André Pfob1,2, Chris Sidey-Gibbons2,3, Geraldine Rauch4, Bettina Thomas5, Benedikt Schaefgen1, Sherko Kuemmel6, Toralf Reimer7, Markus Hahn8, Marc Thill9, Jens-Uwe Blohmer10, John Hackmann11, Wolfram Malter12, Inga Bekes13, Kay Friedrichs14, Sebastian Wojcinski15, Sylvie Joos16, Stefan Paepke17, Tom Degenhardt18, Joachim Rom19, Achim Rody20, Marion van Mackelenbergh20, Maggie Banys-Paluchowski20,21, Regina Große22, Mattea Reinisch6, Maria Karsten10, Michael Golatta1, Joerg Heil1. 1. University Breast Unit, Department of Obstetrics & Gynecology, Heidelberg University Hospital, Heidelberg, Germany. 2. MD Anderson Center for INSPiRED Cancer Care (Integrated Systems for Patient-Reported Data), The University of Texas MD Anderson Cancer Center, Houston, TX. 3. Department of Symptom Research, The University of Texas MD Anderson Cancer Center, Houston, TX. 4. Institute of Biometry and Clinical Epidemiology, Charité-Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, Germany. 5. Coordination Centre for Clinical Trials (KKS), University Heidelberg, Heidelberg, Germany. 6. Breast Unit, Kliniken Essen-Mitte, Essen, Germany. 7. Department of Gynecology/Breast Unit, University Hospital Rostock, Rostock, Germany. 8. Department of Gynecology/Breast Unit, University Hospital Tuebingen, Tuebingen, Germany. 9. Department of Gynecology and Gynecological Oncology/Breast Unit, Agaplesion Markus Hospital Frankfurt, Frankfurt, Germany. 10. Charité-Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt Universität zu Berlin, Department of Gynecology with Breast Center, Berlin, Germany. 11. Department of Gynecology/Breast Unit, Marienhospital, Witten, Germany. 12. Department of Gynecology and Obstetrics, Breast Cancer Center, Medical Faculty, University of Cologne, Cologne, Germany. 13. Department of Gynecology/Breast Unit, University Hospital Ulm, Ulm, Germany. 14. Department of Gynecology/Breast Unit, Jerusalem Hospital Hamburg, Hamburg, Germany. 15. Department of Gynecology and Obstetrics, Breast Cancer Center, Klinikum Bielefeld Mitte GmbH, Bielefeld, Germany. 16. Radiologische Allianz Hamburg, Hamburg, Germany. 17. Department of Gynecology/Breast Unit, Hospital rechts der Isar, Munich, Germany. 18. Department of Gynecology/Breast Unit, University Hospital Munich, Munich, Germany. 19. Department of Gynecology/Breast Unit, Klinikum Frankfurt-Höchst, Frankfurt, Germany. 20. Department of Gynecology/Breast Unit, University Hospital Schleswig-Holstein, Luebeck, Germany. 21. Medical Faculty, Heinrich Heine University Düsseldorf, Düsseldorf, Germany. 22. Department of Gynecology/Breast Unit, University Hospital Halle, Halle, Germany.
Abstract
PURPOSE: Neoadjuvant systemic treatment (NST) elicits a pathologic complete response in 40%-70% of women with breast cancer. These patients may not need surgery as all local tumor has already been eradicated by NST. However, nonsurgical approaches, including imaging or vacuum-assisted biopsy (VAB), were not able to accurately identify patients without residual cancer in the breast or axilla. We evaluated the feasibility of a machine learning algorithm (intelligent VAB) to identify exceptional responders to NST. METHODS: We trained, tested, and validated a machine learning algorithm using patient, imaging, tumor, and VAB variables to detect residual cancer after NST (ypT+ or in situ or ypN+) before surgery. We used data from 318 women with cT1-3, cN0 or +, human epidermal growth factor receptor 2-positive, triple-negative, or high-proliferative Luminal B-like breast cancer who underwent VAB before surgery (ClinicalTrials.gov identifier: NCT02948764, RESPONDER trial). We used 10-fold cross-validation to train and test the algorithm, which was then externally validated using data of an independent trial (ClinicalTrials.gov identifier: NCT02575612). We compared findings with the histopathologic evaluation of the surgical specimen. We considered false-negative rate (FNR) and specificity to be the main outcomes. RESULTS: In the development set (n = 318) and external validation set (n = 45), the intelligent VAB showed an FNR of 0.0%-5.2%, a specificity of 37.5%-40.0%, and an area under the receiver operating characteristic curve of 0.91-0.92 to detect residual cancer (ypT+ or in situ or ypN+) after NST. Spiegelhalter's Z confirmed a well-calibrated model (z score -0.746, P = .228). FNR of the intelligent VAB was lower compared with imaging after NST, VAB alone, or combinations of both. CONCLUSION: An intelligent VAB algorithm can reliably exclude residual cancer after NST. The omission of breast and axillary surgery for these exceptional responders may be evaluated in future trials.
PURPOSE: Neoadjuvant systemic treatment (NST) elicits a pathologic complete response in 40%-70% of women with breast cancer. These patients may not need surgery as all local tumor has already been eradicated by NST. However, nonsurgical approaches, including imaging or vacuum-assisted biopsy (VAB), were not able to accurately identify patients without residual cancer in the breast or axilla. We evaluated the feasibility of a machine learning algorithm (intelligent VAB) to identify exceptional responders to NST. METHODS: We trained, tested, and validated a machine learning algorithm using patient, imaging, tumor, and VAB variables to detect residual cancer after NST (ypT+ or in situ or ypN+) before surgery. We used data from 318 women with cT1-3, cN0 or +, human epidermal growth factor receptor 2-positive, triple-negative, or high-proliferative Luminal B-like breast cancer who underwent VAB before surgery (ClinicalTrials.gov identifier: NCT02948764, RESPONDER trial). We used 10-fold cross-validation to train and test the algorithm, which was then externally validated using data of an independent trial (ClinicalTrials.gov identifier: NCT02575612). We compared findings with the histopathologic evaluation of the surgical specimen. We considered false-negative rate (FNR) and specificity to be the main outcomes. RESULTS: In the development set (n = 318) and external validation set (n = 45), the intelligent VAB showed an FNR of 0.0%-5.2%, a specificity of 37.5%-40.0%, and an area under the receiver operating characteristic curve of 0.91-0.92 to detect residual cancer (ypT+ or in situ or ypN+) after NST. Spiegelhalter's Z confirmed a well-calibrated model (z score -0.746, P = .228). FNR of the intelligent VAB was lower compared with imaging after NST, VAB alone, or combinations of both. CONCLUSION: An intelligent VAB algorithm can reliably exclude residual cancer after NST. The omission of breast and axillary surgery for these exceptional responders may be evaluated in future trials.
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: Maggie Banys-Paluchowski; Marc Thill; Thorsten Kühn; Nina Ditsch; Jörg Heil; Achim Wöckel; Eva Fallenberg; Michael Friedrich; Sherko Kümmel; Volkmar Müller; Wolfgang Janni; Ute-Susann Albert; Ingo Bauerfeind; Jens-Uwe Blohmer; Wilfried Budach; Peter Dall; Peter Fasching; Tanja Fehm; Oleg Gluz; Nadia Harbeck; Jens Huober; Christian Jackisch; Cornelia Kolberg-Liedtke; Hans H Kreipe; David Krug; Sibylle Loibl; Diana Lüftner; Michael Patrick Lux; Nicolai Maass; Christoph Mundhenke; Ulrike Nitz; Tjoung Won Park-Simon; Toralf Reimer; Kerstin Rhiem; Achim Rody; Marcus Schmidt; Andreas Schneeweiss; Florian Schütz; H Peter Sinn; Christine Solbach; Erich-Franz Solomayer; Elmar Stickeler; Christoph Thomssen; Michael Untch; Isabell Witzel; Bernd Gerber Journal: Geburtshilfe Frauenheilkd Date: 2022-09-30 Impact factor: 2.754