Yi-Ju Tseng1, Chuan-En Huang2, Chiao-Ni Wen3, Po-Yin Lai4, Min-Hsien Wu5, Yu-Chen Sun4, Hsin-Yao Wang6, Jang-Jih Lu7. 1. Department of Information Management, Chang Gung University, Taiwan; Department of Laboratory Medicine, Chang Gung Memorial Hospital at Linkou, Taiwan; Healthy Aging Research Center, Chang Gung University, Taiwan. 2. Department of Information Management, Chang Gung University, Taiwan. 3. Department of Laboratory Medicine, Chang Gung Memorial Hospital at Linkou, Taiwan; Department of Medical Biotechnology and Laboratory Science, Chang Gung University, Taiwan. 4. Department of Laboratory Medicine, Chang Gung Memorial Hospital at Linkou, Taiwan. 5. Graduate Institute of Biomedical Engineering, Chang Gung University, Taoyuan City, Taiwan; Division of Haematology/Oncology, Department of Internal Medicine, Chang Gung Memorial Hospital at Linkou, Taoyuan City, Taiwan; Biosensor Group, Biomedical Engineering Research Center, Chang Gung University, Taoyuan City, Taiwan. 6. Department of Laboratory Medicine, Chang Gung Memorial Hospital at Linkou, Taiwan; Ph. D. Program in Biomedical Engineering, Chang Gung University, Taoyuan City, Taiwan; Department of Medicine, College of Medicine, Chang Gung University, Taoyuan City, Taiwan. Electronic address: hsinyaowang@cgmh.org.tw. 7. Department of Laboratory Medicine, Chang Gung Memorial Hospital at Linkou, Taiwan; Department of Medical Biotechnology and Laboratory Science, Chang Gung University, Taiwan; Department of Medicine, College of Medicine, Chang Gung University, Taoyuan City, Taiwan. Electronic address: jjlpcp@cgmh.org.tw.
Abstract
BACKGROUND: Approximately 10%-15% of patients with breast cancer die of cancer metastasis or recurrence, and early diagnosis of it can improve prognosis. Breast cancer outcomes may be prognosticated on the basis of surface markers of tumor cells and serum tests. However, evaluation of a combination of clinicopathological features may offer a more comprehensive overview for breast cancer prognosis. MATERIALS AND METHODS: We evaluated serum human epidermal growth factor receptor 2 (sHER2) as part of a combination of clinicopathological features used to predict breast cancer metastasis using machine learning algorithms, namely random forest, support vector machine, logistic regression, and Bayesian classification algorithms. The sample cohort comprised 302 patients who were diagnosed with and treated for breast cancer and received at least one sHER2 test at Chang Gung Memorial Hospital at Linkou between 2003 and 2016. RESULTS: The random-forest-based model was determined to be the optimal model to predict breast cancer metastasis at least 3 months in advance; the correspondingarea under the receiver operating characteristic curve value was 0. 75 (p < 0. 001). CONCLUSION: The random-forest-based model presented in this study may be helpful as part of a follow-up intervention decision support system and may lead to early detection of recurrence, early treatment, and more favorable outcomes.
BACKGROUND: Approximately 10%-15% of patients with breast cancer die of cancer metastasis or recurrence, and early diagnosis of it can improve prognosis. Breast cancer outcomes may be prognosticated on the basis of surface markers of tumor cells and serum tests. However, evaluation of a combination of clinicopathological features may offer a more comprehensive overview for breast cancer prognosis. MATERIALS AND METHODS: We evaluated serum humanepidermal growth factor receptor 2 (sHER2) as part of a combination of clinicopathological features used to predict breast cancer metastasis using machine learning algorithms, namely random forest, support vector machine, logistic regression, and Bayesian classification algorithms. The sample cohort comprised 302 patients who were diagnosed with and treated for breast cancer and received at least one sHER2 test at Chang Gung Memorial Hospital at Linkou between 2003 and 2016. RESULTS: The random-forest-based model was determined to be the optimal model to predict breast cancer metastasis at least 3 months in advance; the correspondingarea under the receiver operating characteristic curve value was 0. 75 (p < 0. 001). CONCLUSION: The random-forest-based model presented in this study may be helpful as part of a follow-up intervention decision support system and may lead to early detection of recurrence, early treatment, and more favorable outcomes.
Authors: Paula Dhiman; Jie Ma; Constanza L Andaur Navarro; Benjamin Speich; Garrett Bullock; Johanna A A Damen; Lotty Hooft; Shona Kirtley; Richard D Riley; Ben Van Calster; Karel G M Moons; Gary S Collins Journal: BMC Med Res Methodol Date: 2022-04-08 Impact factor: 4.615