Ying Jiang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ying Jiang has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Ningping Zhang
Department of Gastroenterology and Hepatology Zhongshan Hospital, Fudan University Shanghai China
2 shared publications - Ranyi Li
Department of Pharmacy, Zhongshan Hospital, Fudan University, 180 Fenglin Road, Shanghai 200032, China
2 shared publications Xiaoyu Li
Department of Clinical Pharmacology, Zhongshan Hospital, Fudan University, Shanghai 200032, China
2 shared publications- Xiaoyu Li
Department of Pharmacy, Zhongshan Hospital, Fudan University, Shanghai 200032, China
2 shared publications - Hong Gao
Department of Gastroenterology and Hepatology, Zhongshan Hospital, Fudan University, Shanghai, China
1 shared publication Minzhi Lv
Department of Biostatistics Zhongshan Hospital, Fudan University Shanghai China
1 shared publication
Latest Publications
- Open Access
- 20 September 2026
- Published by MDPI AG in Current Oncology
- Vol. 33 (9) , 568
Prediction of Immune Checkpoint Inhibitor-Induced Liver Injury in Patients with Gastrointestinal Cancer: Machine Learning Modeling for Time-Stratified Risk Assessment
Background: Immunotherapy has transformed cancer treatment and is widely used in the Chinese mainland. Though advances have been made, immune checkpoint inhibitor-related liver injury (ICILI) remains a significant clinical challenge. Existing risk models commonly lack time-specific risk stratification for ICILI. The present study aimed to develop and validate interpretable machine learning models to predict grade 2 or higher ICILI at multiple time points in patients with gastrointestinal cancer (GC). Methods: This retrospective cohort study encompassed GC patients who commenced their initial ICI medication between January 2019 and June 2023 at Zhongshan Hospital, Fudan University. Five machine learning algorithms, including Logistic Regression, Random Forest, Extreme Gradient Boosting (XGBoost), Gradient Boosting (GradientBoost), and Adaptive Boosting (AdaBoost), were utilized to develop predictive models for grade ≥ 2 ICILI at specific intervals of 3 months, 6 months, and 12 months. The evaluation of model performance was conducted using the area under the curve (AUC), accuracy, precision, recall, and F1-score. The Shapley Additive exPlanations (SHAP) method was employed to assess feature importance and interpret the final model. Results: A total of 1337, 849, and 401 patients were enrolled in the follow-up groups at 3 months, 6 months, and 12 months. The final model for grade ≥ 2 ICILI was developed with GradientBoost and achieved an AUC of 0.769 (95% CI: 0.732–0.806), with a test set accuracy of 0.834. XGBoost yielded AUCs of 0.671 (95% CI: 0.636–0.706) at 3-month indication, 0.678 (95% CI: 0.638–0.718) at 6 months, and 0.644 (95% CI: 0.589–0.699) at 12-month follow-up in the 5-fold cross-validation. The DCA curve demonstrated solid clinical benefit, whereas the calibration curve indicated good predictive reliability. SHAP analysis identified several parameters as predictive features at different intervals, which suggested that the ICILI determinants varied from acute inflammatory to host-related characteristics. Conclusions: A temporal stratification prediction model for grade ≥ 2 ICILI in GC patients was developed and validated at various intervals using ML algorithms with SHAP interpretability. This methodology facilitated early recognition of varying parameters across different treatment phases, enhancing clinical management and elevating treatment outcomes.
- 20 September 2026
- Published by MDPI AG in Current Oncology
- Vol. 33 (9) , 568
Open AccessPrediction of Immune Checkpoint Inhibitor-Induced Liver Injury in Patients with Gastrointestinal Cancer: Machine Learning Modeling for Time-Stratified Risk Assessment
Background: Immunotherapy has transformed cancer treatment and is widely used in the Chinese mainland. Though advances have been made, immune checkpoint inhibitor-related liver injury (ICILI) remains a significant clinical challenge. Existing risk models commonly lack time-specific risk stratification for ICILI. The present study aimed to develop and validate interpretable machine learning models to predict grade 2 or higher ICILI at multiple time points in patients with gastrointestinal cancer (GC). Methods: This retrospective cohort study encompassed GC patients who commenced their initial ICI medication between January 2019 and June 2023 at Zhongshan Hospital, Fudan University. Five machine learning algorithms, including Logistic Regression, Random Forest, Extreme Gradient Boosting (XGBoost), Gradient Boosting (GradientBoost), and Adaptive Boosting (AdaBoost), were utilized to develop predictive models for grade ≥ 2 ICILI at specific intervals of 3 months, 6 months, and 12 months. The evaluation of model performance was conducted using the area under the curve (AUC), accuracy, precision, recall, and F1-score. The Shapley Additive exPlanations (SHAP) method was employed to assess feature importance and interpret the final model. Results: A total of 1337, 849, and 401 patients were enrolled in the follow-up groups at 3 months, 6 months, and 12 months. The final model for grade ≥ 2 ICILI was developed with GradientBoost and achieved an AUC of 0.769 (95% CI: 0.732–0.806), with a test set accuracy of 0.834. XGBoost yielded AUCs of 0.671 (95% CI: 0.636–0.706) at 3-month indication, 0.678 (95% CI: 0.638–0.718) at 6 months, and 0.644 (95% CI: 0.589–0.699) at 12-month follow-up in the 5-fold cross-validation. The DCA curve demonstrated solid clinical benefit, whereas the calibration curve indicated good predictive reliability. SHAP analysis identified several parameters as predictive features at different intervals, which suggested that the ICILI determinants varied from acute inflammatory to host-related characteristics. Conclusions: A temporal stratification prediction model for grade ≥ 2 ICILI in GC patients was developed and validated at various intervals using ML algorithms with SHAP interpretability. This methodology facilitated early recognition of varying parameters across different treatment phases, enhancing clinical management and elevating treatment outcomes.
- Open Access
- 13 November 2024
- Published by MDPI AG in Current Oncology
- Vol. 31 (11) , 7129-7143
Risk Factors of Immune-Mediated Hepatotoxicity Induced by Immune Checkpoint Inhibitors in Cancer Patients: A Systematic Review and Meta-Analysis
Immune checkpoint inhibitors (ICIs) significantly improve survival, while immune-mediated hepatotoxicity (IMH) has been reported. To evaluate the incidence and potential risk factors of IMH among cancer patients treated by ICIs, PubMed/Medline, Web of Science, Cochrane, and Embase were searched before 30 March 2024 for systematic review and meta-analysis. Odds ratios (ORs) with 95% confidence intervals (CI) were calculated. Quality assessment was completed using the Newcastle–Ottawa scale. Of 1217 articles identified, 24 consisting of 9076 patients were included, with one study being prospective and the rest retrospective. The overall incidence of any grade IMH and grade ≥ 3 secondary to ICIs was 14% and 7%, respectively. The cholestatic pattern was more prevalent than the hepatocellular and mixed patterns. The meta-analysis revealed that ICI treatment was related to reduced risk of IMH in older patients (SMD: −0.18; 95% CI: −0.33 to −0.04), individuals with higher body mass index (WMD: −2.15; 95% CI: −3.92 to −0.38), males (OR: 0.44; 95% CI: 0.27 to 0.72), and patients with lung cancer (OR: 0.58, 95%CI 0.41 to 0.83). On the other hand, patients with liver metastasis (OR: 1.80; 95% CI: 1.47 to 2.20), history of ICI treatment (OR: 3.09; 95% CI: 1.21 to 7.89), diabetes (OR: 2.19; 95% CI: 1.36 to 3.51), chronic HBV (OR: 3.06; 95% CI: 1.11 to 8.46), and concomitant use of ICIs (OR: 8.73; 95% CI: 2.41 to 31.59) increased the risk of developing IMH. This study will provide clinicians with information on potentially high-risk groups for IMH, who need to be cautiously monitored for liver function when receiving immunotherapy.
- 13 November 2024
- Published by MDPI AG in Current Oncology
- Vol. 31 (11) , 7129-7143
Open AccessRisk Factors of Immune-Mediated Hepatotoxicity Induced by Immune Checkpoint Inhibitors in Cancer Patients: A Systematic Review and Meta-Analysis
Immune checkpoint inhibitors (ICIs) significantly improve survival, while immune-mediated hepatotoxicity (IMH) has been reported. To evaluate the incidence and potential risk factors of IMH among cancer patients treated by ICIs, PubMed/Medline, Web of Science, Cochrane, and Embase were searched before 30 March 2024 for systematic review and meta-analysis. Odds ratios (ORs) with 95% confidence intervals (CI) were calculated. Quality assessment was completed using the Newcastle–Ottawa scale. Of 1217 articles identified, 24 consisting of 9076 patients were included, with one study being prospective and the rest retrospective. The overall incidence of any grade IMH and grade ≥ 3 secondary to ICIs was 14% and 7%, respectively. The cholestatic pattern was more prevalent than the hepatocellular and mixed patterns. The meta-analysis revealed that ICI treatment was related to reduced risk of IMH in older patients (SMD: −0.18; 95% CI: −0.33 to −0.04), individuals with higher body mass index (WMD: −2.15; 95% CI: −3.92 to −0.38), males (OR: 0.44; 95% CI: 0.27 to 0.72), and patients with lung cancer (OR: 0.58, 95%CI 0.41 to 0.83). On the other hand, patients with liver metastasis (OR: 1.80; 95% CI: 1.47 to 2.20), history of ICI treatment (OR: 3.09; 95% CI: 1.21 to 7.89), diabetes (OR: 2.19; 95% CI: 1.36 to 3.51), chronic HBV (OR: 3.06; 95% CI: 1.11 to 8.46), and concomitant use of ICIs (OR: 8.73; 95% CI: 2.41 to 31.59) increased the risk of developing IMH. This study will provide clinicians with information on potentially high-risk groups for IMH, who need to be cautiously monitored for liver function when receiving immunotherapy.
- Open Access
- 28 July 2024
- Published by Elsevier in Biochemical Pharmacology
- Vol. 227, 116456
Furanodienone induces apoptosis via regulating the PRDX1/MAPKs/p53/caspases signaling axis through NOX4-derived mitochondrial ROS in colorectal cancer cells
- 28 July 2024
- Published by Elsevier in Biochemical Pharmacology
- Vol. 227, 116456
Open AccessFuranodienone induces apoptosis via regulating the PRDX1/MAPKs/p53/caspases signaling axis through NOX4-derived mitochondrial ROS in colorectal cancer cells
- 23 July 2024
- Published by Wiley in British Journal of Clinical Pharmacology
- Vol. 90 (11) , 2870-2882
Clinical characteristics and prognosis of liver injury induced by immune checkpoint inhibitors in patients with malignancies: A real‐world retrospective study
Aims: Programmed cell death receptor (ligand)‐1 inhibitors (PD‐(L)1), as the preferred immunotherapy, have been widely used in the Chinese mainland and drug‐induced liver injury (DILI) has been reported. The study aimed to investigate the clinical features or risk factors for immunotherapy‐related DILI.Methods: Patients who received PD‐(L)1 inhibitors from January 2020 to July 2021 were retrospectively reviewed. The likelihood of DILI was adjudicated by the Roussel‐Uclaf causality assessment.Results: A total of 1175 patients were included in the study and 89 patients (7.6%) developed DILI, of which 12 (13.5%) progressed to acute liver failure (ALF) and three (3.4%) died. Among the DILI population, 56 (62.9%) had a cholestatic pattern and exhibited a prolonged treatment course and duration for resolution compared to the hepatocellular and mixed patterns. Hepatocellular carcinoma (HCC), hepatitis B virus (HBV) and abnormal baseline of alkaline phosphatase (ALP) had increased risks of DILI by 2.1‐fold (95% confidence interval [CI], 1.231–3.621), 1.9‐fold [95% CI, 1.123–3.325] and 2.1‐fold [95% CI, 1.317–3.508], respectively. The model for end‐stage liver disease (MELD) score had a c‐statistic of 0.894 (95% CI, 0.778–1.000) with a sensitivity of 67% and a specificity of 95% for poor outcomes. COX analysis showed that the MELD ≥ 18 was predictive of immunotherapy‐related ALF or death.Conclusions: PD‐(L)1 inhibitor‐related liver injury manifests primarily as a cholestatic pattern, on which corticosteroid treatment has minimal effect compared to hepatocellular and mixed patterns. MELD score ≥ 18 at the time of liver injury performed best in the prediction of ALF or death in immune checkpoint inhibitor (ICI)‐related DILI.
- 23 July 2024
- Published by Wiley in British Journal of Clinical Pharmacology
- Vol. 90 (11) , 2870-2882
Clinical characteristics and prognosis of liver injury induced by immune checkpoint inhibitors in patients with malignancies: A real‐world retrospective study
Aims: Programmed cell death receptor (ligand)‐1 inhibitors (PD‐(L)1), as the preferred immunotherapy, have been widely used in the Chinese mainland and drug‐induced liver injury (DILI) has been reported. The study aimed to investigate the clinical features or risk factors for immunotherapy‐related DILI.Methods: Patients who received PD‐(L)1 inhibitors from January 2020 to July 2021 were retrospectively reviewed. The likelihood of DILI was adjudicated by the Roussel‐Uclaf causality assessment.Results: A total of 1175 patients were included in the study and 89 patients (7.6%) developed DILI, of which 12 (13.5%) progressed to acute liver failure (ALF) and three (3.4%) died. Among the DILI population, 56 (62.9%) had a cholestatic pattern and exhibited a prolonged treatment course and duration for resolution compared to the hepatocellular and mixed patterns. Hepatocellular carcinoma (HCC), hepatitis B virus (HBV) and abnormal baseline of alkaline phosphatase (ALP) had increased risks of DILI by 2.1‐fold (95% confidence interval [CI], 1.231–3.621), 1.9‐fold [95% CI, 1.123–3.325] and 2.1‐fold [95% CI, 1.317–3.508], respectively. The model for end‐stage liver disease (MELD) score had a c‐statistic of 0.894 (95% CI, 0.778–1.000) with a sensitivity of 67% and a specificity of 95% for poor outcomes. COX analysis showed that the MELD ≥ 18 was predictive of immunotherapy‐related ALF or death.Conclusions: PD‐(L)1 inhibitor‐related liver injury manifests primarily as a cholestatic pattern, on which corticosteroid treatment has minimal effect compared to hepatocellular and mixed patterns. MELD score ≥ 18 at the time of liver injury performed best in the prediction of ALF or death in immune checkpoint inhibitor (ICI)‐related DILI.