PURPOSENeoadjuvant 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.METHODSWe 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.RESULTSIn 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.CONCLUSIONAn 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.