Stacking Ensemble Technique for Classifying Breast Cancer
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Objectives: Breast cancer is the second most common cancer among Korean women. Because breast cancer is strongly associated with negative emotional and physical changes, early detection and treatment of breast cancer are very important. As a supporting tool for classifying breast cancer, we tried to identify the best meta-learner model in a stacking ensemble when the same machine learning models for the base learner and meta-learner are used. Methods: We used machine learning models, such as the gradient boosted model, distributed random forest, generalized linear model, and deep neural network in a stacking ensemble. These models were used to construct a base learner, and each of them was used as a meta-learner again. Then, we compared the performance of machine learning models in the meta-learner to determine the best meta-learner model in the stacking ensemble. Results: Experimental results showed that using the GBM as a meta-learner led to higher accuracy than that achieved with any other model for breast cancer data and using the GLM as a meta learner led to low root-meansquared error for both sets of breast cancer data. Conclusions: We compared the performance of every meta-learner model in a stacking ensemble as a supporting tool for classifying breast cancer. The study showed that using specific models as a metalearner resulted in better performance than single classifiers, and using GBM and GLM as a meta-learner is appropriate as a supporting tool for classifying breast cancer data.
Abstract
Objectives: Breast cancer is the second most common cancer among Korean women. Because breast cancer is strongly associated with negative emotional and physical changes, early detection and treatment of breast cancer are very important. As a supporting tool for classifying breast cancer, we tried to identify the best meta-learner model in a stacking ensemble when the same machine learning models for the base learner and meta-learner are used. Methods: We used machine learning models, such as the gradient boosted model, distributed random forest, generalized linear model, and deep neural network in a stacking ensemble. These models were used to construct a base learner, and each of them was used as a meta-learner again. Then, we compared the performance of machine learning models in the meta-learner to determine the best meta-learner model in the stacking ensemble. Results: Experimental results showed that using the GBM as a meta-learner led to higher accuracy than that achieved with any other model for breast cancer data and using the GLM as a meta learner led to low root-meansquared error for both sets of breast cancer data. Conclusions: We compared the performance of every meta-learner model in a stacking ensemble as a supporting tool for classifying breast cancer. The study showed that using specific models as a metalearner resulted in better performance than single classifiers, and using GBM and GLM as a meta-learner is appropriate as a supporting tool for classifying breast cancer data.
참고문헌 (20)
- "Causes of Death Statistics in 2016" (2019)[URL]
- "National Cancer Registration and Statistics in Korea 2015" (2019)[URL]
- 최배정, "유방암 수술 환자의 불안, 우울에 영향을 미치는 인자", 생물치료정신의학, 17(1), pp.87~95 (2011), 대한생물치료정신의학회
- 남석진, "유방암의 검진 및 진단", 대한의사협회지, 52(10), pp.946~951 (2009), 대한의사협회
- Jung SS, "Recent trends of breast cancer treatment in Korea", J Korean Surg Soc, 41(6), pp.717~726 (1991)
- 김대동, "유방암 환자의 세침흡입 세포검사에서 위음성에 영향을 주는 임상병리학적 특성", Annals of Surgical Treatment and Research, 62(5), pp.403~407 (2002), 대한외과학회
- Layfield LJ, "Fine-needle aspiration in the management of breast masses", Pathol Annu, 24(Pt 2), pp.23~62 (1989)
- Oh BH, "Diagnostic value of ultrasound-guided fine needle aspiration cytology by a endocrine surgeon", Korean J Endocr Surg, 8(3), pp.189~193 (2008)
- Hong SW, "Fine needle aspiration cytology of thyroid follicular proliferative lesions", Korean J Endocr Surg, 8(3), pp.159~166 (2008)
- Cho SJ, "Industrial applications of machine learning(artificial intelligence)", IE Mag, 23(2), pp.34~38 (2016)
- van der Laan MJ, "Super learner", Stat Appl Genet Mol Biol, 6 (2007)
- 임진수, "유방암 분류 성능 향상을 위한 배깅 서포트 벡터 머신", 보건정보통계학회지, 39(1), pp.15~24 (2014), 한국보건정보통계학회
- Krawczyk B, "Evolutionary undersampling boosting for imbalanced classification of breast cancer malignancy", Appl Soft Comput, 38, pp.714~726 (2016)
- Huang MW, "SVM and SVM Ensembles in Breast Cancer Prediction", PLoS One, 12(1), pp.e0161501~ (2017)
- Nagi S, "Classification of microarray cancer data using ensemble approach", Netw Model Anal Health Inform Bioinform, 2(3), pp.159~173 (2013)
- "UCI Machine Learning Repository" (2018)[URL]
- "H2O documentation overview" (2019)[URL]
- 박진희, "유방암생존자의 외상 후 성장에 영향을 미치는 요인", Journal of Korean Academy of Nursing, 46(3), pp.454~462 (2016), 한국간호과학회
- Montazeri M, "Machine learning models in breast cancer survival prediction", Technol Health Care, 24(1), pp.31~42 (2016)
- Hsieh SL, "Design ensemble machine learning model for breast cancer diagnosis", J Med Syst, 36(5), pp.2841~2847 (2012)