Doctmedico journal logo







TITLE: Reviewing Breast Cancer Prediction with machine learning in recent studies and public health perspectives.

Authors: Abbas Jedariforoughi, Farzaneh Karimpour.

ABSTRACT: Breast cancer (BC) is the most commonly found disease among women all over the world. The early diagnosis of breast cancer can potentially reduce the mortality rate and increase the chances of a successful treatment.(1) Breast cancer is most common in middle-aged female population. It is the fourth most dangerous cancer compared to remaining cancers. In recent years, breast cancer patients are significantly increasing, so the early diagnosis of cancer has become a necessary task in the cancer research, to facilitate subsequent clinical management of patients in the public health global management.(15). Breast cancer has become the representative condition for financial toxicity in cancer owing to its annual incidence, public health awareness, and policy relevance.(3)

KEYWORDS: Breast cancer (BC).Machine learning. Prediction. Next Generation Sequencing (NGS). NCBI (National Centre for Biotechnology Information) .public health.artificial neural network (ANN) . logistic regression method AI artificial intelligence.multiple kernel learning (MKL). bayesian optimization.axillary lymph-node (ALN).invasive ductal breast cancer (IDC) . Python.

Published in Doctmedico journal. Year:2021 volume:1 issue :2 page 156-159.

DOI : 10.17613/2t5x-8557

PDF   

REFERENCES:(Citation)

  (Bibliography)  






Title: Reviewing Breast Cancer Prediction with machine learning in recent studies and public health perspectives.


Abstract: Breast cancer (BC) is the most commonly found disease among women all over the world. The early diagnosis of breast cancer can potentially reduce the mortality rate and increase the chances of a successful treatment.(1)

Breast cancer is most common in middle-aged female population. It is the fourth most dangerous cancer compared to remaining cancers. In recent years, breast cancer patients are significantly increasing, so the early diagnosis of cancer has become a necessary task in the cancer research, to facilitate subsequent clinical management of patients in the public health global management.(15).

Breast cancer has become the representative condition for financial toxicity in cancer owing to its annual incidence, public health awareness, and policy relevance.(3)


Authors.  Dr Abbas Jedariforoughi MD. Farzaneh Karimpour ( computer science)


farzaneh.karimpour@yahoo.com

abbasjedari@yahoo.com


Keywords: Breast cancer (BC).Machine learning. Prediction. Next Generation Sequencing (NGS).NCBI (National Centre for Biotechnology Information) .public health.artificial neural network (ANN) . logistic regression method. AI artificial intelligence.multiple kernel learning (MKL). bayesian optimization.axillary lymph-node (ALN).invasive ductal breast cancer (IDC) .Python.

Introduction: A wide reach on cancer prediction and detection using Next Generation Sequencing (NGS) by the application of artificial intelligence is highly appreciated in the current scenario of the medical field. Next generation sequences were extracted from NCBI (National Centre for Biotechnology Information) gene repository .(2)

In previous studies (Seoane et al., 2014; Zhang et al., 2016; Sun et al., 2018; Zhang A. et al., 2019; Zhang Y. et al., 2019), multiple kernel learning (MKL) (Lanckriet et al., 2004; Rakotomamonjy et al., 2008; Kloft et al., 2011) was successfully used to integrate different types of data into a universal model to distinguish short-term and long-term cancers survivors. MKL uses different kernels for different types of data, and then trains the weight of each kernel to select the best combination of kernel functions for classification (7). The results indicated that K-Nearest-Neighbors is the best predictor with 91.6% accuracy (19)

Discussion: According to the report(1) of the Centers for Disease Control and Prevention (CDC), breast cancer is one of the most common cancers among women. About 10% to 15% of all the worldwide women develop the disease in their lifetime (18)

Studies show that . Of all supervised models, decision tree machine learning technique performed most with maximum accuracy in classification of 94.03%. (2)

In some studies , trained and tested an ensemble of machine learning (ML) algorithms (neural network, regularized linear model, support vector machines, and a classification tree) to predict financial toxicity.(3)

According to a study there are five administered AI methods named Support vector machine (SVM), K-closest neighbors, irregular woodlands, fake/ Artificial neural organizations (ANNs). The performance of the study is measured with respect to accuracy, sensitivity, specificity, precision, negative predictive value. (6)

A study shows that the best accuracy of 96.2% for cancer prediction is obtained with Extra tree classifier algorithm by using feature selection technique along with bayesian optimization and hyperparameter tuning.(9)

There are some ML techniques which are used for breast cancer detection and diagnosis. The popular techniques are Support Vector Machine (SVM), Random Forest (RF) and Naive Bayes (NB) and     k-nearest neighbor (k-NN).(11) &(12)

. In a study , A breast cancer metastasis dataset from The Cancer Genome Atlas was used for external validation, showing an accuracy of over 91%. The hub gene assay can be used to predict breast cancer metastasis by machine learning.(13)

The result analysis shows that SVM finds out to be a suitable option for identifying different performance matrices such as Sensitivity, Accuracy, error, and Specificity.(17)

The proposed framework that used in a study is an optimized version of Random Forest algorithm in which feature selection is implemented and the process is incorporated with the preprocessing filters. The proposed framework for breast cancer prediction successfully achieved a prediction accuracy of 90.47%, which is found to be better than the standard classifiers like SVM, neural network, etc.(20)

Conclusion: 

ML models accurately predicted financial toxicity related to breast cancer treatment specialy in public health arguments. These predictions may inform decision making and care planning to avoid financial distress during cancer treatment or enable targeted financial support.(3)

In a study, the utilized ANN technique had a relatively high sensitivity and precision for identifying people with breast cancer comparing to the other methods (logistic regression method).(4)

The machine learning-based radiomics model showed good sensitivity for the prediction of ALN metastasis and could assist the preoperative individualized prediction of ALN status in patients with IDC.(10)

Based on the previous findings, it is recommended to use ML preprocessing python libraries to prepare the dataset before building ML classification model of breast cancer metastasis prediction.(16)


Reference:

  1. Feature selection and classification in breast cancer prediction using IoT and machine learning https://www.sciencedirect.com/science/article/abs/pii/S0263224121004310

  2. Breast cancer prediction using an optimal machine learning technique for next generation sequences https://journals.sagepub.com/doi/abs/10.1177/1063293X21991808

  3. Development of machine learning algorithms for the prediction of financial toxicity in localized breast Cancer following surgical treatment. https://ascopubs.org/doi/full/10.1200/CCI.20.00088

  4. The impact coenzyme Q10 supplementation on the inflammatory indices of women with breast cancer using A machine learning prediction model. https://www.sciencedirect.com/science/article/pii/S2352914821001040

  5. Prediction of Presence of Breast Cancer Disease in the Patient using Machine Learning Algorithms and SFS. https://iopscience.iop.org/article/10.1088/1757-899X/1099/1/012003/meta

  6. Analysis of machine learning techniques for breast cancer prediction. https://www.indianjournals.com/ijor.aspx?target=ijor:ijemr&volume=11&issue=1&article=012

  7. Integrating Somatic Mutations for Breast Cancer Survival Prediction Using Machine Learning Methods. https://www.frontiersin.org/articles/10.3389/fgene.2020.632901/full

  8. Implementation of Machine Learning Approaches for Breast Cancer Prediction https://www.turcomat.org/index.php/turkbilmat/article/view/1562

  9. Hybrid Feature Selection and Bayesian Optimization with Machine Learning for Breast Cancer Prediction. https://ieeexplore.ieee.org/abstract/document/9441914

  10. A machine learning-based radiomics model for the prediction of axillary lymph-node metastasis in breast cancer. https://link.springer.com/article/10.1007/s12282-020-01202-z

  11. An Outline of Machine Learning Techniques for Breast Cancer Prediction  https://scholar.google.com/scholar?start=10&q=allintitle:+breast+cancer+prediction+machine+learning&hl=en&as_sdt=0,5&as_ylo=2021#d=gs_qabs&u=%23p%3D7gXmFCxwmrcJ

  12. Machine Learning Algorithms for Breast Cancer Detection and Prediction. https://link.springer.com/chapter/10.1007/978-981-16-0695-3_14

  13. Machine Learning Model for Lymph Node Metastasis Prediction in Breast Cancer Using Random Forest Algorithm and Mitochondrial Metabolism Hub Genes. https://www.mdpi.com/2076-3417/11/7/2897

  14. Prediction of Breast Cancer Survival by Machine Learning Methods: An Application of Multiple Imputation. https://ijph.tums.ac.ir/index.php/ijph/article/view/16101

  15. Risk Prediction-Based Breast Cancer Diagnosis Using Personal Health Records and Machine Learning Models. https://link.springer.com/chapter/10.1007/978-981-15-9516-5_37

  16. Python-based preprocessing for applying machine learning in breast cancer metastasis prediction. https://ascopubs.org/doi/abs/10.1200/JCO.2021.39.15_suppl.e13558

  17. Efficient role of machine learning classifiers in the prediction and detection of breast cancer. https://scholar.google.com/scholar?start=10&q=allintitle:+breast+cancer+prediction+machine+learning&hl=en&as_sdt=0,5&as_ylo=2021#d=gs_qabs&u=%23p%3DdpW4_O_dtE0J

  18. Machine Learning & Time Based Prediction of Breast Cancer Tumor Recurrence https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3829672

  19. Prediction Model for Breast Cancer Detection Using Machine Learning Algorithms https://link.springer.com/chapter/10.1007/978-981-15-6876-3_33

  20. Breast Cancer Recurrence Prediction in Biopsy Using Machine Learning Framework https://link.springer.com/chapter/10.1007/978-981-15-5341-7_28

  21. Prediction of Pathologic Complete Response to Neoadjuvant Chemotherapy Using Machine Learning Models in Patients with Breast Cancer https://scholar.google.com/scholar?start=20&q=allintitle:+breast+cancer+prediction+machine+learning&hl=en&as_sdt=0,5&as_ylo=2021#d=gs_qabs&u=%23p%3DrZMcOSe7M9MJ

  22. Prediction of the Malignant Tumour Size in Breast Cancer with the Aid of Machine Learning https://scholar.google.com/scholar?start=20&q=allintitle:+breast+cancer+prediction+machine+learning&hl=en&as_sdt=0,5&as_ylo=2021#d=gs_qabs&u=%23p%3DNcEhAdjxwg8J

  23. Machine Learning for Survival Prediction in Breast Cancer https://scholar.google.com/scholar?start=20&q=allintitle:+breast+cancer+prediction+machine+learning&hl=en&as_sdt=0,5&as_ylo=2021#d=gs_qabs&u=%23p%3Dx7cAqQ9gZ5UJ