Breast Cancer Surgery 10-Year Survival Prediction by Machine Learning: A Large Prospective Cohort Study
Machine learning algorithms have proven to be effective for predicting survival after surgery, but their use for predicting 10-year survival after breast cancer surgery has not yet been discussed. This study compares the accuracy of predicting 10-year survival after breast cancer surgery in the foll...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Biology |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-7737/11/1/47 |
| _version_ | 1827666593253949440 |
|---|---|
| author | Shi-Jer Lou Ming-Feng Hou Hong-Tai Chang Hao-Hsien Lee Chong-Chi Chiu Shu-Chuan Jennifer Yeh Hon-Yi Shi |
| author_facet | Shi-Jer Lou Ming-Feng Hou Hong-Tai Chang Hao-Hsien Lee Chong-Chi Chiu Shu-Chuan Jennifer Yeh Hon-Yi Shi |
| author_sort | Shi-Jer Lou |
| collection | DOAJ |
| description | Machine learning algorithms have proven to be effective for predicting survival after surgery, but their use for predicting 10-year survival after breast cancer surgery has not yet been discussed. This study compares the accuracy of predicting 10-year survival after breast cancer surgery in the following five models: a deep neural network (DNN), K nearest neighbor (KNN), support vector machine (SVM), naive Bayes classifier (NBC) and Cox regression (COX), and to optimize the weighting of significant predictors. The subjects recruited for this study were breast cancer patients who had received breast cancer surgery (ICD-9 cm 174–174.9) at one of three southern Taiwan medical centers during the 3-year period from June 2007, to June 2010. The registry data for the patients were randomly allocated to three datasets, one for training (<i>n</i> = 824), one for testing (<i>n</i> = 177), and one for validation (<i>n</i> = 177). Prediction performance comparisons revealed that all performance indices for the DNN model were significantly (<i>p</i> < 0.001) higher than in the other forecasting models. Notably, the best predictor of 10-year survival after breast cancer surgery was the preoperative Physical Component Summary score on the SF-36. The next best predictors were the preoperative Mental Component Summary score on the SF-36, postoperative recurrence, and tumor stage. The deep-learning DNN model is the most clinically useful method to predict and to identify risk factors for 10-year survival after breast cancer surgery. Future research should explore designs for two-level or multi-level models that provide information on the contextual effects of the risk factors on breast cancer survival. |
| first_indexed | 2024-03-10T01:53:55Z |
| format | Article |
| id | doaj.art-4fcbfba289b544629ed55abfbfa8f02e |
| institution | Directory Open Access Journal |
| issn | 2079-7737 |
| language | English |
| last_indexed | 2024-03-10T01:53:55Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biology |
| spelling | doaj.art-4fcbfba289b544629ed55abfbfa8f02e2023-11-23T13:00:15ZengMDPI AGBiology2079-77372021-12-011114710.3390/biology11010047Breast Cancer Surgery 10-Year Survival Prediction by Machine Learning: A Large Prospective Cohort StudyShi-Jer Lou0Ming-Feng Hou1Hong-Tai Chang2Hao-Hsien Lee3Chong-Chi Chiu4Shu-Chuan Jennifer Yeh5Hon-Yi Shi6Graduate Institute of Technological and Vocational Education, National Pingtung University of Science and Technology, Pingtung 91201, TaiwanDepartment of Biomedical Science and Environmental Biology, College of Life Science, Kaohsiung Medical University, Kaohsiung 80708, TaiwanDepartment of Surgery, Kaohsiung Municipal United Hospital, Kaohsiung 80457, TaiwanDepartment of General Surgery, Chi Mei Medical Center, Liouying 73658, TaiwanDepartment of General Surgery, E-Da Cancer Hospital, Kaohsiung 82445, TaiwanDepartment of Healthcare Administration and Medical Informatics, Kaohsiung Medical University, Kaohsiung 80708, TaiwanGraduate Institute of Technological and Vocational Education, National Pingtung University of Science and Technology, Pingtung 91201, TaiwanMachine learning algorithms have proven to be effective for predicting survival after surgery, but their use for predicting 10-year survival after breast cancer surgery has not yet been discussed. This study compares the accuracy of predicting 10-year survival after breast cancer surgery in the following five models: a deep neural network (DNN), K nearest neighbor (KNN), support vector machine (SVM), naive Bayes classifier (NBC) and Cox regression (COX), and to optimize the weighting of significant predictors. The subjects recruited for this study were breast cancer patients who had received breast cancer surgery (ICD-9 cm 174–174.9) at one of three southern Taiwan medical centers during the 3-year period from June 2007, to June 2010. The registry data for the patients were randomly allocated to three datasets, one for training (<i>n</i> = 824), one for testing (<i>n</i> = 177), and one for validation (<i>n</i> = 177). Prediction performance comparisons revealed that all performance indices for the DNN model were significantly (<i>p</i> < 0.001) higher than in the other forecasting models. Notably, the best predictor of 10-year survival after breast cancer surgery was the preoperative Physical Component Summary score on the SF-36. The next best predictors were the preoperative Mental Component Summary score on the SF-36, postoperative recurrence, and tumor stage. The deep-learning DNN model is the most clinically useful method to predict and to identify risk factors for 10-year survival after breast cancer surgery. Future research should explore designs for two-level or multi-level models that provide information on the contextual effects of the risk factors on breast cancer survival.https://www.mdpi.com/2079-7737/11/1/47breast cancer surgery10-year survivalmachine learningdeep neural networkperformance |
| spellingShingle | Shi-Jer Lou Ming-Feng Hou Hong-Tai Chang Hao-Hsien Lee Chong-Chi Chiu Shu-Chuan Jennifer Yeh Hon-Yi Shi Breast Cancer Surgery 10-Year Survival Prediction by Machine Learning: A Large Prospective Cohort Study Biology breast cancer surgery 10-year survival machine learning deep neural network performance |
| title | Breast Cancer Surgery 10-Year Survival Prediction by Machine Learning: A Large Prospective Cohort Study |
| title_full | Breast Cancer Surgery 10-Year Survival Prediction by Machine Learning: A Large Prospective Cohort Study |
| title_fullStr | Breast Cancer Surgery 10-Year Survival Prediction by Machine Learning: A Large Prospective Cohort Study |
| title_full_unstemmed | Breast Cancer Surgery 10-Year Survival Prediction by Machine Learning: A Large Prospective Cohort Study |
| title_short | Breast Cancer Surgery 10-Year Survival Prediction by Machine Learning: A Large Prospective Cohort Study |
| title_sort | breast cancer surgery 10 year survival prediction by machine learning a large prospective cohort study |
| topic | breast cancer surgery 10-year survival machine learning deep neural network performance |
| url | https://www.mdpi.com/2079-7737/11/1/47 |
| work_keys_str_mv | AT shijerlou breastcancersurgery10yearsurvivalpredictionbymachinelearningalargeprospectivecohortstudy AT mingfenghou breastcancersurgery10yearsurvivalpredictionbymachinelearningalargeprospectivecohortstudy AT hongtaichang breastcancersurgery10yearsurvivalpredictionbymachinelearningalargeprospectivecohortstudy AT haohsienlee breastcancersurgery10yearsurvivalpredictionbymachinelearningalargeprospectivecohortstudy AT chongchichiu breastcancersurgery10yearsurvivalpredictionbymachinelearningalargeprospectivecohortstudy AT shuchuanjenniferyeh breastcancersurgery10yearsurvivalpredictionbymachinelearningalargeprospectivecohortstudy AT honyishi breastcancersurgery10yearsurvivalpredictionbymachinelearningalargeprospectivecohortstudy |