Accessible model predicts response in hormone receptor positive HER2 negative breast cancer receiving neoadjuvant chemotherapy
Hormone receptor-positive/HER2-negative breast cancer (BC) is the most common subtype of BC and typically occurs as an early, operable disease. In patients receiving neoadjuvant chemotherapy (NACT), pathological complete response (pCR) is rare and multiple efforts have been made to predict disease recurrence. We developed a framework to predict pCR using clinicopathological characteristics widely available at diagnosis. The machine learning (ML) models were trained to predict pCR (n = 463), evaluated in an internal validation cohort (n = 109) and validated in an external validation cohort (n = 151). The best model was an Elastic Net, which achieved an area under the curve (AUC) of respectively 0.86 and 0.81. Our results highlight how simpler models using few input variables can be as valuable as more complex ML architectures. Our model is freely available and can be used to enhance the stratification of BC patients receiving NACT, providing a framework for the development of risk-adapted clinical trials.
Authors
- Giorgia Arcuri
- Armando Orlandi (ORCID: https://orcid.org/0000-0001-5253-4678)
- Fabio Puglisi (ORCID: https://orcid.org/0000-0003-0573-4938)
- Noemi Maliziola
- Federica Miglietta (ORCID: https://orcid.org/0000-0001-6203-874X)
- Sara Pilotto (ORCID: https://orcid.org/0000-0003-2229-4874)
- Luisa Carbognin (ORCID: https://orcid.org/0000-0003-3532-0963)
- Gianluca Franceschini (ORCID: https://orcid.org/0000-0002-2950-3395)
- Michèle Milella (ORCID: https://orcid.org/0000-0002-3826-5237)
- Giovanni Scambia (ORCID: https://orcid.org/0000-0002-9503-9041)
- Emilio Bria (ORCID: https://orcid.org/0000-0002-2333-704X)
- Ida Paris (ORCID: https://orcid.org/0000-0002-7445-3366)
- Valentina Guarneri (ORCID: https://orcid.org/0000-0002-2375-8397)
- Letizia Pontolillo (ORCID: https://orcid.org/0009-0006-3363-8512)
- Luca Mastrantoni (ORCID: https://orcid.org/0000-0003-1853-4927)
- Alessandra Fabi (ORCID: https://orcid.org/0000-0002-0758-8033)
- Sergio Pannunzio
- Giampaolo Tortora (ORCID: https://orcid.org/0000-0002-1378-4962)
- Lorenzo Gerratana (ORCID: https://orcid.org/0000-0002-8313-4834)
- Giovanna Garufi
- Fabio Marazzi (ORCID: https://orcid.org/0000-0003-0977-0143)
- Roberta Mazzeo
- Antonella Palazzo (ORCID: https://orcid.org/0000-0002-8371-7087)
- Maria Vittoria Dieci (ORCID: https://orcid.org/0000-0002-3967-9861)
- Antonio Franco (ORCID: https://orcid.org/0000-0003-3411-7015)
- Diana Giannarelli (ORCID: https://orcid.org/0000-0002-6085-1195)
- Elena Di Monte
- Valentina Frescura
- Giulia Giordano (ORCID: https://orcid.org/0000-0002-9384-7037)
- Angelachiara Rotondi
Institutions
- Università Cattolica del Sacro Cuore (IT)
- University of Verona (IT)
- University of Udine (IT)
- Agostino Gemelli University Polyclinic (IT)
- Istituto Oncologico Veneto (IT)
- Centro di Riferimento Oncologico (IT)
- Istituti di Ricovero e Cura a Carattere Scientifico (IT)
Publication Details
- Journal
- npj Breast Cancer
- Published
- 2025-02-05
- DOI
- https://doi.org/10.1038/s41523-025-00727-w
- Citations
- 9
- Primary Topic
- Breast Cancer Treatment Studies
- Type
- article
- Field-Weighted Citation Impact
- 8.43
Funders
- Ministero della Salute
- Associazione Italiana per la Ricerca sul Cancro