ABSTRACT
OBJECTIVE: Breast cancer has become the most prevalent malignant tumor in women, and the occurrence of distant metastasis signifies a poor prognosis. Utilizing predictive models to forecast distant metastasis in breast cancer presents a novel approach. This study aims to utilize readily available clinical data and advanced machine learning algorithms to establish an accurate clinical prediction model. The overall objective is to provide effective decision support for clinicians. METHODS: Data from 239 patients from two centers were analyzed, focusing on clinical blood biomarkers (tumor markers, liver and kidney function, lipid profile, cardiovascular markers). Spearman correlation and the least absolute shrinkage and selection operator regression were employed for feature dimension reduction. A predictive model was built using LightGBM and validated in training, testing, and external validation cohorts. Feature importance correlation analysis was conducted on the clinical model and the comprehensive model, followed by univariate and multivariate regression analysis of these features. RESULTS: Through internal and external validation, we constructed a LightGBM model to predict de novo bone metastasis in newly diagnosed breast cancer patients. The area under the receiver operating characteristic curve values of this model in the training, internal validation test, and external validation test1 cohorts were 0.945, 0.892, and 0.908, respectively. Our validation results indicate that the model exhibits high sensitivity, specificity, and accuracy, making it the most accurate model for predicting bone metastasis in breast cancer patients. Carcinoembryonic Antigen, creatine kinase, albumin-globulin ratio, Apolipoprotein B, and Cancer Antigen 153 (CA153) play crucial roles in the model's predictions. Lipoprotein a, CA153, gamma-glutamyl transferase, α-Hydroxybutyrate dehydrogenase, alkaline phosphatase, and creatine kinase are positively correlated with breast cancer bone metastasis, while white blood cell ratio and total cholesterol are negatively correlated. CONCLUSION: This study successfully utilized clinical blood biomarkers to construct an artificial intelligence model for predicting distant metastasis in breast cancer, demonstrating high accuracy. This suggests potential clinical utility in predicting and identifying distant metastasis in breast cancer. These findings underscore the potential prospect of developing economically efficient and readily accessible predictive tools in clinical oncology.
Subject(s)
Artificial Intelligence , Biomarkers, Tumor , Bone Neoplasms , Breast Neoplasms , Humans , Breast Neoplasms/pathology , Female , Bone Neoplasms/secondary , Bone Neoplasms/blood , Middle Aged , Biomarkers, Tumor/blood , Adult , Aged , ROC Curve , Machine Learning , Predictive Value of TestsABSTRACT
Breast cancer metastasis significantly impacts women's health globally. This study aimed to construct predictive models using clinical blood markers and ultrasound data to predict distant metastasis in breast cancer patients, ensuring clinical applicability, cost-effectiveness, relative non-invasiveness, and accessibility of these models. Analysis was conducted on data from 416 patients across two centers, focusing on clinical blood markers (tumor markers, liver and kidney function indicators, blood lipid markers, cardiovascular biomarkers) and maximum lesion diameter from ultrasound. Feature reduction was performed using Spearman correlation and LASSO regression. Two models were built using LightGBM: a clinical model (using clinical blood markers) and a combined model (incorporating clinical blood markers and ultrasound features), validated in training, internal test, and external validation (test1) cohorts. Feature importance analysis was conducted for both models, followed by univariate and multivariate regression analyses of these features. The AUC values of the clinical model in the training, internal test, and external validation (test1) cohorts were 0.950, 0.795, and 0.883, respectively. The combined model showed AUC values of 0.955, 0.835, and 0.918 in the training, internal test, and external validation (test1) cohorts, respectively. Clinical utility curve analysis indicated the combined model's superior net benefit in identifying breast cancer with distant metastasis across all cohorts. This suggests the combined model's superior discriminatory ability and strong generalization performance. Creatine kinase isoenzyme (CK-MB), CEA, CA153, albumin, creatine kinase, and maximum lesion diameter from ultrasound played significant roles in model prediction. CA153, CK-MB, lipoprotein (a), and maximum lesion diameter from ultrasound positively correlated with breast cancer distant metastasis, while indirect bilirubin and magnesium ions showed negative correlations. This study successfully utilized clinical blood markers and ultrasound data to develop AI models for predicting distant metastasis in breast cancer. The combined model, incorporating clinical blood markers and ultrasound features, exhibited higher accuracy, suggesting its potential clinical utility in predicting and identifying breast cancer distant metastasis. These findings highlight the potential prospects of developing cost-effective and accessible predictive tools in clinical oncology.
Subject(s)
Biomarkers, Tumor , Breast Neoplasms , Neoplasm Metastasis , Humans , Breast Neoplasms/blood , Breast Neoplasms/pathology , Breast Neoplasms/diagnostic imaging , Female , Biomarkers, Tumor/blood , Middle Aged , Adult , Ultrasonography/methods , AgedABSTRACT
Objective: This study aims to develop an artificial intelligence model utilizing clinical blood markers, ultrasound data, and breast biopsy pathological information to predict the distant metastasis in breast cancer patients. Methods: Data from two medical centers were utilized, Clinical blood markers, ultrasound data, and breast biopsy pathological information were separately extracted and selected. Feature dimensionality reduction was performed using Spearman correlation and LASSO regression. Predictive models were constructed using LR and LightGBM machine learning algorithms and validated on internal and external validation sets. Feature correlation analysis was conducted for both models. Results: The LR model achieved AUC values of 0.892, 0.816, and 0.817 for the training, internal validation, and external validation cohorts, respectively. The LightGBM model achieved AUC values of 0.971, 0.861, and 0.890 for the same cohorts, respectively. Clinical decision curve analysis showed a superior net benefit of the LightGBM model over the LR model in predicting distant metastasis in breast cancer. Key features identified included creatine kinase isoenzyme (CK-MB) and alpha-hydroxybutyrate dehydrogenase. Conclusion: This study developed an artificial intelligence model using clinical blood markers, ultrasound data, and pathological information to identify distant metastasis in breast cancer patients. The LightGBM model demonstrated superior predictive accuracy and clinical applicability, suggesting it as a promising tool for early diagnosis of distant metastasis in breast cancer.
ABSTRACT
IKKα has been shown to be responsible of multiple pro-tumorigenic functions and therapy resistance independent of canonical NF-κB, but its role in acquired chemotherapy resistance in breast cancer remains unclarified. In this study, we obtained pre-treatment biopsy and post-treatment mastectomy specimens from a retrospective cohort of triple-negative breast cancer (TNBC) patients treated with neoadjuvant chemotherapy(NAC) (n = 43). Immunohistochemical methods were used to detect the expression of IKKα before and after NAC, and the relationship between IKKα and the pathologic response to NAC was examined. In addition, we developed a new ADR-resistant MDA-MB-231 cell line(MDA-MB-231/ADR) and analyzed these cells for changes in IKKα expression, the role and mechanisms of the increased IKKα in promoting drug resistance were determined in vitro and in vivo. We demonstrated that the expression of IKKα in residual TNBC tissues after chemotherapy was significantly higher than that before chemotherapy, and was positively correlated with lower pathological reaction. IKKα expression was significantly higher in ADR-resistant TNBC cells than in ADR-sensitive cells, IKKα knockdown results in apoptotic cell death of chemoresistant cells upon drug treatment. Moreover, IKKα knockdown promotes chemotherapeutic drug-induced tumor cell death in an transplanted tumor mouse model. Functionally, we demonstrated that IKKα knockdown significantly upregulated the expression of cleaved caspase 3 and Bax and inhibited the expression of Bcl-2 upon ADR treatment. Our findings highlighted that IKKα exerts an important and previously unknown role in promoting chemoresistance in TNBC, combining IKKα inhibition with chemotherapy may be an effective strategy to improve treatment outcome in chemoresistant TNBC patients.
Subject(s)
Antineoplastic Agents , Triple Negative Breast Neoplasms , Humans , Animals , Mice , Triple Negative Breast Neoplasms/drug therapy , Triple Negative Breast Neoplasms/genetics , Triple Negative Breast Neoplasms/metabolism , I-kappa B Kinase/metabolism , Doxorubicin/pharmacology , Doxorubicin/therapeutic use , Retrospective Studies , Mastectomy , Apoptosis , Antineoplastic Agents/pharmacology , Cell Line, Tumor , Drug Resistance, NeoplasmABSTRACT
This work aimed to observe the effects of short hairpin RNA (shRNA)-silenced FBI-1 (factor that binds to the inducer of short transcripts of human immunodeficiency virus-1) on proliferation and apoptosis of triple-negative breast cancer cell line MDA-MB-231. qRT-PCR and Western blot analysis were applied to detect the mRNA and/or protein expression of FBI-1, Bcl-2, Bax, cleaved-Caspase 3 and Survivin. RNA interference method was used to silence FBI-1 expression in MDA-MB-231 cells. CCK-8 and colony formation assay were employed to detect the cell proliferation. Flow cytometry was employed for examining cell apoptosis. In vivo tumorigenicity of MDA-MB-231 cells was detected by tumor transplantation in nude mice. The results showed that the mRNA and protein expressions of FBI-1 were higher in MDA-MB-231 cells compared with those in normal human mammary epithelial cells MCF-10A. FBI-1 gene silencing inhibited proliferation and induced apoptosis of MDA-MB-231 cells in vitro, together with decreased Bcl-2 and Survivin protein expression, increased Bax protein expression and activated Caspase 3. Moreover, FBI-1 gene silencing inhibited the tumorigenesis of MDA-MB-231 cells in vivo. These results suggest that silencing of FBI-1 gene inhibits proliferation, induces apoptosis and suppresses the tumorigenesis of MDA-MB-231 cells.
Subject(s)
Apoptosis , Cell Proliferation , DNA-Binding Proteins/genetics , RNA Interference , Transcription Factors/genetics , Triple Negative Breast Neoplasms/genetics , Animals , Caspase 3/metabolism , Cell Line, Tumor , Humans , Mice , Mice, Nude , Proto-Oncogene Proteins c-bcl-2/metabolism , RNA, Messenger , RNA, Small Interfering , Survivin/metabolism , Triple Negative Breast Neoplasms/pathology , bcl-2-Associated X Protein/metabolismABSTRACT
BACKGROUND: A new diagnostic and prognostic biomarker may be of value in cancer diseases. Our study aimed to evaluate the CDKN1A/p21 and TGFBR2 level measurable in a cohort of patients with breast cancer after mastectomy, and to confirm their suitability to serve as prognostic biomarkers of the cancer. METHODS: The expression levels of CDKN1A/p21 and TGFBR2 were detected by reverse transcription-PCR (RT-PCR), western blot assay and immunohistochemical staining for 65 primary tumor samples and paired adjacent noncancerous breast tissues. Their relations to clinicopathologic parameters and to the prognosis of patients with breast cancer were analyzed. RESULTS: We found the mRNA and protein expression levels of CDKN1A/p21 were significantly upregulated in breast cancer tissues compared with adjacent nontumorous breast tissues. Increased CDKN1A/p21 expression showed a significant correlation with larger tumor size (P=0.014), higher tumor dedifferentiation grade (P=0.021), lymph node metastasis (P=0.019) and a shorter disease-free survival (P=0.044). Contrarily, the expression levels of TGFBR2 mRNA and protein were significantly decreased in breast cancer tissues compared with adjacent nontumorous breast tissues. Underexpression of TGFBR2 in breast cancer was correlated with larger tumor size (P=0.034), lymph node metastasis (P=0.039) and a shorter disease-free survival (P=0.035). Statistical analysis suggested that there was no significant association between CDKN1A/p21 and TGFBR2 expression. CONCLUSIONS: in summary, our results suggested that high CDKN1A/p21 and low TGFBR2 expression was closely correlated with adverse pathological parameters and poor prognosis in breast cancer. Both CDKN1A/p21 and TGFBR2 are presented as possible candidates for breast cancer biomarkers.
Subject(s)
Biomarkers, Tumor/analysis , Breast Neoplasms/pathology , Cyclin-Dependent Kinase Inhibitor p21/biosynthesis , Protein Serine-Threonine Kinases/biosynthesis , Receptors, Transforming Growth Factor beta/biosynthesis , Adult , Aged , Blotting, Western , Breast Neoplasms/metabolism , Breast Neoplasms/mortality , Cyclin-Dependent Kinase Inhibitor p21/analysis , Disease-Free Survival , Female , Humans , Immunohistochemistry , Kaplan-Meier Estimate , Middle Aged , Prognosis , Proportional Hazards Models , Protein Serine-Threonine Kinases/analysis , Receptor, Transforming Growth Factor-beta Type II , Receptors, Transforming Growth Factor beta/analysis , Reverse Transcriptase Polymerase Chain ReactionABSTRACT
BACKGROUND: Immunohistochemical (IHC) expression of Ki67 has been identified as a prognostic and predictive marker in hormone receptor (HR)-positive breast cancer, however, there is little evidence of the association of Ki67 with prognosis in HR-negative patients. We aimed to assess the benefit of Ki67 assessment in HR-negative breast cancers after neoadjuvant chemotherapy (NAC). METHODS: In the present study, a total of 183 HR-negative breast cancer patients with Stage II to III that treated with anthracycline and/or taxane-based neoadjuvant chemotherapy between 2004 and 2011 were retrospectively analyzed. Endocrine therapy and trastuzumab was not administered to any patients in this study. Clinical and pathological features of the patients with breast cancer were retrieved from the hospital records. Predictive factors for NAC response and survival were analyzed. RESULTS: Of the 183 patients, 122 (66.6%) were HR- HER2+, and 61 (33.3%) were triple-negative. The clinical response rates were similar across breast cancer subtype. Patients whose tumors contained high Ki67 expression effectively responded to NAC. Ki67 labeling index was a predictive marker for pathologic complete response (pCR). Ki67 expression showed a positive correlation with HER2 status, tumor size, lymph node status, lymphovascular invasion and tumor grade. Furthermore, high Ki67 expression in post-treatment tumors was strongly correlated with poor disease-free survival (DFS), but no correlation of Ki-67 expression with overall survival (OS) was observed. CONCLUSIONS: Our results suggest that Ki67 expression in HR-negative breast cancer may improve the assessment of pathological response after NAC, and Ki67 score in residual tumor was an independent prognosticator for DFS in the HR-negative breast cancer patients.
Subject(s)
Antineoplastic Combined Chemotherapy Protocols/therapeutic use , Breast Neoplasms/chemistry , Breast Neoplasms/drug therapy , Ki-67 Antigen/analysis , Neoadjuvant Therapy , Receptors, Estrogen/analysis , Receptors, Progesterone/analysis , Adult , Aged , Anthracyclines/administration & dosage , Breast Neoplasms/mortality , Breast Neoplasms/pathology , Chemotherapy, Adjuvant , Disease-Free Survival , Female , Humans , Immunohistochemistry , Kaplan-Meier Estimate , Middle Aged , Neoplasm Grading , Neoplasm Staging , Predictive Value of Tests , Proportional Hazards Models , Receptor, ErbB-2/analysis , Retrospective Studies , Taxoids/administration & dosage , Time Factors , Treatment Outcome , Triple Negative Breast Neoplasms/chemistry , Triple Negative Breast Neoplasms/drug therapy , Triple Negative Breast Neoplasms/mortality , Triple Negative Breast Neoplasms/pathology , Tumor BurdenABSTRACT
BACKGROUND: To investigate the prognostic value of hormone receptor (HR) status conversion after neoadjuvant chemotherapy (NAC) in patients with primary breast cancer. METHODS: 267 stage II-III breast cancer patients treated with NAC who had residual disease in the breast after NAC were retrospectively studied. The patients were divided into four groups based on the HR status: Group A, patients with HR-positive both before and after NAC; Group B, patients with HR status positive-to-negative change; Group C, patients with HR status negative-to-positive change; Group D, patients with HR-negative both before and after NAC. Patients with positive HR status (regardless of before or after NAC) were treated with adjuvant endocrine therapy, and a survival analysis was performed. RESULTS: In total, 15.7% of patients had HR status change after NAC. progression-free survival (PFS) in Group A was similar to that in Group C (hazard ratio, 1.16; P = 0.652), but that in Group B was significantly lesser than that in Group A (hazard ratio, 6.88; P = 0.001), and that in Group C was significantly longer than that in Group D (hazard ratio, 6.88; P = 0.001). A similar pattern of results was obtained for overall survival (OS). CONCLUSIONS: The switch of HR status after NAC is remarkable for breast cancer. An HR switch may identify patients who would benefit from adjuvant endocrine therapy and impact the long-term outcome.
Subject(s)
Breast Neoplasms/drug therapy , Carcinoma/drug therapy , Receptor, ErbB-2/biosynthesis , Receptors, Estrogen/biosynthesis , Receptors, Progesterone/biosynthesis , Adult , Antineoplastic Combined Chemotherapy Protocols/therapeutic use , Breast Neoplasms/metabolism , Breast Neoplasms/mortality , Carcinoma/metabolism , Carcinoma/mortality , Disease-Free Survival , Female , Humans , Immunohistochemistry , Kaplan-Meier Estimate , Middle Aged , Neoadjuvant Therapy , Prognosis , Proportional Hazards Models , Retrospective StudiesABSTRACT
A standard systemic therapy for patients with human epidermal growth factor receptor 2 (HER2)-negative advanced breast cancer (ABC) is yet to be identified. Sorafenib has been developed for the treatment of solid tumors, including breast cancer, as an oral multikinase inhibitor with antiangiogenic and antiproliferative activity. The aim of the present study was to assess the efficacy and safety of sorafenib in patients with HER2-negative ABC by performing a meta-analysis. A literature search was applied to databases, including PubMed, EMBASE, the Cochrane Library Databases, American Society of Clinical Oncology and the European Society for Medical Oncology, with the search terms 'advanced breast cancer' and 'sorafenib' and relevant studies were selected for analysis. The data extracted from the selected studies included progression-free survival (PFS), time to progression (TTP), overall survival (OS) and overall response rate (ORR). Major adverse events (AEs) were also analyzed. A total of four randomized controlled trials containing 844 cases were identified. Combined results revealed that when compared with chemotherapy (or with anti-hormone receptor therapy) alone, sorafenib-based therapy significantly increased the PFS [hazard ratio (HR), 0.78; 95% confidence interval (CI), 0.54-1.02] and TTP (HR, 0.74; 95% CI, 0.50-0.97), but not the OS (HR, 0.95; 95% CI, 0.75-1.15) and ORR (relative risk, 1.19; 95% CI, 1.01-1.39). In addition, the incidence of grade 3/4 AEs, including hand-foot skin syndrome, anemia, fatigue, rash and stomatitis, were significantly increased in patients that received sorafenib-based therapy. Therefore, the results from the current meta-analysis indicated that sorafenib-based therapy improved the PFS and TTP in patients with HER2-negative ABC, but not the OS and ORR. In addition, combination treatment was associated with increased toxicities and frequently required dose reductions.
ABSTRACT
BACKGROUND: Iodine 125 ((125)I) seed irradiation is an effective non-surgical treatment for unresectable hepatocellular carcinoma (HCC) patients. However, the safety and tolerability of (125)I seed sequential irradiation therapy remain unclear, there is no unified standard of brachytherapy radiation dose, and further study on the basic radiobiology of continuous rate irradiation is necessary. METHODS: Forty Kunming-mice (KM-mice, China) were injected with suspensions of human hepatocellular carcinoma cells (H22) to create an animal model and mimic (125)I seed implantation. The survival rates of mice, curative effect, pathological impairments including apoptosis and necrosis were investigated. The mice were randomly divided into four groups, A, B, C and D. In group A, 0.78 mCi (125)I seeds were implanted into the tumor focus. In groups B and C, 0.58 mCi and 0.38 mCi (125)I seeds were inserted at the same location, respectively. Group D was a control group, without any treatment. After 28 days of therapy, the survival rates and the tumor size were measured, and pathological impairments was measured by light or electron microscopy. RESULTS: The tumor volume inhibition rate was 68.21% ± 3.21%, 51.38% ± 4.96%, and 35.71% ± 2.79% after 0.78 mCi, 0.58 mCi, and 0.38 mCi (125)I seeds irradiation, respectively. However, radiation-related side effects were also observed in the high-dose group. Pathological results showed that radiation effect was closely associated with radiation dose, as the increase of radiation dose, an increase in apoptosis and necrosis was detected. Significant cellular impairments were noted by pathological analysis under electron microscopy. CONCLUSIONS: Our results demonstrate that the Kunming-mouse is an ideal animal to study (125)I brachytherapy, and the curative effect was closely associated with radiation dose. High-dose of brachytherapy may effectively increase apoptosis and necrosis in liver cells in KM-mice. A dose of 0.58 mCi (125)I radioactive particles may be a safe, effective and minimally invasive therapeutic option for liver cancer.