A Machine Learning Model Based on Health Records for Predicting Recurrence After Microwave Ablation of Hepatocellular Carcinoma
Chao An,1,* Hongcai Yang,1,2,* Xiaoling Yu,1 Zhi-Yu Han,1 Zhigang Cheng,1 Fangyi Liu,1 Jianping Dou,1 Bing Li,3 Yansheng Li,4 Yichao Li,4 Jie Yu,1 Ping Liang1 1Department of Ultrasound, PLA Medical College & 5th Medical Center of Chinese PLA General Hospital, Beijing, 100853, Peo...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Dove Medical Press
2022-07-01
|
| Series: | Journal of Hepatocellular Carcinoma |
| Subjects: | |
| Online Access: | https://www.dovepress.com/a-machine-learning-model-based-on-health-records-for-predicting-recurr-peer-reviewed-fulltext-article-JHC |
| _version_ | 1818162001199759360 |
|---|---|
| author | An C Yang H Yu X Han Z Cheng Z Liu F Dou J Li B Li Y Li Y Yu J Liang P |
| author_facet | An C Yang H Yu X Han Z Cheng Z Liu F Dou J Li B Li Y Li Y Yu J Liang P |
| author_sort | An C |
| collection | DOAJ |
| description | Chao An,1,* Hongcai Yang,1,2,* Xiaoling Yu,1 Zhi-Yu Han,1 Zhigang Cheng,1 Fangyi Liu,1 Jianping Dou,1 Bing Li,3 Yansheng Li,4 Yichao Li,4 Jie Yu,1 Ping Liang1 1Department of Ultrasound, PLA Medical College & 5th Medical Center of Chinese PLA General Hospital, Beijing, 100853, People’s Republic of China; 2School of Medicine, Nankai University, Tianjin, People’s Republic of China; 3National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences, Beijing, People’s Republic of China; 4DHC Mediway Technology CO, Ltd, Beijing, People’s Republic of China*These authors contributed equally to this workCorrespondence: Ping Liang; Jie Yu, Department of Ultrasound, PLA Medical College & 5th Medical Center of Chinese PLA General Hospital, Beijing, 100853, People’s Republic of China, Tel +86-10-66939530, Fax +86-10-68161218, Email liangping301@126.com; yu-jie301@hotmail.comBackground and Aim: Early recurrence (ER) presents a challenge for the survival prognosis of patients with hepatocellular carcinoma (HCC). The aim of this study was to investigate machine learning (ML) models using clinical data for predicting ER after microwave ablation (MWA).Methods: Between August 2005 and December 2019, 1574 patients with early-stage HCC underwent MWA at four hospitals were reviewed. Then, 36 clinical data points per patient were collected, and the patients were assigned to the training, internal, and external validation set. Apart from traditional logistic regression (LR), three ML models—random forest, support vector machine, and eXtreme Gradient Boosting (XGBoost)—were built and validated for their predictive ability with the area under ROC curve (AUC). Algorithms such as SHapley Additive exPlanations (SHAP) and local interpretable model-agnostic explanations (LIME) were used to realize their interpretability.Results: The three ML models all outperformed LR (P < 0.001 for all) in predictive ability. When nine variables (tumor number, platelet, α-fetoprotein, comorbidity score, white blood cell, cholinesterase, prothrombin time, neutrophils, and etiology) were extracted simultaneously using recursive feature elimination with cross-validation, the XGBoost model achieved the best discrimination among all models, with an AUC value 0.75 (95% CI [confidence interval]: 0.72– 0.78) in the training set, 0.74 (95% CI: 0.69– 0.80) in the internal validation set, and 0.76 (95% CI: 0.70– 0.82) in the external validation set, and it was interpreted depending on the visualization of risk factors by the SHAP and LIME algorithms. The predictive system of post-ablation recurrence risk stratification was provided on online (http://114.251.235.51:8001/) based on XGboost analysis.Conclusion: The XGBoost model based on clinical data can effectively predict ER risk after MWA, which can contribute to surveillance, prevention, and treatment strategies for HCC.Keywords: microwave ablation, hepatocellular carcinoma, recurrence, machine learning, risk stratification |
| first_indexed | 2024-12-11T16:26:43Z |
| format | Article |
| id | doaj.art-739d6cabe1c8449bbaba2fbe02ffb29e |
| institution | Directory Open Access Journal |
| issn | 2253-5969 |
| language | English |
| last_indexed | 2024-12-11T16:26:43Z |
| publishDate | 2022-07-01 |
| publisher | Dove Medical Press |
| record_format | Article |
| series | Journal of Hepatocellular Carcinoma |
| spelling | doaj.art-739d6cabe1c8449bbaba2fbe02ffb29e2022-12-22T00:58:41ZengDove Medical PressJournal of Hepatocellular Carcinoma2253-59692022-07-01Volume 967168476896A Machine Learning Model Based on Health Records for Predicting Recurrence After Microwave Ablation of Hepatocellular CarcinomaAn CYang HYu XHan ZCheng ZLiu FDou JLi BLi YLi YYu JLiang PChao An,1,* Hongcai Yang,1,2,* Xiaoling Yu,1 Zhi-Yu Han,1 Zhigang Cheng,1 Fangyi Liu,1 Jianping Dou,1 Bing Li,3 Yansheng Li,4 Yichao Li,4 Jie Yu,1 Ping Liang1 1Department of Ultrasound, PLA Medical College & 5th Medical Center of Chinese PLA General Hospital, Beijing, 100853, People’s Republic of China; 2School of Medicine, Nankai University, Tianjin, People’s Republic of China; 3National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences, Beijing, People’s Republic of China; 4DHC Mediway Technology CO, Ltd, Beijing, People’s Republic of China*These authors contributed equally to this workCorrespondence: Ping Liang; Jie Yu, Department of Ultrasound, PLA Medical College & 5th Medical Center of Chinese PLA General Hospital, Beijing, 100853, People’s Republic of China, Tel +86-10-66939530, Fax +86-10-68161218, Email liangping301@126.com; yu-jie301@hotmail.comBackground and Aim: Early recurrence (ER) presents a challenge for the survival prognosis of patients with hepatocellular carcinoma (HCC). The aim of this study was to investigate machine learning (ML) models using clinical data for predicting ER after microwave ablation (MWA).Methods: Between August 2005 and December 2019, 1574 patients with early-stage HCC underwent MWA at four hospitals were reviewed. Then, 36 clinical data points per patient were collected, and the patients were assigned to the training, internal, and external validation set. Apart from traditional logistic regression (LR), three ML models—random forest, support vector machine, and eXtreme Gradient Boosting (XGBoost)—were built and validated for their predictive ability with the area under ROC curve (AUC). Algorithms such as SHapley Additive exPlanations (SHAP) and local interpretable model-agnostic explanations (LIME) were used to realize their interpretability.Results: The three ML models all outperformed LR (P < 0.001 for all) in predictive ability. When nine variables (tumor number, platelet, α-fetoprotein, comorbidity score, white blood cell, cholinesterase, prothrombin time, neutrophils, and etiology) were extracted simultaneously using recursive feature elimination with cross-validation, the XGBoost model achieved the best discrimination among all models, with an AUC value 0.75 (95% CI [confidence interval]: 0.72– 0.78) in the training set, 0.74 (95% CI: 0.69– 0.80) in the internal validation set, and 0.76 (95% CI: 0.70– 0.82) in the external validation set, and it was interpreted depending on the visualization of risk factors by the SHAP and LIME algorithms. The predictive system of post-ablation recurrence risk stratification was provided on online (http://114.251.235.51:8001/) based on XGboost analysis.Conclusion: The XGBoost model based on clinical data can effectively predict ER risk after MWA, which can contribute to surveillance, prevention, and treatment strategies for HCC.Keywords: microwave ablation, hepatocellular carcinoma, recurrence, machine learning, risk stratificationhttps://www.dovepress.com/a-machine-learning-model-based-on-health-records-for-predicting-recurr-peer-reviewed-fulltext-article-JHCmicrowave ablationhepatocellular carcinomarecurrencemachine learningrisk stratification |
| spellingShingle | An C Yang H Yu X Han Z Cheng Z Liu F Dou J Li B Li Y Li Y Yu J Liang P A Machine Learning Model Based on Health Records for Predicting Recurrence After Microwave Ablation of Hepatocellular Carcinoma Journal of Hepatocellular Carcinoma microwave ablation hepatocellular carcinoma recurrence machine learning risk stratification |
| title | A Machine Learning Model Based on Health Records for Predicting Recurrence After Microwave Ablation of Hepatocellular Carcinoma |
| title_full | A Machine Learning Model Based on Health Records for Predicting Recurrence After Microwave Ablation of Hepatocellular Carcinoma |
| title_fullStr | A Machine Learning Model Based on Health Records for Predicting Recurrence After Microwave Ablation of Hepatocellular Carcinoma |
| title_full_unstemmed | A Machine Learning Model Based on Health Records for Predicting Recurrence After Microwave Ablation of Hepatocellular Carcinoma |
| title_short | A Machine Learning Model Based on Health Records for Predicting Recurrence After Microwave Ablation of Hepatocellular Carcinoma |
| title_sort | machine learning model based on health records for predicting recurrence after microwave ablation of hepatocellular carcinoma |
| topic | microwave ablation hepatocellular carcinoma recurrence machine learning risk stratification |
| url | https://www.dovepress.com/a-machine-learning-model-based-on-health-records-for-predicting-recurr-peer-reviewed-fulltext-article-JHC |
| work_keys_str_mv | AT anc amachinelearningmodelbasedonhealthrecordsforpredictingrecurrenceaftermicrowaveablationofhepatocellularcarcinoma AT yangh amachinelearningmodelbasedonhealthrecordsforpredictingrecurrenceaftermicrowaveablationofhepatocellularcarcinoma AT yux amachinelearningmodelbasedonhealthrecordsforpredictingrecurrenceaftermicrowaveablationofhepatocellularcarcinoma AT hanz amachinelearningmodelbasedonhealthrecordsforpredictingrecurrenceaftermicrowaveablationofhepatocellularcarcinoma AT chengz amachinelearningmodelbasedonhealthrecordsforpredictingrecurrenceaftermicrowaveablationofhepatocellularcarcinoma AT liuf amachinelearningmodelbasedonhealthrecordsforpredictingrecurrenceaftermicrowaveablationofhepatocellularcarcinoma AT douj amachinelearningmodelbasedonhealthrecordsforpredictingrecurrenceaftermicrowaveablationofhepatocellularcarcinoma AT lib amachinelearningmodelbasedonhealthrecordsforpredictingrecurrenceaftermicrowaveablationofhepatocellularcarcinoma AT liy amachinelearningmodelbasedonhealthrecordsforpredictingrecurrenceaftermicrowaveablationofhepatocellularcarcinoma AT liy amachinelearningmodelbasedonhealthrecordsforpredictingrecurrenceaftermicrowaveablationofhepatocellularcarcinoma AT yuj amachinelearningmodelbasedonhealthrecordsforpredictingrecurrenceaftermicrowaveablationofhepatocellularcarcinoma AT liangp amachinelearningmodelbasedonhealthrecordsforpredictingrecurrenceaftermicrowaveablationofhepatocellularcarcinoma AT anc machinelearningmodelbasedonhealthrecordsforpredictingrecurrenceaftermicrowaveablationofhepatocellularcarcinoma AT yangh machinelearningmodelbasedonhealthrecordsforpredictingrecurrenceaftermicrowaveablationofhepatocellularcarcinoma AT yux machinelearningmodelbasedonhealthrecordsforpredictingrecurrenceaftermicrowaveablationofhepatocellularcarcinoma AT hanz machinelearningmodelbasedonhealthrecordsforpredictingrecurrenceaftermicrowaveablationofhepatocellularcarcinoma AT chengz machinelearningmodelbasedonhealthrecordsforpredictingrecurrenceaftermicrowaveablationofhepatocellularcarcinoma AT liuf machinelearningmodelbasedonhealthrecordsforpredictingrecurrenceaftermicrowaveablationofhepatocellularcarcinoma AT douj machinelearningmodelbasedonhealthrecordsforpredictingrecurrenceaftermicrowaveablationofhepatocellularcarcinoma AT lib machinelearningmodelbasedonhealthrecordsforpredictingrecurrenceaftermicrowaveablationofhepatocellularcarcinoma AT liy machinelearningmodelbasedonhealthrecordsforpredictingrecurrenceaftermicrowaveablationofhepatocellularcarcinoma AT liy machinelearningmodelbasedonhealthrecordsforpredictingrecurrenceaftermicrowaveablationofhepatocellularcarcinoma AT yuj machinelearningmodelbasedonhealthrecordsforpredictingrecurrenceaftermicrowaveablationofhepatocellularcarcinoma AT liangp machinelearningmodelbasedonhealthrecordsforpredictingrecurrenceaftermicrowaveablationofhepatocellularcarcinoma |