Pengfei Tian
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Pengfei Tian has a total of 46 co-authors. Here are the top co-authors by number of shared publications:
- He Zhao
Department of Interventional Therapy, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Chaoyang District, Beijing, China
2 shared publications - Jingui Li
Department of Interventional Therapy, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Chaoyang District, Beijing, China
2 shared publications - Xiao Li
Department of Interventional Therapy, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100021, China
2 shared publications - Xiaowu Zhang
Department of Interventional Therapy, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
2 shared publications - Yingen Luo
Cancer Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing 100021, China
2 shared publications - Bai Cui
Institute of Cancer Stem Cell, Dalian Medical University, 9 West Section, Lvshun South Road, Dalian, Liaoning Province, 116044, China
1 shared publication
Latest Publications
- 20 November 2025
- Published by Springer Nature in Hepatology International
- Vol. 20 (2) , 428-440
Enhancing post-TIPS hepatic encephalopathy risk stratification: a hybrid TabPFN model leveraging radiomics, deep transfer learning features, and MELD score
Purpose Predicting hepatic encephalopathy (HE) after transjugular intrahepatic portosystemic shunt (TIPS) is critical for guiding portal hypertension treatment strategies and enabling early intervention. This study aims to employ the Tabular Prior-data Fitted Network (TabPFN) algorithm to develop a machine learning (ML) model that predicts post-TIPS HE. Methods This study retrospectively enrolled 218 patients who underwent TIPS across three hospitals. Preoperative contrast enhanced CT (CECT) scans were used to delineate the volumetric region of interest (VOI) for the liver, spleen, abdominal fat, and abdominal muscle. Radiomics and deep transfer learning (DTL) features were extracted from each VOI. Overt HE occurrence during follow-up was divided into two groups. 171 patients (two hospitals) were randomly split (7:3) into training and validation set, 47 patients (third hospital) formed an external test set. After feature selection, we trained and compared multiple ML models. Shapley additive explanation (SHAP) was performed for model interpretability. Results The overall incidence of overt HE in the study cohort was 20.6%. The combined TabPFN model with the best predictive performance achieved AUCs of 0.953 (training set), 0.870 (validation set), and 0.942 (external test set), with accuracies of 0.933, 0.846, and 0.872, respectively. SHAP analysis identified the liver radiomics signature as a dominant predictors. Time-dependent AUCs at 90, 180, 365, and 730 days exceeded 0.88 in all cohorts, and high-risk patients had significantly higher HE occurrence (p < 0.01). Conclusion A TabPFN-based ML model integrating CECT radiomics, DTL features, and MELD score enables accurate, externally validated prediction of post-TIPS HE, supporting personalized risk stratification and clinical decision-making.
- 20 November 2025
- Published by Springer Nature in Hepatology International
- Vol. 20 (2) , 428-440
Enhancing post-TIPS hepatic encephalopathy risk stratification: a hybrid TabPFN model leveraging radiomics, deep transfer learning features, and MELD score
Purpose Predicting hepatic encephalopathy (HE) after transjugular intrahepatic portosystemic shunt (TIPS) is critical for guiding portal hypertension treatment strategies and enabling early intervention. This study aims to employ the Tabular Prior-data Fitted Network (TabPFN) algorithm to develop a machine learning (ML) model that predicts post-TIPS HE. Methods This study retrospectively enrolled 218 patients who underwent TIPS across three hospitals. Preoperative contrast enhanced CT (CECT) scans were used to delineate the volumetric region of interest (VOI) for the liver, spleen, abdominal fat, and abdominal muscle. Radiomics and deep transfer learning (DTL) features were extracted from each VOI. Overt HE occurrence during follow-up was divided into two groups. 171 patients (two hospitals) were randomly split (7:3) into training and validation set, 47 patients (third hospital) formed an external test set. After feature selection, we trained and compared multiple ML models. Shapley additive explanation (SHAP) was performed for model interpretability. Results The overall incidence of overt HE in the study cohort was 20.6%. The combined TabPFN model with the best predictive performance achieved AUCs of 0.953 (training set), 0.870 (validation set), and 0.942 (external test set), with accuracies of 0.933, 0.846, and 0.872, respectively. SHAP analysis identified the liver radiomics signature as a dominant predictors. Time-dependent AUCs at 90, 180, 365, and 730 days exceeded 0.88 in all cohorts, and high-risk patients had significantly higher HE occurrence (p < 0.01). Conclusion A TabPFN-based ML model integrating CECT radiomics, DTL features, and MELD score enables accurate, externally validated prediction of post-TIPS HE, supporting personalized risk stratification and clinical decision-making.
- Open Access
Hepatic arterial infusion chemotherapy plus regorafenib compared with regorafenib alone as second-line therapy for advanced hepatocellular carcinoma: a randomised controlled trial protocol
Introduction The exact role of hepatic arterial infusion chemotherapy (HAIC) in advanced hepatocellular carcinoma (aHCC) is still unknown. The combination of HAIC and sorafenib has been proven to be more effective than sorafenib alone in the first-line treatment of aHCC. The aim of the study is to evaluate the efficacy and safety of HAIC plus regorafenib in the second-line treatment of aHCC. Methods and analysis This is a multicenter, open-label, randomised controlled phase III trial. A total of 294 patients with aHCC, who are unable to tolerate the first-line systemic therapy or progress after the first-line systemic therapy, will be enrolled in the study. The patients will be randomly (2:1) assigned into the combination treatment group (HAIC plus regorafenib, n=196) and the control group (regorafenib alone, n=98). HAIC and regorafenib (160 mg/day) will be given in a 4-week cycle. The primary endpoint is overall survival in the intention-to-treat population. The second endpoints include progression-free survival, overall response rate, time to progression, etc. The radiological assessments will be based on the criteria of Response Evaluation Criteria in Solid Tumors 1.1. Ethics and dissemination This study is approved by the ethics committee of Cancer Hospital, Chinese Academy of Medical Sciences. All participants are required to provide written informed consent. The results of this study will be disseminated through peer-reviewed publications and esteemed academic conferences. Trial registration number Chinese Clinical Trial Registry (ChiCTR2300073075).
Open AccessHepatic arterial infusion chemotherapy plus regorafenib compared with regorafenib alone as second-line therapy for advanced hepatocellular carcinoma: a randomised controlled trial protocol
Introduction The exact role of hepatic arterial infusion chemotherapy (HAIC) in advanced hepatocellular carcinoma (aHCC) is still unknown. The combination of HAIC and sorafenib has been proven to be more effective than sorafenib alone in the first-line treatment of aHCC. The aim of the study is to evaluate the efficacy and safety of HAIC plus regorafenib in the second-line treatment of aHCC. Methods and analysis This is a multicenter, open-label, randomised controlled phase III trial. A total of 294 patients with aHCC, who are unable to tolerate the first-line systemic therapy or progress after the first-line systemic therapy, will be enrolled in the study. The patients will be randomly (2:1) assigned into the combination treatment group (HAIC plus regorafenib, n=196) and the control group (regorafenib alone, n=98). HAIC and regorafenib (160 mg/day) will be given in a 4-week cycle. The primary endpoint is overall survival in the intention-to-treat population. The second endpoints include progression-free survival, overall response rate, time to progression, etc. The radiological assessments will be based on the criteria of Response Evaluation Criteria in Solid Tumors 1.1. Ethics and dissemination This study is approved by the ethics committee of Cancer Hospital, Chinese Academy of Medical Sciences. All participants are required to provide written informed consent. The results of this study will be disseminated through peer-reviewed publications and esteemed academic conferences. Trial registration number Chinese Clinical Trial Registry (ChiCTR2300073075).
- Open Access
- 28 January 2019
- Published by American Society for Clinical Investigation in Journal of Clinical Investigation
- Vol. 129 (3) , 1030-1046
Stress-induced epinephrine enhances lactate dehydrogenase A and promotes breast cancer stem-like cells
Chronic stress triggers activation of the sympathetic nervous system and drives malignancy. Using an immunodeficient murine system, we showed that chronic stress–induced epinephrine promoted breast cancer stem-like properties via lactate dehydrogenase A–dependent (LDHA-dependent) metabolic rewiring. Chronic stress–induced epinephrine activated LDHA to generate lactate, and the adjusted pH directed USP28-mediated deubiquitination and stabilization of MYC. The SLUG promoter was then activated by MYC, which promoted development of breast cancer stem-like traits. Using a drug screen that targeted LDHA, we found that a chronic stress–induced cancer stem-like phenotype could be reversed by vitamin C. These findings demonstrated the critical importance of psychological factors in promoting stem-like properties in breast cancer cells. Thus, the LDHA-lowering agent vitamin C can be a potential approach for combating stress-associated breast cancer.
- 28 January 2019
- Published by American Society for Clinical Investigation in Journal of Clinical Investigation
- Vol. 129 (3) , 1030-1046
Open AccessStress-induced epinephrine enhances lactate dehydrogenase A and promotes breast cancer stem-like cells
Chronic stress triggers activation of the sympathetic nervous system and drives malignancy. Using an immunodeficient murine system, we showed that chronic stress–induced epinephrine promoted breast cancer stem-like properties via lactate dehydrogenase A–dependent (LDHA-dependent) metabolic rewiring. Chronic stress–induced epinephrine activated LDHA to generate lactate, and the adjusted pH directed USP28-mediated deubiquitination and stabilization of MYC. The SLUG promoter was then activated by MYC, which promoted development of breast cancer stem-like traits. Using a drug screen that targeted LDHA, we found that a chronic stress–induced cancer stem-like phenotype could be reversed by vitamin C. These findings demonstrated the critical importance of psychological factors in promoting stem-like properties in breast cancer cells. Thus, the LDHA-lowering agent vitamin C can be a potential approach for combating stress-associated breast cancer.