Breast Cancer Drug Research Articles

Mechanisms of breast cancer metastasis: the role of extracellular matrix.

The components of the extracellular matrix (ECM) are dynamic, and they mediate mechanical signals that modulate cellular behaviors. Disruption of the ECM can induce the migration and invasion of cancer cells via specific signaling pathways and cytokines. Metastasis is a leading cause of high mortality in malignancies, and early intervention can improve survival rates. However, breast cancer is frequently diagnosed subsequent to metastasis, resulting in poor prognosis and distant metastasis poses substantial hurdles in therapy. In breast cancer, there is notable tissue remodeling of ECM proteins, with several identified as essential components for metastasis. Moreover, specific ECM molecules, receptors, enzymes, and various signaling pathways play crucial roles in breast cancer metastasis, drug treatment, and resistance. The in-depth consideration of these elements could provide potential therapeutic targets to enhance the survival rates and quality of life for breast cancer patients. This review explores the mechanisms by which alterations in the ECM contribute to breast cancer metastasis and discusses current clinical applications targeting ECM in breast cancer treatment, offering valuable perspectives for future ECM-based therapies.

A trafficking regulatory subnetwork governs αVβ6 integrin-HER2 cross-talk to control breast cancer invasion and drug resistance.

HER2 and αVβ6 integrin are independent predictors of breast cancer survival and metastasis. We identify an αVβ6/HER2 cross-talk mechanism driving invasion, which is dysregulated in drug-resistant HER2+ breast cancer cells. Proteomic analyses reveal ligand-bound αVβ6 recruits HER2 and a trafficking subnetwork, comprising guanosine triphosphatases RAB5 and RAB7A and the Rab regulator guanine nucleotide dissociation inhibitor 2 (GDI2). The RAB5/RAB7A/GDI2 functional module mediates direct cross-talk between αVβ6 and HER2, affecting receptor trafficking and signaling. Acute exposure to trastuzumab increases recruitment of the subnetwork to αVβ6, but trastuzumab resistance decouples GDI2 recruitment. GDI2, RAB5, and RAB7A cooperate to regulate migration and transforming growth factor-β activation to promote invasion. However, these mechanisms are dysregulated in trastuzumab-resistant cells. In patients, RAB5A, RAB7A, and GDI2 expression correlates with patient survival and αVβ6 expression predicts relapse following trastuzumab treatment. Thus, the RAB5/RAB7A/GDI2 subnetwork regulates αVβ6-HER2 cross-talk to drive breast cancer invasion but is subverted in trastuzumab-resistant cells to drive αVβ6-independent and HER2-independent tumor progression.

DVGEDR: a drug repositioning method based on dual-view fusion and graph enhancement mechanism in heterogeneous networks

Drug repositioning, the discovery of new therapeutic uses for existing drugs, is increasingly gaining attention as a cost-effective and high-yield drug discovery strategy. Existing methods integrate diverse biological information into heterogeneous networks, providing a comprehensive framework for understanding complex drug–disease associations, which also will introduces noise into the data and affect the performance of the model. In this paper, first, a novel drug repositioning method, namely DVGEDR, is proposed, which generates two subgraphs of the target drug–disease pair to fuse biological information and integrate drug–disease associations from two distinct perspectives: drug–disease heterogeneous network and similarity networks. Next, a Multiple Attention Graph encoder (MAGencoder) module is designed to learn subgraph features and explore relationships between entities, which also improve the interpretability of the model. Finally, a graph enhancement mechanism is devised to improve the perception of critical information of model, enabling the model to flexibly process different graph structures. Performance comparisons with baseline models on three public datasets validate the state-of-the-art performance of DVGEDR in the field of drug repositioning. In case study, DVGEDR identifies 10 new candidate drugs for breast cancer and COVID-19, demonstrating not only superior performance in experimental settings but also potential therapeutic advantages in clinical environments. Furthermore, we select two sets of instances and further analyzed the attention distribution of the different nodes in the subgraph to explain the decision process of the model.

LMAN2 Promotes Breast Cancer Tumorigenesis and Drug Resistance by Interacting With MAPK9 via Activation of the MAPK Pathway

ABSTRACTIntroductionBreast cancer (BC) is the most prevalent malignancy among women worldwide. Lectin, mannose‐binding 2 (LMAN2) is a cargo receptor engaged in the transport and sorting of glycoproteins. Despite its ubiquity, the function and underlying mechanisms of LMAN2 in BC continue to elude understanding.MethodsMultiple databases were employed to examine the expression of LMAN2 in breast cancer. Immunohistochemistry(IHC), qRT‐PCR, and Western blot were performed to quantify LMAN2 expression in BC cell lines and clinical samples. Heat map analysis and Kaplan–Meier analysis were used to analyze the correlation between LMAN2 and clinicopathological features. SiRNAs and overexpression plasmids were transfected into two BC cells to assess the effect of LMAN2 on malignant phenotypes. Coimmunoprecipitation and immunofluorescence were used to screen for potential interacting proteins. Additionally, tumor subcutaneous xenograft mode was constructed to explore tumor chemoresistance.ResultLMAN2 expression was significantly higher in BC compared to that in matched, adjacent normal tissues, and its higher expression level was correlated with worse patient prognosis. In vitro, we found that LMAN2 functions as an oncogene, promoting BC cell proliferation, cell cycle progression, invasion, and chemoresistance while preventing apoptosis. Coimmunoprecipitation and colocalization experiments confirmed the direct binding of LMAN2 to MAPK9 in BC cells. Our investigation of signaling pathways suggested that LMAN2 is involved in the regulation of the MAPK signaling pathway, utilizing this pathway to confer cisplatin resistance. Furthermore, knockdown of LMAN2 improves the sensitivity of drug‐resistant BC cells to cisplatin (DDP) in vivo.ConclusionLMAN2 was a novel diagnostic and prognostic biomarker for BC that promotes chemoresistance via interaction with MAPK9 and activation of the MAPK pathway.

SLFN12 Expression Significantly Effects the Response to Chemotherapy Drugs in Triple-Negative Breast Cancer.

Schlafen12 (SLFN12) is an intermediate human Schlafen protein shown to correlate with survivability in triple-negative breast cancer (TNBC). SLFN12 causes differential expressions of significant cancer genes, but how they change in response to chemotherapy remains unknown. Our aim is to identify the effect of chemotherapy on genes that improve TNBC outcomes and other SLFN family members following SLFN12 knockout or overexpression. We overexpressed SLFN12 using a lentiviral vector and knocked out SLFN12 (AdvShSLFN12) using a hairpin adenovirus in MDA-MB-231 TNBC cells. Cells were treated with camptothecin, paclitaxel, zoledronic acid, or carboplatin to evaluate the SLFN12 signature cancer genes associated with improved TNBC outcomes using qPCR. Additionally, cells were treated alone and in combination with AdvShSLFN12, IFN-α2 (known SLFN12 stimulator), carboplatin, and paclitaxel. After treatment, the viable cell numbers were analyzed utilizing a colorimetric crystal violet assay for cell viability. The SLFN family and SLFN12 cancer signature gene mRNA expressions were analyzed by RT-qPCR. Treating SLFN12-overexpressing TNBC cells with chemotherapy agents resulted in the differential expressions of eight cancer-related genes. Notably, GJB3 was downregulated following treatment with each chemotherapeutic drug. Inducing SLFN12 with IFN-α2 resulted in decreased cell viability and increased SLFN12 mRNA levels following treatment with paclitaxel or carboplatin. These results suggest that SLFN12 overexpression significantly affects the expressions of genes driving phenotypic changes in response to chemotherapy and influences additional SLFN family members following IFN-α2 treatment. This may contribute to improving the survival of patients with SLFN12 overexpression. Additionally, patient SLFN12 levels can be used as a factor when pursuing personalized chemotherapy treatments.

Nanomaterials: breaking the bottleneck of breast cancer drug resistance.

Drug resistance poses a significant challenge in the treatment of breast cancer. In recent years, a variety of nanomaterials have been discovered and synthesized that can selectively target tumor cells and play a crucial role in the advancement of breast cancer therapies. As our understanding of tumor heterogeneity deepens, the emerging potential of nanomaterials in addressing drug resistance has garnered considerable attention. These materials not only selectively target tumor cells but also possess unique properties that make them promising options for cancer treatment, including low toxicity, excellent biocompatibility, ease of preparation, the ability to carry antitumor drugs, and customizable surface functions. In this review, we will comprehensively summarize two key developments in breast cancer treatment: the application of antitumor drugs and nanomaterials. We will explore the mechanisms by which nanomaterials improve drug resistance in breast cancer, targeted nanotherapy strategies to mitigate this resistance, and recent research advancements in anticancer nanomaterials. This overview aims to highlight the significant role of nanomaterials in breast cancer treatment and provide a theoretical framework for identifying optimal treatment strategies in the future.

Disruption of Ferroptosis Inhibition and Immune Evasion with Tumor-Activatable Prodrug for Boosted Photodynamic/Chemotherapy Eradication of Drug-Resistant Tumors.

Breast cancer is a malignant tumor that threatens the life and health of women worldwide. As the first-line chemotherapy drug for breast cancer, doxorubicin (DOX) can inhibit the synthesis of RNA and DNA, and it exhibits strong inhibitory activity against breast cancer. However, drug-induced systemic toxicity and drug resistance can occur with DOX treatment. In this work, TSPO protein is identified as a promising target for overcoming drug resistance and we designed a novel BT-DOX/PDP conjugate to solve these problems in drug chemotherapy. It is found that BT-DOX/PDP can effectively downregulate TSPO1 protein and sensitize MCF-7/Adr to DOX. Furthermore, due to its positive charge, BT-DOX/PDP is readily loaded into puerarin (PUE), the resulting BT-DOX/PDP@PUE exhibited minimal systemic toxicity but enhanced antitumor activity in animal models, as compared with BT-DOX/PDP. This study demonstrates the advantages of combined chemotherapy and photodynamic therapy in overcoming drug resistance, which may be applied in the design of other photodynamic therapy-based conjugates to enhance antitumor therapy.

Breast cancer stem cells origins and the memory stem cells: clinical significance of biomarkers and the active therapeutic approaches

Despite recent improvements in diagnosis and treatment, breast cancer (BC) remains one of the leading causes of cancer-related deaths among women. In this complex disease, breast cancer stem cells (BCSCs) are a small but significant subset of different cancer cells with the ability to proliferate and self-renew. According to an increasing amount of studies, BCSCs are essential for breast cancer metastasis, drug resistance, and recurrence. Due to its diverse nature, BC includes numerous subtypes, each of which displays unique BCSC types and concentrations that are connected to different therapy outcomes and outcomes. Despite significant advancements in the treatment of early-stage breast cancer, there are still few effective therapy approaches for metastatic BC. The development, progression, and dissemination of BC are largely attributed to cancer stem-like cells (CSCs), which are characterized by their exceptional adaptability and self-renewal ability. An overview of the development of BCSCs, their biomarkers, clinical significance, and the mechanisms behind their behavior is the goal of the current study. The active therapy strategies being employed to address BCSCs will also be examined.

Molecular insights from structural dynamics of HER2-inhibitor complexes pave the way for new breast cancer drugs

The human epidermal growth factor receptor 2 (HER2) is closely associated with the development and progression of breast cancer, making it a critical target for therapeutic interventions. In this study, we employed a comprehensive computational drug discovery strategy to identify potential inhibitors of HER2. Our approach combined virtual screening, re-docking procedures, molecular dynamics (MD) simulations, and free energy landscape analysis using principal component analysis (PCA). From the extensive PubChem library, we initially screened 733 compounds for their binding potential to HER2, using docking scores as a primary filter. These scores ranged notably from −11.172 to −7.028 kcal/mol, indicating substantial binding capacities. Following this screening, we selected four promising compounds (PubChem CID 166029206, 166544027, 21031510, and 11712721) along with a control compound (70I) for in-depth analysis. Utilizing the Amber software suite for MD simulations, we conducted 200-nanosecond simulations to assess the interactions and binding efficiencies of these selected compounds with HER2. We analysed the molecular interactions through various parameters such as root mean square deviation (RMSD), root mean square fluctuation (RMSF), and hydrogen bond formation patterns, free binding energy calculations. The PCA-based free energy landscape analysis revealed that these compounds consistently occupied a distinct low-energy basin, indicating their high stability and strong binding affinity for the HER2. This detailed analysis provided insights into the stability and conformational dynamics of these potential inhibitors when bound to the HER2. Our findings pave the way for further experimental validation and development of these compounds as therapeutic agents in breast cancer treatment.

Capivasertib augments chemotherapy via Akt inhibition in preclinical small cell lung cancer models.

Small cell lung cancer (SCLC) is a highly aggressive type of lung cancer for which platinum-based chemotherapy is the standard of care. Despite an initial response to this therapy, patients eventually develop resistance to the chemotherapy. To investigate the potential of capivasertib, an approved drug for advanced breast cancer, to enhance the efficacy of cisplatin in preclinical SCLC models and explore the underlying mechanisms. SCLC cell lines were treated with capivasertib and cisplatin, alone or in combination, to assess cell viability, proliferation, colony formation, and apoptosis. Next, capivasertib's effects, alone and combined with cisplatin, were evaluated in an SCLC mouse model. Mechanistic studies focused on Akt and MYC signaling, with constitutively active Akt overexpression used to assess its role. Capivasertib is active against a panel of SCLC cell lines regardless of cellular origin and genetic profiling with IC50 at a clinically achievable range. Particularly, capivasertib inhibits proliferation and anchorage-independent colony formation and induces apoptosis in SCLC cells. It significantly augments cisplatin's inhibitory effects in all tested cell lines. Importantly, capivasertib at a non-toxic dose is effective in delaying SCLC growth in mice and its combination with cisplatin achieves nearly complete tumor growth inhibition. Mechanistic studies confirm that capivasertib inhibits Akt and MYC signaling, and furthermore, that overexpression of constitutively active Akt reversed anti-SCLC activity of capivasertib. Our work is the first to reveal that Akt inhibition can augment chemotherapy in SCLC, and capivasertib is a useful addition to the treatment armamentarium for SCLC.

Liposomes and Their Therapeutic Applications in Enhancing Psoriasis and Breast Cancer Treatments.

Psoriasis and breast cancer are two examples of diseases where associated inflammatory pathways within the body's immune system are implicated. Psoriasis is a complex, chronic and incurable inflammatory skin disorder that is primarily recognized by thick, scaly plaques on the skin. The most noticeable pathophysiological effect of psoriasis is the abnormal proliferation of keratinocytes. Breast cancer is currently the most diagnosed cancer and the leading cause of cancer-related death among women globally. While treatments targeting the primary tumor have significantly improved, preventing metastasis with systemic treatments is less effective. Nanocarriers such as liposomes and lipid nanoparticles have emerged as promising drug delivery systems for drug targeting and specificity. Advances in technologies and drug combinations have emerged to develop more efficient lipid nanocarriers to include more than one drug in combinational therapy to enhance treatment outcomes and/or relief symptoms for better patients' quality of life. Although there are FDA-approved liposomes with anti-cancer drugs for breast cancer, there are still unmet clinical needs to reduce the side effects associated with those nanomedicines. Hence, combinational nano-therapy may eliminate some of the issues and challenges. Furthermore, there are no nanomedicines yet clinically available for psoriasis. Hence, this review will focus on liposomes encapsulated single and/or combinational therapy to augment treatment outcomes with an emphasis on the effectiveness of combinational therapy within liposomal-based nanoparticulate drug delivery systems to tackle psoriasis and breast cancer. This review will also include an overview of both diseases, challenges in delivering drug therapy and the roles of nanomedicines as well as psoriasis and breast cancer models used for testing therapeutic interventions to pave the way for effective in vivo testing prior to the clinical trials.

Transglutaminase 2 in breast cancer metastasis and drug resistance.

Transglutaminase 2 (TG2) is a widely distributed multifunctional protein with various enzymatic and non-enzymatic activities. It is becoming increasingly evident that high levels of TG2 in tumors induce the occurrence of epithelial to mesenchymal transition (EMT) and the acquisition of stem cell-like phenotypes, promoting tumor metastasis and drug resistance. By regulating intracellular and extracellular signaling pathways, TG2 promotes breast cancer metastasis to lung, brain, liver and bone, as well as resistance to various chemotherapy drugs including docetaxel, doxorubicin, platinum and neratinib. More importantly, recent studies described the involvement of TG2 in PD-1/PD-L1 inhibitors resistance. An in-depth understanding of the role that TG2 plays in the progression of metastasis and drug resistance will offer new therapeutic targets for breast cancer treatment. This review covers the extensive and rapidly growing field of the role of TG2 in breast cancer. Based on the role of TG2 in EMT, we summarize TG2-related signaling pathways in breast cancer metastasis and drug resistance and discuss TG2 as a therapeutic target.

Design, Synthesis, and In-Silico Analysis of Thiazole-Embedded Schiff Base Derivatives for Breast Cancer Therapeutic Potential

Thiazole-derived Schiff base compounds possess significant pharmacological properties, influencing various enzymes in metabolic pathways and exhibiting antibacterial, antifungal, anti-inflammatory, antioxidant, and antiproliferative activities. This study delves into the synthesis, characterization, and in-silico analysis of ten thiazole-embedded Schiff base derivatives (TZ1-10), benchmarking them against five Food and Drug Administration (FDA)-approved breast cancer drugs. Molecular docking against multiple therapeutic targets related to fatty acid synthase and cell proliferation (PDB IDs: 4FX3, 4OAR, 3NUP, and 3ERT) alongside ADME and Lipinski rule assessments were conducted. Compounds TZ6 and TZ8 emerged as promising candidates with docking scores of -8.0 kcal/mol and -8.2 kcal/mol respectively against the 4FX3 protein. These findings contribute to a deeper understanding of thiazole-embedded Schiff base derivatives, showcasing their potential for future medicinal and scientific applications.

PH-responsive magnetic CuFe2O4-PMAA nanogel conjugated with amino-modified lignin for controlled breast cancer drug delivery

In this study, a novel magnetic and pH-responsive nanocarrier was developed, incorporating both natural and synthetic polymers, for delivering curcumin (CUR) to breast cancer cells. For this purpose, CuFe2O4@poly(methacrylic acid) (CuFe2O4@PMAA) nanogel was developed and conjugated with amino-modified lignin (Lignin-adipic acid dihydrazide conjugate, Lig-ADH) to achieve the CuFe2O4@PMAA@Lig-ADH nanocarrier. The morphology, structure, and physical properties of the synthesized nanomaterials were examined using a range of techniques, including transmission electron microscopy (TEM), field emission scanning electron microscopy (FESEM), Fourier transform infrared (FT-IR) spectroscopy, X-ray diffraction (XRD), energy dispersive X-ray (EDX), and vibrating sample magnetometer (VSM). The synthesized nanocarrier exhibited a spherical shape, with an average diameter of approximately 15 nm, and demonstrated good magnetic responsiveness. Moreover, the in vitro drug release was found to be pH-dependent, with an increased release rate in acidic conditions. To evaluate cytotoxicity, the survival of MCF-7 cells was measured using the MTT assay for 24 h. Notably, the synthesized CuFe2O4@PMAA@Lig-ADH@CUR and CUR exhibited significant cytotoxic effects, effectively eliminating MCF-7 cells with IC50 values of 39.80 µg/mL and 4.27 µg/mL, respectively. Also, the significant intracellular uptake of NPs was confirmed by FITC and DAPI staining after 4 h. This research highlighted the potential of CuFe2O4@PMAA@Lig-ADH@CUR as a highly effective nano-delivery system and demonstrated a straightforward method for utilizing renewable lignin.

Next generation of drugs in breast cancer

Next generation of drugs in breast cancer

Assessing the real-world effectiveness of 8 major metastatic breast cancer drugs using target trial emulation

BackgroundDemonstration of trial emulation ability to benchmark randomised controlled trials (RCTs) from real-world data (RWD) is required to increase confidence in the use of routinely collected data for decision making in oncology. MethodsTo assess the frequency with which emulation findings align with RCTs regarding effect size on overall survival (OS) in metastatic breast cancer (MBC), 8 of 13 pre-selected pivotal RCTs in MBC were emulated using data from 32,598 patients enrolled in the French ESME-MBC cohort between January 1, 2008 and December 31, 2021. Adjustment methods and confounders were selected a priori for each emulation; stabilized weight was the reference method to mitigate confounding. Concordance in OS hazard ratios with associated 95 % confidence intervals between RCTs and emulations were assessed used predefined metrics based on statistical significance, estimates, and standardized differences. ResultsThe effect sizes were consistent with RCT results in 7 out of the 8 emulations; 4 emulations achieved full statistical significance agreement; 5 emulations had a point estimate included in the RCT CI (estimate agreement); 6 emulations reported no significant differences between RCT and emulation (standardized difference agreement). Discrepancies related to residual confounders and significant shifts in prescription practices post-drug approval may arise in some cases. ConclusionTarget trial emulation from RWD combined with appropriate adjustment can provide conclusions similar to RCTs in MBC. In oncology, this methodology offers opportunities for confirming the impact on long-term survival, for expanding indications in patients excluded from RCTs and for comparative effectiveness in single-arm trials using external control arms.

Investigating the availability, affordability, and market dynamics of innovative oncology drugs in Morocco: an original report.

The cost of cancer drugs presents a significant challenge to accessibility of treatment worldwide. Projections indicate that by 2040, two-thirds of cancer cases will occur in low- and middle- income countries. Paradoxically, despite this impending burden, LMICs command less than 5% share of global resources for treating cancer. Morocco, like many LMICs, faces significant obstacles in providing innovative cancer treatments to its population. Firstly, we aimed to conduct an original research investigating the availability and affordability of innovative cancer drugs in Morocco. Secondly, we sought to review the broader market dynamics, pricing, and reimbursement policies in the country. For the first objective, we identified a preliminary list of medicines approved for oncological indications in the Moroccan market based on resources from ANAM (National Agency for Health Insurance), pharmacy regulators, and online resources that compile information on approved medicines. For the second objective, we exhaustively reviewed the regulatory documents, legal texts and grey literature reports. All the informations were examined by pharma delegates and local experts. As of January 2024, Morocco has 39 innovative anticancer medicines with market authorization. 30% of these drugs were approved after 2020. The majority of approved drugs were for breast, lung, colorectal, and prostate cancer. The period between FDA approval and entry into the Moroccan market ranges from 2 to 7years, with a median of 3years for breast cancer drugs and 7years for more expensive drugs like Olaparib and Osimertinib. 22 out of the 39 drugs are not reimbursed, with an average reimbursement time of 4years. Compared to prices in France, the most notable pricing disparities concern immunotherapy agents, priced 600 to 900 euros lower in France, while drugs like Pazopanib and Erlotinib cost 50% less in Morocco. Our study reveals significant disparities in the availability and affordability of innovative cancer drugs in Morocco. Regulatory hurdles, importation challenges, and pricing strategies contribute to this inequitable landscape. Addressing systemic barriers, fostering collaborations between stakeholders, and adopting a value-based pricing approach are imperative steps toward ensuring equitable access to high-quality interventions for patients, regardless of their geographical location.

Engineered Age-Mimetic Breast Cancer Models Reveal Differential Drug Responses in Young and Aged Microenvironments.

Aging is one of the most significant risk factors for breast cancer. With the growing interests in the alterations of the aging breast tissue microenvironment, it has been identified that aging is related to tumorigenesis, invasion, and drug resistance. However, current pre-clinical disease models often neglect the impact of aging and sometimes result in worse clinical outcomes. In this study, we utilized aged animal-generated materials to create and validate a novel age-mimetic breast cancer model that generates an aging microenvironment for cells and alters cells towards a phenotype found in the aged environment. Furthermore, we utilized the age-mimetic models for 3D breast cancer invasion assessment and high-throughput screening of over 700 drugs in the FDA-approved drug library. We identified 36 potential effective drug targets and 34 potential drug targets with different drug responses in different age groups, demonstrating the potential of this age-mimetic breast cancer model for further in-depth breast cancer studies and drug development.

Prediction of pathological complete response to chemotherapy for breast cancer using deep neural network with uncertainty quantification.

The I-SPY 2 trial is a national-wide, multi-institutional clinical trial designed to evaluate multiple new therapeutic drugs for high-risk breast cancer. Previous studies suggest that pathological complete response (pCR) is a viable indicator of long-term outcomes of neoadjuvant chemotherapy for high-risk breast cancer. While pCR can be assessed during surgery after the chemotherapy, early prediction of pCR before the completion of the chemotherapy may facilitate personalized treatment management to achieve an improved outcome. Notably, the acquisition of dynamic contrast-enhanced magnetic resonance (DCEMR) images at multiple time points during the I-SPY 2 trial opens up the possibility of achieving early pCR prediction. In this study, we investigated the feasibility of the early prediction of pCR to neoadjuvant chemotherapy using multi-time point DCEMR images and clinical data acquired in the I-SPY2 trial. The prediction uncertainty was also quantified to allow physicians to make patient-specific decisions on treatment plans based on the level of associated uncertainty. The dataset used in our study included 624 patients with DCEMR images acquired at 3 time points before the completion of the chemotherapy: pretreatment (T0), after 3 cycles of treatment (T1), and after 12 cycles of treatment (T2). A convolutional long short-term memory (LSTM) network-based deep learning model, which integrated multi-time point deep image representations with clinical data, including tumor subtypes, was developed to predict pCR. The performance of the model was evaluated via the method of nested 5-fold cross validation. Moreover, we also quantified prediction uncertainty for each patient through test-time augmentation. To investigate the relationship between predictive performance and uncertainty, the area under the receiver operating characteristic curve (AUROC) was assessed on subgroups of patients stratified by the uncertainty score. By integrating clinical data and DCEMR images obtained at three-time points before treatment completion, the AUROC reached 0.833 with a sensitivity of 0.723 and specificity of 0.800. This performance was significantly superior (p<0.01) to models using only images (AUROC=0.706) or only clinical data (AUROC=0.746). After stratifying the patients into eight subgroups based on the uncertainty score, we found that group #1, with the lowest uncertainty, had a superior AUROC of 0.873. The AUROC decreased to 0.637 for group #8, which had the highest uncertainty. The results indicate that our convolutional LSTM network-based deep learning model can be used to predict pCR earlier before the completion of chemotherapy. By combining clinical data and multi-time point deep image representations, our model outperforms models built solely on clinical or image data. Estimating prediction uncertainty may enable physicians to prioritize or disregard predictions based on their associated uncertainties. This approach could potentially enhance the personalization of breast cancer therapy.

P91-1 Efficacy of tamoxifen as a serm drugs in combined with other drugs for metastatic breast cancer: a systematic review

P91-1 Efficacy of tamoxifen as a serm drugs in combined with other drugs for metastatic breast cancer: a systematic review