BRCA Variations Risk Assessment in Breast Cancers Using Different Artificial Intelligence Models

Artificial intelligence provides modelling on machines by simulating the human brain using learning and decision-making abilities. Early diagnosis is highly effective in reducing mortality in cancer. This study aimed to combine cancer-associated risk factors including genetic variations and design an artificial intelligence system for risk assessment. Data from a total of 268 breast cancer patients have been analysed for 16 different risk factors including genetic variant classifications. In total, 61 BRCA1, 128 BRCA2 and 11 both BRCA1 and BRCA2 genes associated breast cancer patients’ data were used to train the system using Mamdani’s Fuzzy Inference Method and Feed-Forward Neural Network Method as the model softwares on MATLAB. Sixteen different tests were performed on twelve different subjects who had not been introduced to the system before. The rates for neural network were 99.9% for training success, 99.6% for validation success and 99.7% for test success. Despite neural network’s overall success was slightly higher than fuzzy logic accuracy, the results from developed systems were similar (99.9% and 95.5%, respectively). The developed models make predictions from a wider perspective using more risk factors including genetic variation data compared with similar studies in the literature. Overall, this artificial intelligence models present promising results for BRCA variations’ risk assessment in breast cancers as well as a unique tool for personalized medicine software.

Download Full-text

Incidence and Risk Factors of the Infusion-Related Reactions in Breast Cancer Patients Receiving Trastuzumab

Journal of Korean Society of Health-System Pharmacists ◽

10.32429/jkshp.2018.35.2.004 ◽

2018 ◽

Vol 35 (2) ◽

pp. 177-183

Author(s):

정지혜 ◽

여미진 ◽

박애령 ◽

황보신이 ◽

나현오 ◽

...

Keyword(s):

Breast Cancer ◽

Risk Factors ◽

Cancer Patients ◽

Breast Cancer Patients

Download Full-text

An Exploration of Heart Failure Risk in Breast Cancer Patients Receiving Anthracyclines with or without Trastuzumab in Thailand: A Retrospective Study

Clinics and Practice ◽

10.3390/clinpract11030064 ◽

2021 ◽

Vol 11 (3) ◽

pp. 484-493

Author(s):

Jukapun Yoodee ◽

Aumkhae Sookprasert ◽

Phitjira Sanguanboonyaphong ◽

Suthan Chanthawong ◽

Manit Seateaw ◽

...

Keyword(s):

Breast Cancer ◽

Risk Factors ◽

Cancer Patients ◽

Left Ventricular ◽

Left Ventricular Ejection ◽

Breast Cancer Patients ◽

Ventricular Ejection Fraction ◽

Factors Associated ◽

Palliative Intent ◽

Increased Risk

Anthracycline-based regimens with or without anti-human epidermal growth factor receptor (HER) 2 agents such as trastuzumab are effective in breast cancer treatment. Nevertheless, heart failure (HF) has become a significant side effect of these regimens. This study aimed to investigate the incidence and factors associated with HF in breast cancer patients treated with anthracyclines with or without trastuzumab. A retrospective cohort study was performed in patients with breast cancer who were treated with anthracyclines with or without trastuzumab between 1 January 2014 and 31 December 2018. The primary outcome was the incidence of HF. The secondary outcome was the risk factors associated with HF by using the univariable and multivariable cox-proportional hazard model. A total of 475 breast cancer patients were enrolled with a median follow-up time of 2.88 years (interquartile range (IQR), 1.59–3.93). The incidence of HF was 3.2%, corresponding to an incidence rate of 11.1 per 1000 person-years. The increased risk of HF was seen in patients receiving a combination of anthracycline and trastuzumab therapy, patients treated with radiotherapy or palliative-intent chemotherapy, and baseline left ventricular ejection fraction <65%, respectively. There were no statistically significant differences in other risk factors for HF, such as age, cardiovascular comorbidities, and cumulative doxorubicin dose. In conclusion, the incidence of HF was consistently high in patients receiving combination anthracyclines trastuzumab regimens. A reduced baseline left ventricular ejection fraction, radiotherapy, and palliative-intent chemotherapy were associated with an increased risk of HF. Intensive cardiac monitoring in breast cancer patients with an increased risk of HF should be advised to prevent undesired cardiac outcomes.

Download Full-text

Risk factors for pegylated liposomal doxorubicin-induced moderate to severe hand-foot syndrome in breast cancer patients: assessment of baseline clinical parameters

BMC Cancer ◽

10.1186/s12885-021-08028-8 ◽

2021 ◽

Vol 21 (1) ◽

Author(s):

Guohua Liang ◽

Wenjie Ma ◽

Yanfang Zhao ◽

Eryu Liu ◽

Xiaoyu Shan ◽

...

Keyword(s):

Breast Cancer ◽

Risk Factors ◽

Prediction Model ◽

Cancer Patients ◽

Blood Circulation ◽

Pegylated Liposomal Doxorubicin ◽

Dose Intensity ◽

Breast Cancer Patients ◽

Hand Foot Syndrome ◽

Peripheral Blood Circulation

Abstract Background Hand-foot syndrome (HFS) is a side effect of skin related to pegylated liposomal doxorubicin (PLD) application. Moderate to severe hand-foot syndrome (MSHFS) might have a serious impact on patients’ quality of life and treatment. However, information on risk factors for the development of MSHFS is still limited. To analyze the risk factors for PLD-induced MSHFS in breast cancer patients and constructed a logistic regression prediction model. Methods We conducted a retrospective analysis of breast cancer patients who were treated with a PLD regimen in the Tumor Hospital of Harbin Medical University from January 2017 to August 2019. A total of 26 factors were collected from electronic medical records. Patients were divided into MSHFS (HFS > grade 1) and NMHFS (HFS ≤ grade 1) groups according to the NCI classification. Statistical analysis of these factors and the construction of a logistic regression prediction model based on risk factors. Results A total of 44.7% (206/461) of patients developed MSHFS. The BMI, dose intensity, and baseline Alanine aminotransferase (ALT) and Aspartate aminotransferase (AST) levels in the MSHFS group, as well as good peripheral blood circulation, excessive sweat excretion, history of gallstones, and tumour- and HER2-positive percentages, were all higher than those in the NMHFS group (P < 0.05). The model for predicting the occurrence of MSHFS was P = 1/1 + exp. (11.138–0.110*BMI-0.234*dose intensity-0.018*baseline ALT+ 0.025*baseline AST-1.225*gallstone history-0.681* peripheral blood circulation-1.073*sweat excretion-0.364*with or without tumor-0.680*HER-2). The accuracy of the model was 72.5%, AUC = 0.791, and Hosmer-Lemeshow fit test P = 0.114 > 0.05. Conclusions Nearly half of the patients developed MSHFS. The constructed prediction model may be valuable for predicting the occurrence of MSHFS in patients.

Download Full-text

How can artificial intelligence models assist PD-L1 expression scoring in breast cancer: results of multi-institutional ring studies

npj Breast Cancer ◽

10.1038/s41523-021-00268-y ◽

2021 ◽

Vol 7 (1) ◽

Author(s):

Xinran Wang ◽

Liang Wang ◽

Hong Bu ◽

Ningning Zhang ◽

Meng Yue ◽

...

Keyword(s):

Breast Cancer ◽

Artificial Intelligence ◽

Clinical Practice ◽

Subjective Assessment ◽

Current Guideline ◽

Scoring Method ◽

Programmed Death ◽

Intelligence Models ◽

Artificial Intelligence Models ◽

Scoring Accuracy

AbstractProgrammed death ligand-1 (PD-L1) expression is a key biomarker to screen patients for PD-1/PD-L1-targeted immunotherapy. However, a subjective assessment guide on PD-L1 expression of tumor-infiltrating immune cells (IC) scoring is currently adopted in clinical practice with low concordance. Therefore, a repeatable and quantifiable PD-L1 IC scoring method of breast cancer is desirable. In this study, we propose a deep learning-based artificial intelligence-assisted (AI-assisted) model for PD-L1 IC scoring. Three rounds of ring studies (RSs) involving 31 pathologists from 10 hospitals were carried out, using the current guideline in the first two rounds (RS1, RS2) and our AI scoring model in the last round (RS3). A total of 109 PD-L1 (Ventana SP142) immunohistochemistry (IHC) stained images were assessed and the role of the AI-assisted model was evaluated. With the assistance of AI, the scoring concordance across pathologists was boosted to excellent in RS3 (0.950, 95% confidence interval (CI): 0.936–0.962) from moderate in RS1 (0.674, 95% CI: 0.614–0.735) and RS2 (0.736, 95% CI: 0.683–0.789). The 2- and 4-category scoring accuracy were improved by 4.2% (0.959, 95% CI: 0.953–0.964) and 13% (0.815, 95% CI: 0.803–0.827) (p < 0.001). The AI results were generally accepted by pathologists with 61% “fully accepted” and 91% “almost accepted”. The proposed AI-assisted method can help pathologists at all levels to improve the PD-L1 assay (SP-142) IC assessment in breast cancer in terms of both accuracy and concordance. The AI tool provides a scheme to standardize the PD-L1 IC scoring in clinical practice.

Download Full-text

Is There a Bias Against Obese Patients in the Treatment of Breast Cancer?

The American Surgeon ◽

10.1177/0003134820984877 ◽

2020 ◽

pp. 000313482098487

Author(s):

Melinda Wang ◽

Julian Huang ◽

Anees B. Chagpar

Keyword(s):

Breast Cancer ◽

Neoadjuvant Chemotherapy ◽

Cancer Patients ◽

Prophylactic Mastectomy ◽

Implicit Bias ◽

Treatment Decision ◽

Obese Patients ◽

Breast Cancers ◽

Breast Cancer Patients ◽

Immediate Reconstruction

Background Patient and tumor characteristics often coincide with obesity, potentially affecting treatment decision-making in obese breast cancer patients. Independent of all of these factors, however, it is unclear whether obesity itself impacts the decision to offer patients undergoing mastectomy breast reconstruction, postmastectomy radiation therapy (PMRT), or neoadjuvant chemotherapy. We sought to determine whether implicit bias against obese breast cancer patients undergoing mastectomy plays a role in their treatment. Methods Medical records of breast cancer patients undergoing mastectomy from January 2010 to April 2018 from a single institution were retrospectively reviewed, separated into obese (BMI ≥30) and nonobese (BMI <30) categories, and compared using nonparametric statistical analyses. Results Of 972 patients, 291 (31.2%) were obese. Obese patients were more likely to have node-positive, triple-negative breast cancers ( P = .026) and were also more likely to have other comorbidities such as a history of smoking ( P = .026), hypertension ( P < .001), and diabetes ( P < .001). Receipt of immediate reconstruction and contralateral prophylactic mastectomy did not vary between obese and nonobese patients. While obese patients were more likely to undergo neoadjuvant chemotherapy (26.5% vs. 18.1%, P = .004) and PMRT (33.0% vs. 23.4%, P = .003), this did not remain significant when controlling for comorbidities and clinicopathologic confounders. Conclusion Obese patients present with more aggressive tumors and often have concomitant comorbidities. Independent of these factors, however, differences in the treatment of patients undergoing mastectomy do not seem to be affected by an implicit bias against obese patients.

Download Full-text

Predominance of RAD21 and ERBB2 amplification and progesterone receptor positivity in tumors of the right breast support breast cancer lateralization.

Journal of Clinical Oncology ◽

10.1200/jco.2021.39.15_suppl.e12557 ◽

2021 ◽

Vol 39 (15_suppl) ◽

pp. e12557-e12557

Author(s):

Zachary Spigelman ◽

Jo-Ellen Murphy

Keyword(s):

Breast Cancer ◽

Progesterone Receptor ◽

Cancer Patients ◽

Breast Tumors ◽

Left Breast ◽

Breast Cancers ◽

Her2 Expression ◽

Breast Cancer Patients ◽

The Right ◽

Chi Square Analysis

e12557 Background: Biologic lateralization broadly impacts breast cancer. Malignancies originating in the left breast compared to the right breast tend to be more frequent, larger and of poorer prognosis. Left breast tumors respond differently to HER2-neu signaling and have lateralized Ki67 expression. In a prior study a right-left asymmetry in the neutrophil/lymphocyte ratio (NLR) of breast cancers was identified (ASCO 2018, e13094). As a follow-up, retrospective analysis of results from comprehensive genomic profiling (CGP) of right and left side breast cancer specimens was performed to determine a potential genomic etiology for the observed NLR lateralization. Methods: Tumors from 43 consecutive breast cancer patients underwent analysis for all classes of genomic alterations by hybrid capture-based CGP (Foundation Medicine). The CGP results from the 25 left- and 18 right-sided breast cancer samples were analyzed along with the histologic grade and status of estrogen receptor (ER), progesterone receptor (PR), and HER2 expression. Results: In this cohort of advanced breast cancer patients (stage 3-4), no statistically significant differences in lateralization were identified based on patient age, tumor stage, or frequency of ER or Her2 expression (Table). A predominance of PR positivity (p=0.14 chi square analysis) and amplifications in the ERBB2 (p=0.37) and RAD21 (p=0.08) genes were detected in right side tumors. Conclusions: Together with the prior study, trends in asymmetry based on genomic, pathologic, and immunohistologic differences have been detected in breast cancers, including an increased incidence of ERBB2 and RAD21 amplification in right-side breast tumors in this cohort. The predominance of lower PR positivity in the left breast tumors may be due to preferential hypermethylation, consistent with reports that it mediates biologic lateralization changes, downregulates PR expression, and alters amplification rates. Epigenetic methylation, may contribute to asymmetric breast cancer biology and have implications for therapeutic strategy. Further study is warranted.[Table: see text]

Download Full-text