Research on Breast Cancer Diagnosis and Survival Prediction Based on Ensemble Learning

Jiayao Li; Haojie Huo; Guo Chen; Bo Zhang; Yinuo Tian

doi:10.54097/xa1pzp39

Authors

Jiayao Li
Haojie Huo
Guo Chen
Bo Zhang
Yinuo Tian

DOI:

https://doi.org/10.54097/xa1pzp39

Keywords:

Breast Cancer, Auxiliary Diagnosis and Treatment System, Enhanced Whale Optimization Algorithm, Improved Starling Optimization Algorithm

Abstract

To address the need for high-precision auxiliary diagnosis and survival prediction in breast cancer, a comprehensive diagnosis and treatment system has been developed. In terms of diagnosis, multivariate linear regression and the Enhanced Whale Optimization Algorithm (EWOA) are employed for feature selection and hyperparameter tuning, combined with stacking ensemble learning to improve the model’s accuracy and generalization capability. For survival prediction, the Adaptive Synthetic Sampling (ADASYN) method is used to balance data distribution, and Multi-strategy Improved Nutcracker Optimization Algorithm (MSNOA) is proposed to optimize features and hyperparameters simultaneously. This is integrated with a decision tree-based ensemble learning algorithm (CatBoost) to accurately predict patient survival status. Finally, a multi-platform compatible auxiliary diagnosis and treatment system is developed based on Gradio and Flask frameworks, enabling remote diagnosis and prediction functions, providing intelligent support for clinical personalized treatment, and promoting the development of precision medicine.

Downloads

Download data is not yet available.

References

[1] Wu J, Ma Y Y, Huang J, et al. Predictive value of radiomics based on DBT in triple-negative breast cancer[J]. Journal of Clinical Radiology, 2024, 43(8): 1292-1297.

[2] Deng Z, Su B H, Zhang K. Research on breast cancer classification based on ensemble learning[J]. China Medical Equipment, 2020, 35(12): 59-62.

[3] Wang D, Qu Y, Liu Y H, et al. Classification and diagnosis of breast cancer based on optimized random forest algorithm[J]. Computer Engineering and Design, 2022, 43(3): 706-712.

[4] Gao T, Yuan D C. Improved whale algorithm optimized support vector machine for breast cancer prediction[J]. Modern Electronics Technique, 2024, 47(11): 156-160.

[5] Du X X, Wang Z F, Wang B, et al. Black widow optimization algorithm based on chi-square transition strategy and its application[J]. Journal of Shaanxi University of Science & Technology, 2023, 41(6): 162-175.

[6] Maleki A, Raahemi M, Nasiri H. Breast cancer diagnosis from histopathology images using deep neural network and XGBoost[J]. Biomedical Signal Processing and Control, 2023, 86: 105152.

[7] Williamson S, Vijayakumar K, Kadam V J. Predicting breast cancer biopsy outcomes from BI-RADS findings using random forests with chi-square and MI features[J]. Multimedia Tools and Applications, 2022, 81(26): 36869-36889.

[8] Huang M W, Chen C W, Lin W C, et al. SVM and SVM ensembles in breast cancer prediction[J]. PLOS ONE, 2017, 12(1): e0161501.

[9] Abdar M, Makarenkov V. CWV-BANN-SVM ensemble learning classifier for an accurate diagnosis of breast cancer[J]. Measurement, 2019, 146: 557-570.

[10] Wu Z S, Li F, Zhang H Q, et al. Prognostic factors and construction of survival prediction nomogram for breast cancer patients with brain metastasis: a single-center large sample retrospective study[J]. Journal of Medical Colleges of PLA, 2024, 45(5): 493-502.

[11] Wu G L, Liu J, Sun H. Construction of a nomogram for predicting survival probability of early elderly HER2-positive breast cancer based on SEER database[J]. Chinese Journal of Clinical Pharmacology and Therapeutics, 2024, 29(3): 283-295.

[12] Ye S J, Wang Y X. Cancer survival prediction method of WSI based on graph neural network[J]. Electro-Optic Engineering, 2024, 51(4): 66-78.

[13] Nguyen Q T N, Nguyen P A, Wang C J, et al. Machine learning approaches for predicting 5-year breast cancer survival: A multicenter study[J]. Cancer Science, 2023, 114(10): 4063-4072.

[14] Mahmoud A, Alhussein M, Aurangzeb K, et al. Breast cancer survival prediction modelling based on genomic data: An improved prognosis-driven deep learning approach[J]. IEEE Access, 2024.

[15] Yuan H, Xu H. Deep multi-modal fusion network with gated unit for breast cancer survival prediction[J]. Computer Methods in Biomechanics and Biomedical Engineering, 2024, 27(7): 883-896.

[16] Zhang G, Ma C, Yan C, et al. MSFN: a multi-omics stacked fusion network for breast cancer survival prediction[J]. Frontiers in Genetics, 2024, 15: 1378809.