RESUMO
BACKGROUND: Breast cancer (BC) has particular characteristics in young women, with diagnosis at more advanced stages, a poorer prognosis and highly aggressive tumors. In NeoFit, we will use an activity tracker to identify and describe various digital profiles (heart rate, physical activity, and sleep patterns) in women below the age of 45 years on neoadjuvant chemotherapy for BC. METHODS: NeoFit is a prospective, national, multicenter, single-arm open-label study. It will include 300 women below the age of 45 years treated with neoadjuvant chemotherapy for BC. Participants will be asked to wear a Withing Steel HR activity tracker round the clock for 12 months. The principal assessments will be performed at baseline, at the end of neoadjuvant chemotherapy and at 12 months. We will evaluate clinical parameters, such as toxicity and the efficacy of chemotherapy, together with quality of life, fatigue, and parameters relating to lifestyle and physical activity. The women will complete REDCap form questionnaires via a secure internet link. DISCUSSION: In this study, the use of an activity tracker will enable us to visualize changes in the lifestyle of young women on neoadjuvant chemotherapy for BC, over the course of a one-year period. This exploratory study will provide crucial insight into the digital phenotypes of young BC patients on neoadjuvant chemotherapy and the relationship between these phenotypes and the toxicity and efficacy of treatment. This trial will pave the way for interventional studies involving sleep and physical activity interventions. TRIAL REGISTRATION: Clinicaltrials.gov identifier: NCT05011721 . Registration date: 18/08/2021.
Assuntos
Neoplasias da Mama , Terapia Neoadjuvante , Protocolos de Quimioterapia Combinada Antineoplásica/efeitos adversos , Neoplasias da Mama/patologia , Feminino , Humanos , Masculino , Estudos Multicêntricos como Assunto , Terapia Neoadjuvante/métodos , Estudos Prospectivos , Qualidade de VidaRESUMO
Triple-negative breast cancer (TNBC) is a rare cancer, characterized by high metastatic potential and poor prognosis, and has limited treatment options. The current standard of care in nonmetastatic settings is neoadjuvant chemotherapy (NACT), but treatment efficacy varies substantially across patients. This heterogeneity is still poorly understood, partly due to the paucity of curated TNBC data. Here we investigate the use of machine learning (ML) leveraging whole-slide images and clinical information to predict, at diagnosis, the histological response to NACT for early TNBC women patients. To overcome the biases of small-scale studies while respecting data privacy, we conducted a multicentric TNBC study using federated learning, in which patient data remain secured behind hospitals' firewalls. We show that local ML models relying on whole-slide images can predict response to NACT but that collaborative training of ML models further improves performance, on par with the best current approaches in which ML models are trained using time-consuming expert annotations. Our ML model is interpretable and is sensitive to specific histological patterns. This proof of concept study, in which federated learning is applied to real-world datasets, paves the way for future biomarker discovery using unprecedentedly large datasets.