Predict Breast Cancer Recurrence Research Articles

A multi-model approach integrating whole-slide imaging and clinicopathologic features to predict breast cancer recurrence risk.

Breast cancer is the most common malignancy affecting women worldwide and is notable for its morphologic and biologic diversity, with varying risks of recurrence following treatment. The Oncotype DX Breast Recurrence Score test is an important predictive and prognostic genomic assay for estrogen receptor positive/HER2 negative breast cancer that guides therapeutic strategies; however, such tests can be expensive, delay care, and are not widely available. The aim of this study was to develop a multi-model approach integrating the analysis of whole-slide images and clinicopathologic data to predict their associated breast cancer recurrence risks and categorize these patients into two risk groups according to the predicted score: low-risk and high-risk. The proposed novel methodology uses convolutional neural networks for feature extraction and vision transformers for contextual aggregation, complemented by a logistic regression model that analyzes clinicopathologic data for classification into two risk categories. This method was trained and tested on 956 hematoxylin and eosin-stained whole-slide images of 950 ER+/HER2- breast cancer patients with corresponding clinicopathological features that had prior Oncotype DX testing. The model's performance was evaluated using an internal test set of 192 patients from Dartmouth Health and an external test set of 405 patients from the University of Chicago. The multi-model approach achieved an AUC of 0.91 (95% CI: 0.87-0.95) on the internal set and an AUC of 0.84 (95% CI: 0.78-0.89) on the external cohort for predicting low- and high-breast cancer recurrence risk categories based on the Oncotype DX recurrence score. With further validation, the proposed methodology could provide an alternative to assist clinicians in personalizing treatment for breast cancer patients and potentially improving their outcomes.

Enhancing fairness in breast cancer recurrence prediction through temporal machine learning models

Enhancing fairness in breast cancer recurrence prediction through temporal machine learning models

Oncological outcomes of stage I–II breast cancer treatment after subcutaneous/skin-sparing mastectomies with reconstruction

Aim. To study the recurrence of stage I–II breast cancer after subcutaneous/skin-sparing mastectomies with reconstruction with or without radiation therapy. Materials and methods. From 2013 to 2022, 984 patients diagnosed with breast cancer underwent 1020 subcutaneous/skin-sparing mastectomies with reconstruction at the P.A. Herzen Moscow State Medical Institute. Histological types are presented: cancer in situ – 7, invasive cancer without signs of specificity – 818, invasive lobular cancer – 105, combined cancer – 40, rare forms – 50. Subcutaneous mastectomy with reconstruction was performed in 617 (60.5 %), skin-sparing mastectomy in 403 (39.5 %) cases. Reconstruction with own tissues was performed in 5.7 %, expanders/implants in 94.3 % of patients. Patients with diagnosed mutations in the genes ВRCА1, 2, СНЕК2 amounted to 208 (21.1 %), while among patients with primary multiple synchronous cancer, the percentage with mutations was 25 %. Results. In the studied group of patients, recurrence of breast cancer was diagnosed in 40 (4.1 ± 0.1 %) cases, distant metastases – in 52 (5.3 ± 0.1 %) cases. The minimum time to relapse was 36 months, and the maximum was 108 months. In a single-factor analysis of the stage of the disease: at stage I, relapse was diagnosed in 25 (5.8 %) cases, at stage IIA (T2N0M0) – in 5 (2.0 %), at stage IIA (T1N1M0) – in 6 (4.2 %), at stage IIB T2N1M0 – in 4 (2.1 %) (p > 0.05). The recurrence in the group with radiation therapy was 2.5 ± 0.6 (odd ratio 0.98, 95 % confidential interval 1.52–3.48), without radiation therapy 5.1 % (odd ratio 2.13, 95 % confidential interval 0.92–5.18) regardless of the stage of breast cancer (t-criterion >2, p > 0.05). In our study, the recurrence of breast cancer at the edge of R1 was 6.8 ± 2.5 %, at R0 – 3 ± 0.6 % (p > 0.05). When analyzing age and risk of recurrence, we did not identify age dependence, up to 40 years the probability of recurrence is 4.3 ± 1 %, after 40 years – 3.3 ± 0.7 % (t-criterion 0.44, p > 0.05). The dependence of the degree of malignancy of the tumor node and the frequency of recurrence is as follows: G1 – 2. 3 ± 2.3 %, G2 – 3 ± 0.7 %, G3 – 3.9 ± 1 %, when compared G3 c G1 (t-criterion 0.52, p>0.05), when comparing G3 from G2 (t-criterion 0.49, p > 0.05). Recurrence of breast cancer with triple negative type was diagnosed in 2.5 ± 0.9 % relative to other molecular biological types (t-criterion 1.49, p > 0.05). We analyzed the dependence of relapse on the non-luminal and luminal HER2 positive types; the relapse was 5.4 ± 1.5 % (p > 0.05); the dependence on the level of Ki-67; at a level of 40 %, the probability of recurrence is 4 ± 0.8 %, at a level > 40 %, recurrence is 2 ± 0.8 % (t-criterion 1.77, p > 0.05). A statistically significant difference in our study was revealed, in addition to radiation therapy, during neoadjuvant polychemotherapy, so in the group with neoadjuvant polychemotherapy, the recurrence was 2 ± 0.8 %, without neoadjuvant polychemotherapy – 4.1 ± 0.7 % (t-criterion 2.16, р < 0.05). Conclusion. A link between breast cancer recurrence and morphological features (R1 resection margin, lymphovascular invasion, lymphatic tumor emboli, luminal and non-luminal HER2+ subtype, G3) and clinical characteristics (presence of mutations, location of a lesion in the gland, stages) was found. Further search for predictors of breast cancer recurrence after combination or integrated treatment is necessary.

288P External validation of an AI-enabled digital test (PreciseDx Breast) to predict breast cancer recurrence within 6-years exhibited good independent performance on a comparable early-stage cohort from the Netherlands

288P External validation of an AI-enabled digital test (PreciseDx Breast) to predict breast cancer recurrence within 6-years exhibited good independent performance on a comparable early-stage cohort from the Netherlands

Impact of Hyperparameter Optimization to Enhance Machine Learning Performance: A Case Study on Breast Cancer Recurrence Prediction

Accurate and early prediction of breast cancer recurrence is crucial to guide medical decisions and treatment success. Machine learning (ML) has shown promise in this domain. However, its effectiveness critically depends on proper hyperparameter setting, a step that is not always performed systematically in the development of ML models. In this study, we aimed to highlight the impact that this process has on the final performance of ML models through a real-world case study by predicting the five-year recurrence of breast cancer patients. We compared the performance of five ML algorithms (Logistic Regression, Decision Tree, Gradient Boosting, eXtreme Gradient Boost, and Deep Neural Network) before and after optimizing their hyperparameters. Simpler algorithms showed better performance using the default hyperparameters. However, after the optimization process, the more complex algorithms demonstrated superior performance. The AUCs obtained before and after adjustment were 0.7 vs. 0.84 for XGB, 0.64 vs. 0.75 for DNN, 0.7 vs. 0.8 for GB, 0.62 vs. 0.7 for DT, and 0.77 vs. 0.72 for LR. The results underscore the critical importance of hyperparameter selection in the development of ML algorithms for the prediction of cancer recurrence. Neglecting this step can undermine the potential of more powerful algorithms and lead to the choice of suboptimal models.

Contrast-enhanced ultrasound features as a potential biomarker for the prediction of breast cancer recurrence.

To investigate the associations between contrast-enhanced ultrasound imaging features and disease recurrence among patients with locally advanced breast cancer treated with neoadjuvant chemotherapy. In the study, pre- and post-neoadjuvant chemotherapy contrast-enhanced ultrasound images of 43 patients with breast cancer were retrospectively analysed. Post-acquisition image processing involved the placement of freehand-drawn regions of interest, followed by the generation of blood flow kinetics representing blood volume and velocity for these regions of interest. Qualitative and quantitative contrast-enhanced ultrasound parameters were compared to predict recurrence, and receiver operating characteristic analysis was used to evaluate predictive ability. Among the 43 patients, 10 (23%) exhibited disease recurrence (median [range]: 27 [4-68] months). Post-neoadjuvant chemotherapy peak enhancement, wash-in area under the curve, wash-out area under the curve, and wash-in and wash-out area under the curve (p=0.003, p=0.004, p=0.026, and p=0.014, respectively) differed between the no-recurrence and recurrence groups. The area under the receiver operating characteristic curve (0.88; 95% confidence interval: 0.75-1.00) for post-neoadjuvant chemotherapy peak enhancement was the highest among the contrast-enhanced ultrasound parameters, with a cut-off of 13.33 arbitrary units. Higher peak enhancement on post-neoadjuvant chemotherapy contrast-enhanced ultrasound images was associated with recurrence in women with locally advanced breast cancer and is a potential biomarker of tumor recurrence.

Comparative analysis of genomic tests for the prediction for late recurrence risk in hormone receptor–positive invasive breast cancer in a sample of Colombian patients.

e13092 Background: Approximately 70% of invasive breast cancers are hormone receptor-positive, requiring 5 years of endocrine therapy as the gold standard treatment. However, extended endocrine therapy (EET) may be needed, considering the late recurrence risk up to 15 years post-diagnosis. Different genomic tests predict the risk of recurrence. The 70-gene signature classifies patients as low or high risk during the first 5-years after diagnosis. The 12-gene test identifies high and low-risk patients for distant relapse up to 15 years, while a third test, based on 7-gene expression, assesses distant relapse risk up to 10 years. These tests assist clinicians in defining the need for EET. This study aims to compare the results of these genomic tests to determine late recurrence and distant relapse risks after 5 years, guiding EET indications. Methods: This is a retrospective descriptive transversal study involving 27 female patients diagnosed with hormone receptor-positive invasive breast cancer, treated in the same oncologic center in Colombia. All patients were first tested with the 70-gene genomic profile, with 15 patients undergoing the 12-gene test and 12 cases undergoing the 7-gene assay approximately 5 years later. Concordance between test results was assessed, and socio-demographic variables were descriptively analyzed. Results: The mean age was 54.4 years (SD=11.7). Invasive ductal carcinoma comprised 77.7% and invasive lobular carcinoma 22.22%. The 70-gene profile identified 21 cases (77.7%) as low-risk. Among those, 87.5% had a high-risk result with the 12-gene test, and 60% had a high-risk score with the 7-gene test. Conclusions: The findings support the utility observed in the sub-analysis of the NSABP-B42 study, showing that a low-risk result in the 70-genes signature, means high risk of late recurrence and the need for EET, emphasizing the importance of further evaluation and validation of genomic tests in predicting breast cancer recurrence risks. Larger sample sizes are necessary to confirm these results and establish their clinical relevance in oncology practice.

Abstract PO5-01-10: Evaluating a computer-aided platform for predicting recurrence and survival in an Oncotype Dx tested breast cancer cohort

Abstract Background: Oncotype DX Breast Recurrence ScoreÒ (ODXRS) is a widely used predictive measure of breast cancer recurrence risk and chemotherapy benefit for patients with estrogen receptor positive (ER+), human epidermal growth factor receptor-2 negative (HER2-) breast cancers. ODXRS testing incurs additional costs and delays. These drawbacks could be obviated by innovative computer-aided technologies within digital pathology workflows. Such technologies could be developed to perform a wide variety of diagnostic and prognostic tests on digital whole slide images (WSIs) of hematoxylin and eosin (H&E)-stained tissue alone. This would save time, cost, and sample tissue whilst still providing critical prognostic information for patient management. Q-Plasia OncoReader Breast (QPORB) is a computer-aided solution which extracts information from H&E WSIs to provide diagnostic and prognostic information for breast cancer specimens. Aims: The aim of this study was to identify whether the computer aided QPROB platform could successfully predict breast cancer recurrence from H&E WSIs alone in line with recurrence predicted by ODXRS. Methods: H&E slides corresponding to tissue blocks sent for ODXRS testing from primary breast cancer resection/excision specimens from St James’s University Hospital, Leeds, UK (n=137 cases, 1 slide per case) were collected, anonymized, and scanned at x20 magnification on an Aperio AT2 scanner. Relevant pathological and clinical data were collected from electronic pathology reports and patient records. These data included ODXRS and recurrence events. QPORB analyzed each case/slide and generated a digital biomarker profile from the H&E images alone, combining statistical physics and tumor biology to quantify malignant cell cycle deformation. QPORB’s biomarker profile and ODXRS for each case was compared to disease-free survival (DFS) and overall survival (OS). Kaplan-Meier survival analyses were performed. Confounding factors (age, tumor grade, invasive tumor size and Charlson Comorbidity Index) were accounted for. Results: Results of three QPORB-generated indices - two putatively associated with overall cell cycle signature and one with G1 deformation, and their combined overall biomarker profile did not predict DFS in this cohort. However, with regards to OS, all three indices and the combined biomarker profile predicted OS over a median follow-up period of 5 years (P=0.044). 5% of WSIs (7/137) did not meet the criteria to be analyzed by QPORB and 4% (6/137) could not be analyzed by QPORB (attrition). While ODXRS similarly predicted OS but not DFS, the follow-up duration was suboptimal. Conclusion: While QPORB indices evaluated in this work, putatively associated with overall cell cycle signature and G1 deformation, did not predict breast cancer recurrence on a par with ODXRS, it has shown promising results as potential adjunct device to provide an estimate of OS for breast cancer patients eligible for ODXRS testing. Future work will expand on this observational cohort, blindly validate these findings, and extend the work to encompass all breast cancer molecular subtypes. Citation Format: Satabhisa Mukhopadhyay, Elizabeth Walsh, Rebecca Millican-Slater, Andrew Hanby, Joanne Stephenson, Tathagata Dasgupta, Nicolas Orsi. Evaluating a computer-aided platform for predicting recurrence and survival in an Oncotype Dx tested breast cancer cohort [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO5-01-10.

Traditional Clinicopathological Biomarkers Still Determine Disease-Free and Overall Survival in Invasive Breast Cancer Patients: A Pilot Study.

Background: Molecular classification, tumor diameter, Ki67 expression, and brachytherapy administration still act as the most potent potential predictors of breast cancer recurrence and overall survival. Methods: Over the period of 23 months, we included in the study 92 invasive breast cancer (IBrC) patients initially diagnosed at the Clinical Ward of Breast Cancer and Reconstructive Surgery, Oncology Center in Bydgoszcz, Poland. The probability of disease-free survival (DFS) and overall survival (OS) in relation to potential prognostic factors for the patients were determined using a Kaplan-Meier analysis, and univariate and multivariate Cox regression analyses evaluated the predictive factors of IBrC patients. The investigation of the potential prognostic model's accuracy was analyzed using the ROC curve. Results: Patients with tumor size < 2 cm, Ki67 expression < 20%, luminal-A molecular subtype, and extra-dose brachytherapy boost administration displayed the most favorable prognosis according to breast cancer disease-free survival and overall survival. The estimated 5 year probability of DFS and OS rates in women with tumor diameter < 2 cm were 89% and 90%, respectively. In tumor diameter > 2 cm, the estimated 5 year probability of DFS was 73% and OS was 76%. Interestingly, the tumor diameter of 1.6 cm with a specificity of 60.5% and a sensitivity of 75% occurred as the best threshold point to differentiate patients with cancer recurrence from those without cancer progression. Conclusions: Our study provides essential information on the clinicopathological profile and future outcomes of early stage IBrC patients. Furthermore, the tumor diameter cut-off value of 1.6 cm discriminating between disease recurrence and those without disease progression patients represents an innovative direction for further research.

Breast cancer recurrence prediction with deep neural network and feature optimization

Breast cancer remains a pervasive global health concern, necessitating continuous efforts to attain effectiveness of recurrence prediction schemes. This work focuses on breast cancer recurrence prediction using two advanced architectures such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), integrated with feature selection techniques utilizing Logistic Regression (LR) and Analysis of Variance (ANOVA). The well-known Wisconsin cancer registry dataset, which contains vital diagnostic data from breast mass fine-needle aspiration biopsies, was employed in this study. The mean values of accuracy, precision, recall and F1-score for the proposed LR-CNN-LSTM model were calculated as 98.24%, 99.14%, 98.30% and 98.14% respectively. The mean values of accuracy, precision, recall and F1-score for the proposed ANOVA-GRU model were calculated as 96.49%, 97.04%, 96.67% and 96.67% respectively. The comparison with traditional methods showcases the superiority of our proposed approach. Moreover, the insights gained from feature selection contribute to a deeper understanding of the critical factors influencing breast cancer recurrence. The combination of LSTM and GRU models with feature selection methods not only enhances prediction accuracy but also provides valuable insights for medical practitioners. This research holds the potential to aid in early diagnosis and personalized treatment strategies.

Bone mineral density fall during aromatase inhibitor treatment may predict lower breast cancer recurrence.

Aromatase inhibitors (AIs) are associated with reduction in bone mineral density (BMD). The use of bone strengthening agents zoledronic acid and denosumab are associated with improved breast cancer outcomes for post-menopausal patients treated with AIs. This study investigates whether change in BMD with AI therapy is associated with breast cancer recurrence. A cohort of patients treated at a single institution diagnosed with hormone receptor-positive breast cancer with baseline BMD and subsequent BMD test while receiving adjuvant aromatase inhibitor therapy were studied. Demographic, treatment and outcome data was obtained. Simple and multiple linear regression analysis was performed to investigate predictors of annual percent BMD change at the LS and hip. Univariate and multivariate Cox proportional hazards modelling were undertaken to investigate predictors of breast cancer recurrence. 353 patients eligible patients were identified. In multivariate analysis of lumbar spine BMD change, the difference between those in quartile 1, which showed the greatest reduction in BMD, and quartile 3, with substantially less reduction, was significant (HR = 3.02, 95% CI 1.15-7.90 p = 0.025). Hip BMD reduction was also not significantly associated with breast cancer recurrence. The two quartiles with the least reduction in hip BMD showing a non-significant reduced risk of recurrence relative to the quartile with the greatest (p = 0.10). The findings suggest an association may exist between lumbar spine BMD change and breast cancer recurrence for patients treated with adjuvant AI. Further research is required to determine whether BMD change can be utilised as a biomarker.

Assessment of Background Parenchymal Enhancement at Dynamic Contrast-enhanced MRI in Predicting Breast Cancer Recurrence Risk.

Background Background parenchymal enhancement (BPE) at dynamic contrast-enhanced (DCE) MRI of cancer-free breasts increases the risk of developing breast cancer; implications of quantitative BPE in ipsilateral breasts with breast cancer are largely unexplored. Purpose To determine whether quantitative BPE measurements in one or both breasts could be used to predict recurrence risk in women with breast cancer, using the Oncotype DX recurrence score as the reference standard. Materials and Methods This HIPAA-compliant retrospective single-institution study included women diagnosed with breast cancer between January 2007 and January 2012 (development set) and between January 2012 and January 2017 (internal test set). Quantitative BPE was automatically computed using an in-house-developed computer algorithm in both breasts. Univariable logistic regression was used to examine the association of BPE with Oncotype DX recurrence score binarized into high-risk (recurrence score >25) and low- or intermediate-risk (recurrence score ≤25) categories. Models including BPE measures were assessed for their ability to distinguish patients with high risk versus those with low or intermediate risk and the actual recurrence outcome. Results The development set included 127 women (mean age, 58 years ± 10.2 [SD]; 33 with high risk and 94 with low or intermediate risk) with an actual local or distant recurrence rate of 15.7% (20 of 127) at a minimum 10 years of follow-up. The test set included 60 women (mean age, 57.8 years ± 11.6; 16 with high risk and 44 with low or intermediate risk). BPE measurements quantified in both breasts were associated with increased odds of a high-risk Oncotype DX recurrence score (odds ratio range, 1.27-1.66 [95% CI: 1.02, 2.56]; P < .001 to P = .04). Measures of BPE combined with tumor radiomics helped distinguish patients with a high-risk Oncotype DX recurrence score from those with a low- or intermediate-risk score, with an area under the receiver operating characteristic curve of 0.94 in the development set and 0.79 in the test set. For the combined models, the negative predictive values were 0.97 and 0.93 in predicting actual distant recurrence and local recurrence, respectively. Conclusion Ipsilateral and contralateral DCE MRI measures of BPE quantified in patients with breast cancer can help distinguish patients with high recurrence risk from those with low or intermediate recurrence risk, similar to Oncotype DX recurrence score. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Zhou and Rahbar in this issue.

Androgen Receptor Influenced Recurrence Score Correlation in Hormone Positive and HER2 Negative Breast Cancer Indian Patients: A Comparative Approach

Breast cancer (BC) recurrence is a major concern for both patients and healthcare providers. Accurately predicting the risk of BC recurrence can help guide treatment decisions and improve patient outcomes for a disease-free survival. There are several approaches and models that have been developed to predict BC recurrence risk. These include derived clinical assays such as genetic profiling (Oncotye Dx, MammaPrint, CanAssist and others), and algorithm derived open access tools such as Magee equations (ME), CTS5 Calculator and Predict Breast cancer. All the clinical assays are well accepted, but affordability and feasibility remain the challenge due to a noteworthy price tag of USD 3000. As per The American Society of Clinical Oncology (ASCO) updates, open access tools are possible substitutes but the availability of limited information on their applicability is a concern. These tools take into consideration the histopathologic parameters and immunohistochemistry (IHC) biomarkers data for estrogen receptor/progesterone (ER/PR), human epidermal growth factor receptor 2 (HER2), and Ki67. The current study focuses on the application of these tools in a subset of 55 Indian BC patients considering the influence of the androgen receptor (AR) IHC expression profile. AR is a potent target and a close interacting neighbor protein to ER and available literature also suggests their crosstalk expression in BC clinical models. Our comparative recurrence scores (RSs) predictive data showed a statistically significant AR expression correlation with average ME scores. No significance was noted across different prediction tools. The findings are suggestive that ME predictive scores are more relevant and informative compared to other online tools and with an additional AR IHC expression analysis the recurrence prediction might prove to be beneficial and feasible to many deprived BC patients.

Optimized Deep Convolutional Neural Network for the Prediction of Breast Cancer Recurrence

With more than 2.1 million new cases of diagnosis each year, breast cancer is considered to be the most prevalent women disease. Within 10 years, nearly 30% patients who got cured at early-stages experienced cancer recurrence. Recurrence is a crucial aspect of breast cancer behaviour that is inseparably linked to mortality. Despite its importance, the significant proportion of breast cancer datasets rarely include it, which makes research into its prediction more challenging. It is still difficult to predict who will experience a recurrence and who won't, which has implications for the treatment that goes along with it. Clinicians treating breast cancer may be able to avoid ineffective overtreatment if Artificial Intelligence (AI) methods are developed that can forecast the likelihood of breast cancer recurrence. This work proposes a novel automatic breast cancer recurrence classification and prediction system incorporating novel Deep Convolutional Neural Network (DCNN) algorithm. The proposed DCNN model is deployed on Wisconsin Breast Cancer dataset for further evaluation. The role of AI in forecasting recurrence is examined in this work. The experimental results were analysed for various combination of train and validation dataset. The accuracy, precision, recall and F1-score for the proposed DCNN was calculated as 97.63 %, 98.57 %, 96.84 %, 97.89 % respectively.

Machine learning-based models for the prediction of breast cancer recurrence risk

Breast cancer is the most common malignancy diagnosed in women worldwide. The prevalence and incidence of breast cancer is increasing every year; therefore, early diagnosis along with suitable relapse detection is an important strategy for prognosis improvement. This study aimed to compare different machine algorithms to select the best model for predicting breast cancer recurrence. The prediction model was developed by using eleven different machine learning (ML) algorithms, including logistic regression (LR), random forest (RF), support vector classification (SVC), extreme gradient boosting (XGBoost), gradient boosting decision tree (GBDT), decision tree, multilayer perceptron (MLP), linear discriminant analysis (LDA), adaptive boosting (AdaBoost), Gaussian naive Bayes (GaussianNB), and light gradient boosting machine (LightGBM), to predict breast cancer recurrence. The area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and F1 score were used to evaluate the performance of the prognostic model. Based on performance, the optimal ML was selected, and feature importance was ranked by Shapley Additive Explanation (SHAP) values. Compared to the other 10 algorithms, the results showed that the AdaBoost algorithm had the best prediction performance for successfully predicting breast cancer recurrence and was adopted in the establishment of the prediction model. Moreover, CA125, CEA, Fbg, and tumor diameter were found to be the most important features in our dataset to predict breast cancer recurrence. More importantly, our study is the first to use the SHAP method to improve the interpretability of clinicians to predict the recurrence model of breast cancer based on the AdaBoost algorithm. The AdaBoost algorithm offers a clinical decision support model and successfully identifies the recurrence of breast cancer.

A framework for predicting breast cancer recurrence

Breast cancer is one of the serious diseases that threaten the life of many women worldwide. The seriousness of this disease is that it is often discovered in late stages after a period of its occurrence. This causes a wide spread of the disease and difficulty in its treatment. Another important characteristic of this disease is that it can return again after a period of its treatment. Therefore, predicting the occurrence or recurrence of such disease early is the best solution to have a high cure rate. The main objective of this paper is to improve the prediction performance of the breast cancer recurrence. Many methods have been proposed to predict breast cancer recurrence. However, these methods did not achieve the desired results on one of the most famous datasets in the field of breast cancer recurrence’s prediction (i.e., Wisconsin Prognosis Breast Cancer (WPBC) dataset). The highest accuracy achieved using the previous methods is 89.89%. Therefore, this paper provides a framework for improving the prediction of breast cancer recurrence. The proposed framework has the ability to overcome many of the challenges in the existing dataset such as: (a) the problem of imbalance between classes using a data over-sampling technique; and (b) the large number of data dimensions using Principal Component Analysis (PCA), and a wrapper dimensionality reduction technique based on Genetic Algorithm (GA). It also uses the neural network algorithm to fuse the results of two individual classifiers (i.e., Random Forest (RF) and Support Vector Machine (SVM)). Our proposed framework evaluation showed a significant improvement in the predication performance. It achieved an accuracy of 98.3%, area under the curve of 99%, and precision, recall, and f1-measure of 98%.

S3LR: Novel feature selection approach for Microarray-Based breast cancer recurrence prediction

Enhancing the accuracy of breast cancer recurrence prediction is crucial, mainly when dealing with genomics data, which presents challenges such as high dimensionality, noise, non-linearity, and limited sample sizes. This paper introduces Semi-Supervised Survival Laplacian Regression (S3LR), a novel feature selection algorithm designed to improve breast cancer recurrence prediction by effectively handling censored, event, and unlabeled data. S3LR modifies the Laplacian Score (LS) by incorporating a distance matrix to calculate the weight matrix, and it integrates heuristic and metaheuristic optimization algorithms to optimize the weighted matrix. These enhancements refine feature selection and overall performance. In our evaluations using three datasets and comparisons with state-of-the-art techniques, S3LR combined with Particle Swarm Optimization (PSO) demonstrates significant improvements in C-index and mean absolute error (MAE). Average C-index values reach 68.80 %, 59.49 %, and 67.66 %, with average MAE values of 15.98, 7.87, and 8.65 months, respectively. These results showcase S3LR's effectiveness in predicting recurrence, even with censored data, for more precise and reliable outcomes. Furthermore, the framework's versatility extends beyond breast cancer and can readily be applied to address other survival and recurrence problems.

308P Regression-based deep-learning predicts breast cancer recurrence risk score from pathology slides

308P Regression-based deep-learning predicts breast cancer recurrence risk score from pathology slides

Breast Cancer Recurrence Prediction Using Data Mining

Today, the Healthcare sector is generating a vast amount of meticulously detailed information on individuals and their medical issues. Medical data may be investigated for hidden patterns or connections using data mining techniques. The spread and return of the illness are the main causes of breast cancer fatalities. One of the most important areas of study in the field of medicine is the early diagnosis of breast cancer. Healthcare businesses can benefit from data mining by forecasting patient illnesses and behaviour trends. This is performed by analyzing data from many angles and by using data mining to find hidden patterns and associations between seemingly unrelated bits of information. Months after the original diagnosis and breast cancer therapy, a metastatic recurrence of the disease may happen. Only a few number of techniques have been researched in the state of the art due to the challenges associated with early breast cancer recurrence prediction during its medication. The aim of the research is to review the work done by different researchers in this field and to compare the various traditional data mining classifiers (Logistic Regression, Naïve Bayes, K-Nearest Neighbours, Decision Tree, Support Vector Machines, and Random Forest) applied to Breast Cancer Data Set from UCI Machine Learning Repository. Out of these, the best results were given by Random Forest Algorithm with 98.4% accuracy.

Predictive value of machine learning for breast cancer recurrence: a systematic review and meta-analysis.

Recurrence of breast cancer leads to a high lifetime risk and a low 5year survival rate. Researchers have used machine learning to predict the risk of recurrence in patients with breast cancer, but the predictive performance of machine learning remains controversial. Hence, this study aimed to explore the accuracy of machine learning in predicting breast cancer recurrence risk and aggregate predictive variables to provide guidance for the development of subsequent risk scoring systems. We searched Pubmed, EMBASE, Cochrane, and Web of Science. The risk of bias in the included studies was evaluated using prediction model risk of bias assessment tool (PROBAST). Meta-regression was adopted to explore whether there was a significant difference in the recurrence time by machine learning. Thirty-four studies involving 67,560 subjects were included, among whom 8695 experienced breast cancer recurrence. The c-index of prediction models was 0.814 (95%CI 0.802-0.826) and 0.770 (95%CI 0.737-0.803) in the training and validation sets, respectively; the sensitivity and specificity were 0.69 (95% CI 0.64-0.74), 0.89 (95% CI 0.86-0.92) in the training, and 0.64 (95% CI 0.58-0.70), 0.88 (95% CI 0.82-0.92) in the validation, respectively. Age, histological grading, and lymph node status are the most commonly used variables in model construction. Attention should be paid to unhealthy lifestyles such as drinking, smoking and BMI as modeling variables. Risk prediction models based on machine learning have long-term monitoring value for breast cancer population, and subsequent studies should consider using large-sample and multi-center data to establish risk equations for verification. Machine learning may be used as a predictive tool for breast cancer recurrence. Currently, there is a lack of effective and universally applicable machine learning models in clinical practice. We expect to incorporate multi-center studies in the future and attempt to develop tools for predicting breast cancer recurrence risk, so as to effectively identify populations at high risk of recurrence and develop personalized follow-up strategies and prognostic interventions to reduce the risk of recurrence.