A Machine Learning Model for Predicting Prognosis in HCC Patients With Diabetes After TACE
Linxia Wu,1– 3,* Lei Chen,1– 3,* Lijie Zhang,1,4,* Yiming Liu,1,5,* Die Ouyang,1 Wenlong Wu,5,6 Yu Lei,5,6 Ping Han,1 Huangxuan Zhao,1– 3 Chuansheng Zheng1– 3 1Department of Radiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technolo...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Dove Medical Press
2025-01-01
|
| Series: | Journal of Hepatocellular Carcinoma |
| Subjects: | |
| Online Access: | https://www.dovepress.com/a-machine-learning-model-for-predicting-prognosis-in-hcc-patients-with-peer-reviewed-fulltext-article-JHC |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592099477815296 |
|---|---|
| author | Wu L Chen L Zhang L Liu Y Ouyang D Wu W Lei Y Han P Zhao H Zheng C |
| author_facet | Wu L Chen L Zhang L Liu Y Ouyang D Wu W Lei Y Han P Zhao H Zheng C |
| author_sort | Wu L |
| collection | DOAJ |
| description | Linxia Wu,1– 3,* Lei Chen,1– 3,* Lijie Zhang,1,4,* Yiming Liu,1,5,* Die Ouyang,1 Wenlong Wu,5,6 Yu Lei,5,6 Ping Han,1 Huangxuan Zhao,1– 3 Chuansheng Zheng1– 3 1Department of Radiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei Province, 430022, People’s Republic of China; 2Department of Interventional Radiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei Province, 430022, People’s Republic of China; 3Hubei Provincial Clinical Research Center for Precision Radiology & Interventional Medicine, Wuhan, Hubei Province, 430022, People’s Republic of China; 4Department of Interventional Radiology, The Fifth Medical Center of Chinese, PLA General Hospital, Beijing, 100039, People’s Republic of China; 5Department of Interventional Radiology, Auto Valley Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei Province, 430056, People’s Republic of China; 6Department of Interventional Radiology, Jinyinhu Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei Province, 430048, People’s Republic of China*These authors contributed equally to this workCorrespondence: Chuansheng Zheng; Huangxuan Zhao, Department of Radiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei Province, 430022, People’s Republic of China, Email hqzcsxh@sina.com; zhao_huangxuan@sina.comPurpose: Type II diabetes mellitus (T2DM) has been found to increase the mortality of patients with hepatocellular carcinoma (HCC). Therefore, this study aimed to establish and validate a machine learning-based explainable prediction model of prognosis in patients with HCC and T2DM undergoing transarterial chemoembolization (TACE).Patients and Methods: The prediction model was developed using data from the derivation cohort comprising patients from three medical centers, followed by external validation utilizing patient data extracted from another center. Further, five predictive models were employed to establish prognosis models for 1-, 2-, and 3-year survival, respectively. Prediction performance was assessed by the receiver operating characteristic (ROC), calibration, and decision curve analysis curves. Lastly, the SHapley Additive exPlanations (SHAP) method was used to interpret the final ML model.Results: A total of 636 patients were included. Thirteen variables were selected for the model development. The final random survival forest (RSF) model exhibited excellent performance in the internal validation cohort, with areas under the ROC curve (AUCs) of 0.824, 0.853, and 0.810 in the 1-, 2-, and 3-year survival groups, respectively. This model also demonstrated remarkable discrimination in the external validation cohort, achieving AUCs of 0.862, 0.815, and 0.798 in the 1-, 2-, and 3-year survival groups, respectively. SHAP summary plots were also created to interpret the RSF model.Conclusion: An RSF model with good predictive performance was developed by incorporating simple parameters. This prognostic prediction model may assist physicians in early clinical intervention and improve prognosis outcomes in patients with HCC and comorbid T2DM after TACE.Keywords: hepatocellular carcinoma, type II diabetes mellitus, transarterial chemoembolization, overall survival, SHapley Additive exPlanations |
| format | Article |
| id | doaj-art-f2f1e6df7e1f41cb97975153e4d0d938 |
| institution | Kabale University |
| issn | 2253-5969 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Dove Medical Press |
| record_format | Article |
| series | Journal of Hepatocellular Carcinoma |
| spelling | doaj-art-f2f1e6df7e1f41cb97975153e4d0d9382025-01-21T16:58:07ZengDove Medical PressJournal of Hepatocellular Carcinoma2253-59692025-01-01Volume 12779199431A Machine Learning Model for Predicting Prognosis in HCC Patients With Diabetes After TACEWu LChen LZhang LLiu YOuyang DWu WLei YHan PZhao HZheng CLinxia Wu,1– 3,* Lei Chen,1– 3,* Lijie Zhang,1,4,* Yiming Liu,1,5,* Die Ouyang,1 Wenlong Wu,5,6 Yu Lei,5,6 Ping Han,1 Huangxuan Zhao,1– 3 Chuansheng Zheng1– 3 1Department of Radiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei Province, 430022, People’s Republic of China; 2Department of Interventional Radiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei Province, 430022, People’s Republic of China; 3Hubei Provincial Clinical Research Center for Precision Radiology & Interventional Medicine, Wuhan, Hubei Province, 430022, People’s Republic of China; 4Department of Interventional Radiology, The Fifth Medical Center of Chinese, PLA General Hospital, Beijing, 100039, People’s Republic of China; 5Department of Interventional Radiology, Auto Valley Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei Province, 430056, People’s Republic of China; 6Department of Interventional Radiology, Jinyinhu Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei Province, 430048, People’s Republic of China*These authors contributed equally to this workCorrespondence: Chuansheng Zheng; Huangxuan Zhao, Department of Radiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei Province, 430022, People’s Republic of China, Email hqzcsxh@sina.com; zhao_huangxuan@sina.comPurpose: Type II diabetes mellitus (T2DM) has been found to increase the mortality of patients with hepatocellular carcinoma (HCC). Therefore, this study aimed to establish and validate a machine learning-based explainable prediction model of prognosis in patients with HCC and T2DM undergoing transarterial chemoembolization (TACE).Patients and Methods: The prediction model was developed using data from the derivation cohort comprising patients from three medical centers, followed by external validation utilizing patient data extracted from another center. Further, five predictive models were employed to establish prognosis models for 1-, 2-, and 3-year survival, respectively. Prediction performance was assessed by the receiver operating characteristic (ROC), calibration, and decision curve analysis curves. Lastly, the SHapley Additive exPlanations (SHAP) method was used to interpret the final ML model.Results: A total of 636 patients were included. Thirteen variables were selected for the model development. The final random survival forest (RSF) model exhibited excellent performance in the internal validation cohort, with areas under the ROC curve (AUCs) of 0.824, 0.853, and 0.810 in the 1-, 2-, and 3-year survival groups, respectively. This model also demonstrated remarkable discrimination in the external validation cohort, achieving AUCs of 0.862, 0.815, and 0.798 in the 1-, 2-, and 3-year survival groups, respectively. SHAP summary plots were also created to interpret the RSF model.Conclusion: An RSF model with good predictive performance was developed by incorporating simple parameters. This prognostic prediction model may assist physicians in early clinical intervention and improve prognosis outcomes in patients with HCC and comorbid T2DM after TACE.Keywords: hepatocellular carcinoma, type II diabetes mellitus, transarterial chemoembolization, overall survival, SHapley Additive exPlanationshttps://www.dovepress.com/a-machine-learning-model-for-predicting-prognosis-in-hcc-patients-with-peer-reviewed-fulltext-article-JHChepatocellular carcinomatype ii diabetes mellitustransarterial chemoembolizationoverall survivalshapley additive explanations. |
| spellingShingle | Wu L Chen L Zhang L Liu Y Ouyang D Wu W Lei Y Han P Zhao H Zheng C A Machine Learning Model for Predicting Prognosis in HCC Patients With Diabetes After TACE Journal of Hepatocellular Carcinoma hepatocellular carcinoma type ii diabetes mellitus transarterial chemoembolization overall survival shapley additive explanations. |
| title | A Machine Learning Model for Predicting Prognosis in HCC Patients With Diabetes After TACE |
| title_full | A Machine Learning Model for Predicting Prognosis in HCC Patients With Diabetes After TACE |
| title_fullStr | A Machine Learning Model for Predicting Prognosis in HCC Patients With Diabetes After TACE |
| title_full_unstemmed | A Machine Learning Model for Predicting Prognosis in HCC Patients With Diabetes After TACE |
| title_short | A Machine Learning Model for Predicting Prognosis in HCC Patients With Diabetes After TACE |
| title_sort | machine learning model for predicting prognosis in hcc patients with diabetes after tace |
| topic | hepatocellular carcinoma type ii diabetes mellitus transarterial chemoembolization overall survival shapley additive explanations. |
| url | https://www.dovepress.com/a-machine-learning-model-for-predicting-prognosis-in-hcc-patients-with-peer-reviewed-fulltext-article-JHC |
| work_keys_str_mv | AT wul amachinelearningmodelforpredictingprognosisinhccpatientswithdiabetesaftertace AT chenl amachinelearningmodelforpredictingprognosisinhccpatientswithdiabetesaftertace AT zhangl amachinelearningmodelforpredictingprognosisinhccpatientswithdiabetesaftertace AT liuy amachinelearningmodelforpredictingprognosisinhccpatientswithdiabetesaftertace AT ouyangd amachinelearningmodelforpredictingprognosisinhccpatientswithdiabetesaftertace AT wuw amachinelearningmodelforpredictingprognosisinhccpatientswithdiabetesaftertace AT leiy amachinelearningmodelforpredictingprognosisinhccpatientswithdiabetesaftertace AT hanp amachinelearningmodelforpredictingprognosisinhccpatientswithdiabetesaftertace AT zhaoh amachinelearningmodelforpredictingprognosisinhccpatientswithdiabetesaftertace AT zhengc amachinelearningmodelforpredictingprognosisinhccpatientswithdiabetesaftertace AT wul machinelearningmodelforpredictingprognosisinhccpatientswithdiabetesaftertace AT chenl machinelearningmodelforpredictingprognosisinhccpatientswithdiabetesaftertace AT zhangl machinelearningmodelforpredictingprognosisinhccpatientswithdiabetesaftertace AT liuy machinelearningmodelforpredictingprognosisinhccpatientswithdiabetesaftertace AT ouyangd machinelearningmodelforpredictingprognosisinhccpatientswithdiabetesaftertace AT wuw machinelearningmodelforpredictingprognosisinhccpatientswithdiabetesaftertace AT leiy machinelearningmodelforpredictingprognosisinhccpatientswithdiabetesaftertace AT hanp machinelearningmodelforpredictingprognosisinhccpatientswithdiabetesaftertace AT zhaoh machinelearningmodelforpredictingprognosisinhccpatientswithdiabetesaftertace AT zhengc machinelearningmodelforpredictingprognosisinhccpatientswithdiabetesaftertace |