Comparison of Random Survival Forest Based‐Overall Survival With Deep Learning and Cox Proportional Hazard Models in HER‐2‐Positive HR‐Negative Breast Cancer
ABSTRACT Background Traditional CoxPH models are limited in handling real‐world data complexities. While machine learning models like RSF and DeepSurv show promise, their application and comparative evaluation in the HER2‐positive/HR‐negative breast cancer subtype require further validation. Aims Th...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-07-01
|
| Series: | Cancer Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/cnr2.70262 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839612816075522048 |
|---|---|
| author | Wenqi Cai Yan Qi Linhui Zheng Huachao Wu Chunqian Yang Runze Zhang Chaoyan Wu Haijun Yu |
| author_facet | Wenqi Cai Yan Qi Linhui Zheng Huachao Wu Chunqian Yang Runze Zhang Chaoyan Wu Haijun Yu |
| author_sort | Wenqi Cai |
| collection | DOAJ |
| description | ABSTRACT Background Traditional CoxPH models are limited in handling real‐world data complexities. While machine learning models like RSF and DeepSurv show promise, their application and comparative evaluation in the HER2‐positive/HR‐negative breast cancer subtype require further validation. Aims This study aims to build a survival prediction model for breast cancer patients based on different methods. The optimal model will provide more accurate survival predictions for clinical decision‐making of HER2 positive and HR negative cancer patients. Methods and Results This study analyzed 8,119 HER2‐positive HR‐negative breast cancer patients from the SEER database, randomly allocated to training/validation/test cohorts (7:1:2 ratio). Predictive models were developed using five feature sets and three algorithms (Cox PH, RSF, DeepSurv), with feature selection optimized via Concordance index (C‐index). Evaluation revealed: The C‐index of the DeepSurv models constructed using the training set is greater than 0.8, performing better than both the RSF and CoxPH models. However, CoxPH outperforms DeepSurv in terms of C‐index when testset. The Brier scores for all models were below 0.25. Which indicates that the models predicted with high accuracy. Based on the training set, the Deepsurv model predicted the highest ROC‐AUCs of 0.91, 0.863, and 0.855 for 1‐, 3‐, and 5‐year overall survival (OS), respectively. The RSF model achieved the highest AUCs, specifically 0.876, 0.861, and 0.845, for 1‐, 3‐, and 5‐year overall survival in the test group. The calibration graphs indicate that of the three models forecasting overall survival at 1, 3, and 5 years, the RSF model demonstrated the greatest level of agreement between predictions and actual observations, trailed by the DeepSurv model. There was poor agreement between CoxPH model predictions and observed data. Optimal Clinical Net Benefits at 1, 3, and 5 Years for DCA of the Deepsurv Model in the Training Set Data. However, in the test set, compared to other models, RSF showed better Optimal Clinical Net Benefits. Conclusions In conclusion, compared to conventional prognostic models, the Random Survival Forest (RSF) model serves as a reliable tool for predicting long‐term survival in breast cancer patients, demonstrating consistent performance across diverse datasets. Furthermore, the feature set selected via RSF‐Variable Importance (VIMP) (compared with LASSO regression and Cox regression) significantly enhances the performance of prognostic models. Our findings may offer practical guidance for future development of long‐term prognostic models tailored to breast cancer subtypes. |
| format | Article |
| id | doaj-art-7a19fad7f77d49e598acf31f97d67dbd |
| institution | Matheson Library |
| issn | 2573-8348 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Wiley |
| record_format | Article |
| series | Cancer Reports |
| spelling | doaj-art-7a19fad7f77d49e598acf31f97d67dbd2025-07-27T23:36:41ZengWileyCancer Reports2573-83482025-07-0187n/an/a10.1002/cnr2.70262Comparison of Random Survival Forest Based‐Overall Survival With Deep Learning and Cox Proportional Hazard Models in HER‐2‐Positive HR‐Negative Breast CancerWenqi Cai0Yan Qi1Linhui Zheng2Huachao Wu3Chunqian Yang4Runze Zhang5Chaoyan Wu6Haijun Yu7Department of Radiation and Medical Oncology, Hubei Key Laboratory of Tumor Biological Behaviors, Hubei Cancer Clinical Study Center Zhongnan Hospital of Wuhan University Wuhan Hubei ChinaDepartment of Radiation and Medical Oncology, Hubei Key Laboratory of Tumor Biological Behaviors, Hubei Cancer Clinical Study Center Zhongnan Hospital of Wuhan University Wuhan Hubei ChinaDepartment of Radiation and Medical Oncology, Hubei Key Laboratory of Tumor Biological Behaviors, Hubei Cancer Clinical Study Center Zhongnan Hospital of Wuhan University Wuhan Hubei ChinaDepartment of Radiation and Medical Oncology, Hubei Key Laboratory of Tumor Biological Behaviors, Hubei Cancer Clinical Study Center Zhongnan Hospital of Wuhan University Wuhan Hubei ChinaDepartment of Radiation and Medical Oncology, Hubei Key Laboratory of Tumor Biological Behaviors, Hubei Cancer Clinical Study Center Zhongnan Hospital of Wuhan University Wuhan Hubei ChinaDepartment of Radiation and Medical Oncology, Hubei Key Laboratory of Tumor Biological Behaviors, Hubei Cancer Clinical Study Center Zhongnan Hospital of Wuhan University Wuhan Hubei ChinaDepartment of Integrated Traditional Chinese Medicine and Western Medicine Zhongnan Hospital of Wuhan University Wuhan Hubei ChinaDepartment of Radiation and Medical Oncology, Hubei Key Laboratory of Tumor Biological Behaviors, Hubei Cancer Clinical Study Center Zhongnan Hospital of Wuhan University Wuhan Hubei ChinaABSTRACT Background Traditional CoxPH models are limited in handling real‐world data complexities. While machine learning models like RSF and DeepSurv show promise, their application and comparative evaluation in the HER2‐positive/HR‐negative breast cancer subtype require further validation. Aims This study aims to build a survival prediction model for breast cancer patients based on different methods. The optimal model will provide more accurate survival predictions for clinical decision‐making of HER2 positive and HR negative cancer patients. Methods and Results This study analyzed 8,119 HER2‐positive HR‐negative breast cancer patients from the SEER database, randomly allocated to training/validation/test cohorts (7:1:2 ratio). Predictive models were developed using five feature sets and three algorithms (Cox PH, RSF, DeepSurv), with feature selection optimized via Concordance index (C‐index). Evaluation revealed: The C‐index of the DeepSurv models constructed using the training set is greater than 0.8, performing better than both the RSF and CoxPH models. However, CoxPH outperforms DeepSurv in terms of C‐index when testset. The Brier scores for all models were below 0.25. Which indicates that the models predicted with high accuracy. Based on the training set, the Deepsurv model predicted the highest ROC‐AUCs of 0.91, 0.863, and 0.855 for 1‐, 3‐, and 5‐year overall survival (OS), respectively. The RSF model achieved the highest AUCs, specifically 0.876, 0.861, and 0.845, for 1‐, 3‐, and 5‐year overall survival in the test group. The calibration graphs indicate that of the three models forecasting overall survival at 1, 3, and 5 years, the RSF model demonstrated the greatest level of agreement between predictions and actual observations, trailed by the DeepSurv model. There was poor agreement between CoxPH model predictions and observed data. Optimal Clinical Net Benefits at 1, 3, and 5 Years for DCA of the Deepsurv Model in the Training Set Data. However, in the test set, compared to other models, RSF showed better Optimal Clinical Net Benefits. Conclusions In conclusion, compared to conventional prognostic models, the Random Survival Forest (RSF) model serves as a reliable tool for predicting long‐term survival in breast cancer patients, demonstrating consistent performance across diverse datasets. Furthermore, the feature set selected via RSF‐Variable Importance (VIMP) (compared with LASSO regression and Cox regression) significantly enhances the performance of prognostic models. Our findings may offer practical guidance for future development of long‐term prognostic models tailored to breast cancer subtypes.https://doi.org/10.1002/cnr2.70262breast cancerCoxPHDeepsurvRSFRSF‐VIMP |
| spellingShingle | Wenqi Cai Yan Qi Linhui Zheng Huachao Wu Chunqian Yang Runze Zhang Chaoyan Wu Haijun Yu Comparison of Random Survival Forest Based‐Overall Survival With Deep Learning and Cox Proportional Hazard Models in HER‐2‐Positive HR‐Negative Breast Cancer Cancer Reports breast cancer CoxPH Deepsurv RSF RSF‐VIMP |
| title | Comparison of Random Survival Forest Based‐Overall Survival With Deep Learning and Cox Proportional Hazard Models in HER‐2‐Positive HR‐Negative Breast Cancer |
| title_full | Comparison of Random Survival Forest Based‐Overall Survival With Deep Learning and Cox Proportional Hazard Models in HER‐2‐Positive HR‐Negative Breast Cancer |
| title_fullStr | Comparison of Random Survival Forest Based‐Overall Survival With Deep Learning and Cox Proportional Hazard Models in HER‐2‐Positive HR‐Negative Breast Cancer |
| title_full_unstemmed | Comparison of Random Survival Forest Based‐Overall Survival With Deep Learning and Cox Proportional Hazard Models in HER‐2‐Positive HR‐Negative Breast Cancer |
| title_short | Comparison of Random Survival Forest Based‐Overall Survival With Deep Learning and Cox Proportional Hazard Models in HER‐2‐Positive HR‐Negative Breast Cancer |
| title_sort | comparison of random survival forest based overall survival with deep learning and cox proportional hazard models in her 2 positive hr negative breast cancer |
| topic | breast cancer CoxPH Deepsurv RSF RSF‐VIMP |
| url | https://doi.org/10.1002/cnr2.70262 |
| work_keys_str_mv | AT wenqicai comparisonofrandomsurvivalforestbasedoverallsurvivalwithdeeplearningandcoxproportionalhazardmodelsinher2positivehrnegativebreastcancer AT yanqi comparisonofrandomsurvivalforestbasedoverallsurvivalwithdeeplearningandcoxproportionalhazardmodelsinher2positivehrnegativebreastcancer AT linhuizheng comparisonofrandomsurvivalforestbasedoverallsurvivalwithdeeplearningandcoxproportionalhazardmodelsinher2positivehrnegativebreastcancer AT huachaowu comparisonofrandomsurvivalforestbasedoverallsurvivalwithdeeplearningandcoxproportionalhazardmodelsinher2positivehrnegativebreastcancer AT chunqianyang comparisonofrandomsurvivalforestbasedoverallsurvivalwithdeeplearningandcoxproportionalhazardmodelsinher2positivehrnegativebreastcancer AT runzezhang comparisonofrandomsurvivalforestbasedoverallsurvivalwithdeeplearningandcoxproportionalhazardmodelsinher2positivehrnegativebreastcancer AT chaoyanwu comparisonofrandomsurvivalforestbasedoverallsurvivalwithdeeplearningandcoxproportionalhazardmodelsinher2positivehrnegativebreastcancer AT haijunyu comparisonofrandomsurvivalforestbasedoverallsurvivalwithdeeplearningandcoxproportionalhazardmodelsinher2positivehrnegativebreastcancer |