biostudies-literatureHan LChina Scholarship CouncilFundo para o Desenvolvimento das Ciências e da Tecnologia103356https://www.ebi.ac.uk/biostudies/studies/S-EPMC12303063biostudies-literatureUnknown86<h4>Background</h4>Neoadjuvant therapy (NAT) regimens for breast cancer are generally determined according to cancer stage and molecular subtypes without fully considering the inter-patient variability, which may lead to inefficiency or overtreatment. Artificial intelligence (AI) may support personalized regimen recommendations by learning the synergistic relationship between pre-NAT individual-patient data, regimens, and corresponding short- or long-term therapy responses.<h4>Methods</h4>In this retrospective study, we collected data from breast cancer patients treated with NAT between 2000 and 2020 from the Netherlands and the USA. Median follow-up times ranged from 3·7 to 4·9 years across molecular subtypes and cohorts. We developed and externally validated a multi-modal model integratiEClinicalMedicineExploring personalized neoadjuvant therapy selection strategies in breast cancer: an explainable multi-modal response model.PMC123030632020062400650105/2022/APinker-Domenig KKok Mvan der Voort AHan LLiang XLu CMann RZhang TGao YTan TWang XSonke GTeuwen JD'Angelo AfalseExploring personalized neoadjuvant therapy selection strategies in breast cancer: an explainable multi-modal response model.<h4>Background</h4>Neoadjuvant therapy (NAT) regimens for breast cancer are generally determined according to cancer stage and molecular subtypes without fully considering the inter-patient variability, which may lead to inefficiency or overtreatment. Artificial intelligence (AI) may support personalized regimen recommendations by learning the synergistic relationship between pre-NAT individual-patient data, regimens, and corresponding short- or long-term therapy responses.<h4>Methods</h4>In this retrospective study, we collected data from breast cancer patients treated with NAT between 2000 and 2020 from the Netherlands and the USA. Median follow-up times ranged from 3·7 to 4·9 years across molecular subtypes and cohorts. We developed and externally validated a multi-modal model integrati2025-01-01T00:00:00Z2025 Aug2026-07-15T09:46:48.234Z2025-08-17T03:05:55.137ZS-EPMC123030634072701410.1016/j.eclinm.2025.103356