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

Poster Display session 2

1096 - OncotypeDX® predictive nomogram for recurrence score output: a machine learning system based on quantitative immunochemistry analysis - ADAPTED01

Date

29 Sep 2019

Session

Poster Display session 2

Topics

Tumour Site

Breast Cancer

Presenters

Fabio Marazzi

Citation

Annals of Oncology (2019) 30 (suppl_5): v55-v98. 10.1093/annonc/mdz240

Authors

F. Marazzi1, V. Masiello1, R. Barone2, V. Magri3, A. Mulé4, A. Santoro4, F. Cacciatori4, L. Boldrini1, G. Franceschini4, F. Moschella4, G. Naso3, S. Tomao3, G. Mantini1, R. Masetti4, D. Smaniotto1, V. Valentini1

Author affiliations

  • 1 Dipartimento Di Radiologia, Radioterapia Oncologica E Ematologia, Fondazione Policlinico Gemelli IRCSS, 00168 - Roma/IT
  • 2 Technology For Life, Radius, 40054 - Budrio/IT
  • 3 Oncologia Medica, Università LaSapienza, 00100 - Roma/IT
  • 4 Dipartimento Di Scienze Della Salute Della Donna E Del Bambino E Di Sanità Pubblica, Fondazione Policlinico Gemelli IRCSS, 00168 - Roma/IT
More

Resources

Abstract 1096

Background

OncotypeDX (ODX®) can enhance prediction of breast cancer recurrence, guiding adjuvant treatment options. However, the opportunity to access this test is not always possible. The aim of this study is to investigate the correlation between phenotypical tumor characteristics, quantitative classical immunohistochemistry (IHC) and recurrent score (RS) resulting from ODX®.

Methods

All breast cancer patients who underwent ODX® between 2014 and 2018 were retrospectively included in the study. The data selected for analysis were age, menopausal status, pathological and IHC features. IHC was performed with standardized quantitative methods. Dataset was split into two subsets (70% for training and 30% for internal validation). Logistic models were built with statistically significant features for predicting RS ≤ 25 or ≤ 20. An external validation set, provided by another center, was used to test reliability of prediction models.

Results

The internal dataset included 407 patients (Table) who underwent ODX®. Mean age was 53.7 (31-80) and 222 patients (54.55%) were > 50 years old. ODX® results showed: 67 patients (16.6%) between 0-10, 272 patients between 11-25 (66.8%) and 68 pts > 26 (16.6%). At the logistic regression analysis, RS score was significantly associated with ER (p = 0.004), PgR (p < 0.001), and Ki67% (p < 0.001) with the threshold equal to 25. Above patients with RS ≤ 25, the generalized linear regression resulted in a well calibrated model with an AUC of 92.2% (sensitivity 84.2%; specificity 80.1%). External validation set included 180 patients and confirmed the model performance with an AUC of 82.3% and good calibration. A nomogram predicting RS score ≤25 was generated.Table:

261P Tumor characteristics training set + internal test set

Training + internal test set – Tumor characteristics
Histological subtype classificationInvasive Ductal Carcinoma318 pts (78,1%)
Invasive Lobular Carcinoma47 pts (11,5%)
Other42 pts (10,3%)
Grading128 pts (6.8%)
2268 pts (65,8%)
3111 pts (27,3%)
pT1a3 pts (0,7%)
1b38 pts (9,3%)
1c216 pts (53,1%)
2143 pts (35,1%)
36 pts (1,5%)
41 pt (0,3%)
pN0233 pts (57,2%)
0i+12 pts (3%)
1mic43 pts (10,6%)
1108 pts (26,5%)
NA11 pts (2,7%)
Mean T diameter [cm]1.9 (Range 0,2-8,5)
Mean Sentinel Lymph Node (SLN) diameter [mm]1.7 (Range 0-40)
Mean Axillary Lymph Node (ALN) diameter [mm]0.8 (Range 0-25)
Mean N Ratio0.14 (0.00 – 1.00)
SLN involvement [n° of nodes]0261 pts (64,1%)
1112 pts (27,5%)
224 pts (5,8%)
31 pt (0,2%)
NA9 pts (2,2%)
ALN involvement [n° of nodes]0338 pts (83%)
 0i+4 pts (1%)
 1mic3 pts (0,7%)
 131 pts (7,6%)
 28 pts (2%)
 35 pts (1,2%)
 51 pt (0,2%)
 NA17 pts (4,1%)
MultifocalityYes97 pts (23,8%)
No300 pts (73,7%)
NA10 pts (2.5%)
MulticentricityYes20 pts (4,9%)
No376 pts (92,4%)
 NA11 pts (2,7%)
PVIAbsent242 pts (59,4%)
Focal51 pts (12,5%)
Moderate32 pts (7,8%)
Massive59 pts (14,5%)
NA23 pts (5,6%)
Mean ER expression87,9% (Range 1-100)
Mean PgR expression62.2% (Range 0-100)
Mean AR expression7.7% (Range 0-90)
Mean Ki67% expression29.8% (Range 0-90)
Her2 Expression0187 pts (46%)
1112 pts (27,5%)
2104 pts (25,5%)
NA4 pts (0,9%)
Fluorescence in situ hybridization (FISH) for HER-2Not determined300 pts (73,7%)
Not amplificated100 pts (23,7%)
Undetermined1 pt (0,2%)
Equivocal1 pt (0,2%)

Conclusions

Quantitative IHC presents a good correlation with RS score in patients with RS ≤ 25, also in external validation set. A nomogram for physician that enhances a cost/effectiveness clinical approach practice has been developed. Prospective clinical application will be tested in further studies.

Clinical trial identification

Editorial acknowledgement

Legal entity responsible for the study

Fabio Marazzi.

Funding

Has not received any funding.

Disclosure

All 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.