André Pfob1, Chris Sidey-Gibbons2, Han-Byoel Lee3, Marios Konstantinos Tasoulis4, Vivian Koelbel1, Michael Golatta1, Gaiane M Rauch5, Benjamin D Smith6, Vicente Valero7, Wonshik Han3, Fiona MacNeill4, Walter Paul Weber8, Geraldine Rauch9, Henry M Kuerer10, Joerg Heil11. 1. Department of Gynecology, Heidelberg University, Heidelberg, Germany. 2. Department of Symptom Research, The University of Texas MD Anderson Cancer Center, Houston, USA. 3. Department of Surgery, Seoul National University College of Medicine, Seoul, South Korea; Biomedical Research Institute, Seoul National University Hospital, Seoul, South Korea; Cancer Research Institute, Seoul National University, Seoul, South Korea. 4. Department of Breast Surgery, The Royal Marsden NHS Foundation Trust, London, United Kingdom. 5. Department of Diagnostic Radiology, The University of Texas MD Anderson Cancer Center, Houston, USA. 6. Department of Radiation Oncology, University of Texas MD Anderson Cancer Center, Houston, USA. 7. Department of Breast Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, USA. 8. Department of Breast Surgery, University Hospital Basel and University of Basel, Basel, Switzerland. 9. Institute of Biometry and Clinical Epidemiology, Charité - Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, And Berlin Institute of Health, Berlin, Germany. 10. Department of Breast Surgical Oncology, The University of Texas MD Anderson Cancer Center, Houston, USA. 11. Department of Gynecology, Heidelberg University, Heidelberg, Germany. Electronic address: Joerg.Heil@med.uni-heidelberg.de.
Abstract
BACKGROUND: Neoadjuvant systemic treatment elicits a pathologic complete response (pCR) in about 35% of women with breast cancer. In such cases, breast surgery may be considered overtreatment. We evaluated multivariate algorithms using patient, tumor, and vacuum-assisted biopsy (VAB) variables to identify patients with breast pCR. METHODS: We developed and tested four multivariate algorithms: a logistic regression with elastic net penalty, an Extreme Gradient Boosting (XGBoost) tree, Support Vector Machines (SVM), and neural network. We used data from 457 women, randomly partitioned into training and test set (2:1), enrolled in three trials with stage 1-3 breast cancer, undergoing VAB before surgery. False-negative rate (FNR) and specificity were the main outcome measures. The best performing algorithm was validated in an independent fourth trial. RESULTS: In the test set (n = 152), the logistic regression with elastic net penalty, XGboost tree, SVM, and neural network revealed an FNR of 1.2% (1 of 85 patients with missed residual cancer). Specificity of the logistic regression with elastic net penalty was 52.2% (35 of 67 women with surgically confirmed breast pCR identified), of the XGBoost tree 55.2% (37 of 67), of SVM 62.7% (42 of 67), and of the neural network 67.2% (45 of 67). External validation (n = 50) of the neural network showed an FNR of 0% (0 of 27) and a specificity of 65.2% (15 of 23). Area under the ROC curve for the neural network was 0.97 (95% CI, 0.94-1.00). CONCLUSION: A multivariate algorithm can accurately select breast cancer patients without residual cancer after neoadjuvant treatment.
BACKGROUND: Neoadjuvant systemic treatment elicits a pathologic complete response (pCR) in about 35% of women with breast cancer. In such cases, breast surgery may be considered overtreatment. We evaluated multivariate algorithms using patient, tumor, and vacuum-assisted biopsy (VAB) variables to identify patients with breast pCR. METHODS: We developed and tested four multivariate algorithms: a logistic regression with elastic net penalty, an Extreme Gradient Boosting (XGBoost) tree, Support Vector Machines (SVM), and neural network. We used data from 457 women, randomly partitioned into training and test set (2:1), enrolled in three trials with stage 1-3 breast cancer, undergoing VAB before surgery. False-negative rate (FNR) and specificity were the main outcome measures. The best performing algorithm was validated in an independent fourth trial. RESULTS: In the test set (n = 152), the logistic regression with elastic net penalty, XGboost tree, SVM, and neural network revealed an FNR of 1.2% (1 of 85 patients with missed residual cancer). Specificity of the logistic regression with elastic net penalty was 52.2% (35 of 67 women with surgically confirmed breast pCR identified), of the XGBoost tree 55.2% (37 of 67), of SVM 62.7% (42 of 67), and of the neural network 67.2% (45 of 67). External validation (n = 50) of the neural network showed an FNR of 0% (0 of 27) and a specificity of 65.2% (15 of 23). Area under the ROC curve for the neural network was 0.97 (95% CI, 0.94-1.00). CONCLUSION: A multivariate algorithm can accurately select breast cancerpatients without residual cancer after neoadjuvant treatment.
Authors: Khadijeh Saednia; Andrew Lagree; Marie A Alera; Lauren Fleshner; Audrey Shiner; Ethan Law; Brianna Law; David W Dodington; Fang-I Lu; William T Tran; Ali Sadeghi-Naini Journal: Sci Rep Date: 2022-06-11 Impact factor: 4.996
Authors: Fernando A Angarita; Robert Brumer; Matthew Castelo; Nestor F Esnaola; Stephen B Edge; Kazuaki Takabe Journal: Cancers (Basel) Date: 2022-09-20 Impact factor: 6.575
Authors: Benedikt Schaefgen; Annika Funk; H-P Sinn; Thomas Bruckner; Christina Gomez; Aba Harcos; Anne Stieber; Annabelle Haller; Juliane Nees; Riku Togawa; André Pfob; André Hennigs; Johanna Hederer; Fabian Riedel; Sarah Fastner; Christof Sohn; Jörg Heil; Michael Golatta Journal: Breast Cancer Res Treat Date: 2021-12-08 Impact factor: 4.872