correlation over 0.2 were selected for model development. The ML-nomogram development and validation were based both on classification and regression models and included linear and logistic regression to predict DR and CT benefit.

Results

Compared to RSClin outcomes, classification model for DR achieved a ROC AUC of 0.97, while for CT benefit reached a score of 0.99. The regression analyses for DR and CT benefit yielded significant R2 scores of 0.84 and 0.72, respectively. A web-based tool was then implemented to increase ML nomogram accessibility worldwide. Within the study population, the use of this tool was able to refine the RS alone estimates of CT benefit converting the advice of CT sparing to CT recommendation in 27/290 (9.8%) patients, assuming a CT benefit>3% as clinically relevant. Table: 70P

Performance of ML tool for RSClin anticipation

Classifier Number of features ROC AUC F1
DR 11 0.97 0.93
CT benefit 12 0.99 0.97
Regressor Number of features R2 RMSE
DR 10 0.84 4.5
CT benefit 11 0.72 5.2

Abbreviations: CT: chemotherapy benefit; DR: distant relapse; ML: machine learning; R2: R-squared; RMSE: Root mean squared error; ROC AUC: Receiver operating characteristic, area under the curve.

Conclusions

Our ML-based nomogram can accurately reproduce RSClin results to support treatment decisions for patients with N0 HR+/HER2- eBC, identifying high-risk patients who may benefit from treatment intensification compared to RS alone. It can also be freely used in Europe where RSClin is not available.

Legal entity responsible for the study

The authors.

Funding

Has not received any funding.

Disclosure

F. Jacobs: Financial Interests, Personal, Other, Support for attending medical conferences: Novartis, Gilead. E. Agostinetto: Financial Interests, Personal, Speaker’s Bureau: Eli Lilly, Sandoz, AstraZeneca; Financial Interests, Personal and Institutional, Research Grant: Gilead; Financial Interests, Personal, Other, Support for attending medical conferences: Novartis, Eli Lilly, Roche, Genetic, Istituto Gentili, Daiichi Sankyo, AstraZeneca. R. De Sanctis: Financial Interests, Personal and Institutional, Research Grant: Gilead; Financial Interests, Personal, Advisory Board: Gilead, Lilly, Novartis, Istituto Clinico Gentili, Amgen, Eisai, Ipsen. A. Santoro: Financial Interests, Personal, Advisory Role: Bristol Myers Squibb, Servier, Gilead Science, Pfizer, Eisai, Bayer, MSD, Sanofi, Incyte; Financial Interests, Personal, Speaker’s Bureau: Takeda, Roche, AbbVie, Amgen, AstraZeneca, Lilly, Sandoz, Novartis, BMS, Servier, Gilead, Pfizer, Eisai, Bayer, MSD. E. de Azambuja: Financial Interests, Personal, Advisory Board: Roche/GNE, Novartis, Seagen, MSD; Financial Interests, Personal, Invited Speaker: Zodiac, Libbs, Pierre Fabre, Lilly, AstraZeneca, Gilead Sciences; Financial Interests, Personal, Other, Chair of the Gilead Sciences Research Scholars Program in Solid Tumours: Gilead Sciences; Financial Interests, Institutional, Research Grant: Roche/GNE, AstraZeneca, GSK/Novartis, Servier; Financial Interests, Institutional, Other, Travel Grant: Roche/GNE; Financial Interests, Institutional, Invited Speaker: MSD, ABCSG, Nektar, Gilead, Immunomedics, Synthon, Odonate Therapeutics; Financial Interests, Invited Speaker, ASCENT 04: Gilead; Financial Interests, Invited Speaker, Aphinity, Lorelei, Impassion03: Roche; Financial Interests, Invited Speaker, AURORA: Breast International Group; Financial Interests, Invited Speaker, Olympia: AstraZeneca; Financial Interests, Personal, Other, Travel grant: AstraZeneca; Non-Financial Interests, Advisory Role, Member of the cardio-oncology council: European Society for Cardiology (ESC); Non-Financial Interests, Advisory Role, Belgium governmental institution for cancer: KCE; Non-Financial Interests, Other, Editorial board member: ESMO Open; Non-Financial Interests, Advisory Role: Anticancer Fund; Non-Financial Interests, Leadership Role, President 2023-2026: Belgian Society of Medical Oncology (BSMO). A. Zambelli: Financial Interests, Personal, Speaker’s Bureau: Roche, Novartis, Lilly, Pfizer, AstraZeneca, Seagen, Gilead Sciences, Daiichi Sankyo Europe GmbH, Exact Sciences, Merck ; Financial Interests, Personal, Advisory Board: Gilead Sciences, Daiichi Sankyo Europe GmbH, Seagen; Financial Interests, Personal, Other, Travel, Accommodations, Expenses: AstraZeneca, Daiichi Sankyo Europe GmbH, Lilly. All other authors have declared no conflicts of interest.

This site uses cookies. Some of these cookies are essential, while others help us improve your experience by providing insights into how the site is being used.

For more detailed information on the cookies we use, please check our Privacy Policy.

Customise settings
  • Necessary cookies enable core functionality. The website cannot function properly without these cookies, and you can only disable them by changing your browser preferences.