Background. Neoadjuvant therapy has become the standard of care for HER2-positive breast cancer (BC). However, only half of the patients achieve a pathological complete response (pCR). Our study aims to test the CE/IVD MammaTyper kit (Cerca Biotech) as a predictor of response to neoadjuvant chemotherapy (NACT). Materials and Methods. Fifty-three HER2-positive/3+ IHC-score invasive BC patients undergoing NACT were enrolled. The study was approved by the local Ethical Committee and written consent was obtained from each participant. Four patients were excluded due to insufficient amount of RNA required for analysis, therefore a total of 49 FFPE preoperatory biopsies samples were selected and tested. Of these, 25 were hormone-positive (HR+) and 24 hormone-negative (HR-), 33 obtained a pCR and 16 a pathological partial response (pPR). MammaTyper®, a molecular in vitro diagnostic RT-qPCR test, was used to assess the relative mRNA expression levels of ERBB2 (HER2), ESR1 (ER), PGR (PgR) and MKI67 (Ki67) genes. A machine-learning, Python-based Decision Tree Algorithm was used to predict PCR from the ddCq values of ERBB2, ESR1, PGR, and MKI67. Samples were divided based on hormone receptors (ER and/or PgR) status from MammaTyper®. Focusing on a balance of interpretability and generalizability, we tuned key hyperparameters and used GridSearchCV with 5-fold cross-validation. Analytical accuracy was analyzed in terms of sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV). Results. Of the Decision Trees generated, two were selected showing high specificity and sensitivity, and plausible biomarkers hierarchy. In detail, the selected tree for HR+ tumors had a sensitivity of 94%, a specificity of 83%, a PPV of 94% and a NPV of 83%; instead, that for HR- tumors had a sensitivity of 94%, a specificity of 86%, a PPV of 94% and a NPV of 86%. Conclusions. MammaTyper could discriminate patients with HER2-positive BC who will achieve pCR from those who will not, representing a powerful decision tool in terms of escalation/de-escalation treatment approaches. However, these promising and preliminary data need to be confirmed on a larger cohort of patients. Funding: Research Project "Tuscany Health Ecosystem" Ecosistema dell’innovazione sulle scienze e le tecnologie della vita in Toscana (THE) - Spoke 6: Precision Medicine & Personalized Healthcare - Advanced biomarkers for patient stratification. CUP I53C22000780001.

Prediction of response to neoadjuvant chemotherapy in HER2 positive breast cancer by MammaTyper®

Cristian Scatena;Eugenia Belcastro;Rosa Scarpitta;Antonio Giuseppe Naccarato
2024-01-01

Abstract

Background. Neoadjuvant therapy has become the standard of care for HER2-positive breast cancer (BC). However, only half of the patients achieve a pathological complete response (pCR). Our study aims to test the CE/IVD MammaTyper kit (Cerca Biotech) as a predictor of response to neoadjuvant chemotherapy (NACT). Materials and Methods. Fifty-three HER2-positive/3+ IHC-score invasive BC patients undergoing NACT were enrolled. The study was approved by the local Ethical Committee and written consent was obtained from each participant. Four patients were excluded due to insufficient amount of RNA required for analysis, therefore a total of 49 FFPE preoperatory biopsies samples were selected and tested. Of these, 25 were hormone-positive (HR+) and 24 hormone-negative (HR-), 33 obtained a pCR and 16 a pathological partial response (pPR). MammaTyper®, a molecular in vitro diagnostic RT-qPCR test, was used to assess the relative mRNA expression levels of ERBB2 (HER2), ESR1 (ER), PGR (PgR) and MKI67 (Ki67) genes. A machine-learning, Python-based Decision Tree Algorithm was used to predict PCR from the ddCq values of ERBB2, ESR1, PGR, and MKI67. Samples were divided based on hormone receptors (ER and/or PgR) status from MammaTyper®. Focusing on a balance of interpretability and generalizability, we tuned key hyperparameters and used GridSearchCV with 5-fold cross-validation. Analytical accuracy was analyzed in terms of sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV). Results. Of the Decision Trees generated, two were selected showing high specificity and sensitivity, and plausible biomarkers hierarchy. In detail, the selected tree for HR+ tumors had a sensitivity of 94%, a specificity of 83%, a PPV of 94% and a NPV of 83%; instead, that for HR- tumors had a sensitivity of 94%, a specificity of 86%, a PPV of 94% and a NPV of 86%. Conclusions. MammaTyper could discriminate patients with HER2-positive BC who will achieve pCR from those who will not, representing a powerful decision tool in terms of escalation/de-escalation treatment approaches. However, these promising and preliminary data need to be confirmed on a larger cohort of patients. Funding: Research Project "Tuscany Health Ecosystem" Ecosistema dell’innovazione sulle scienze e le tecnologie della vita in Toscana (THE) - Spoke 6: Precision Medicine & Personalized Healthcare - Advanced biomarkers for patient stratification. CUP I53C22000780001.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11568/1224392
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact