Chengjing Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Chengjing Zhang has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- Bo Xu
School of Management Fudan University 670, Guoshun Road Shanghai 200433 China
1 shared publication Chenghu Liu
Naval Med Univ, Second Mil Med Univ, Eastern Hepatobiliary Surg Hosp, Dept Hepat Surg 3, 225 Changhai Rd, Shanghai 200438, Peoples R China
1 shared publication- Dong Wei
Department of Endocrinology and Metabolism, Diabetic Foot Care Center, Chengdu Second People’s Hospital, Chengdu, 610017, People’s Republic of China
1 shared publication Feiyang Ye
Naval Med Univ, Second Mil Med Univ, Eastern Hepatobiliary Surg Hosp, Dept Hepat Surg 3, 225 Changhai Rd, Shanghai 200438, Peoples R China
1 shared publicationGaowei Yang
Naval Med Univ, Second Mil Med Univ, Eastern Hepatobiliary Surg Hosp, Dept Hepat Surg 3, 225 Changhai Rd, Shanghai 200438, Peoples R China
1 shared publicationHua Yu
Department of Pathology, Eastern Hepatobiliary Surgery Hospital, Second Military Medical University, Naval Medical University, Shanghai, China
1 shared publication
Latest Publications
- Open Access
- 25 August 2025
- Published by Springer Nature in BMC Medical Research Methodology
- Vol. 25 (1) , 1-8
Artificial intelligence for the science of evidence synthesis: how good are AI-powered tools for automatic literature screening?
Background: Literature screening constitutes a critical component in evidence synthesis; however, it typically requires substantial time and human resources. Artificial intelligence (AI) has shown promise in this field, yet the accuracy and effectiveness of AI tools for literature screening remain uncertain. This study aims to evaluate the performance of several existing AI-powered automated tools for literature screening. Methods: This diagnostic accuracy study employed a cohort to evaluate the performance of five AI tools—ChatGPT 4.0, Claude 3.5, Gemini 1.5, DeepSeek-V3, and RobotSearch—in literature screening. We selected a random sample of 1,000 publications from a well-established literature cohort, with 500 as randomized controlled trials (RCTs) group and 500 as others group. Diagnostic accuracy was measured using several metrics, including the false negative fraction (FNF), time used for screening, false positive fraction (FPF), and the redundancy number needed to screen. Results: We reported the FNF for the RCTs group and the FPF for the others group. In the RCTs group, RobotSearch exhibited the lowest FNF at 6.4% (95% CI: 4.6% to 8.9%), whereas Gemini exhibited the highest at 13.0% (95% CI: 10.3% to 16.3%). In the others group, the FPF of the four large language models ranged from 2.8% (95% CI: 1.7% to 4.7%) to 3.8% (95% CI: 2.4% to 5.9%), both of which were significantly lower than RobotSearch's rate of 22.2% (95% CI: 18.8% to 26.1%). In terms of screening efficiency, the mean time used for screening per article was 1.3 s for ChatGPT, 6.0 s for Claude, 1.2 s for Gemini, and 2.6 s for DeepSeek. Conclusions: The AI tools assessed in this study demonstrated commendable performance in literature screening; however, they are not yet suitable as standalone solutions. These tools can serve as effective auxiliary aids, and a hybrid approach that integrates human expertise with AI may enhance both the efficiency and accuracy of the literature screening process. Graphical
- 25 August 2025
- Published by Springer Nature in BMC Medical Research Methodology
- Vol. 25 (1) , 1-8
Open AccessArtificial intelligence for the science of evidence synthesis: how good are AI-powered tools for automatic literature screening?
Background: Literature screening constitutes a critical component in evidence synthesis; however, it typically requires substantial time and human resources. Artificial intelligence (AI) has shown promise in this field, yet the accuracy and effectiveness of AI tools for literature screening remain uncertain. This study aims to evaluate the performance of several existing AI-powered automated tools for literature screening. Methods: This diagnostic accuracy study employed a cohort to evaluate the performance of five AI tools—ChatGPT 4.0, Claude 3.5, Gemini 1.5, DeepSeek-V3, and RobotSearch—in literature screening. We selected a random sample of 1,000 publications from a well-established literature cohort, with 500 as randomized controlled trials (RCTs) group and 500 as others group. Diagnostic accuracy was measured using several metrics, including the false negative fraction (FNF), time used for screening, false positive fraction (FPF), and the redundancy number needed to screen. Results: We reported the FNF for the RCTs group and the FPF for the others group. In the RCTs group, RobotSearch exhibited the lowest FNF at 6.4% (95% CI: 4.6% to 8.9%), whereas Gemini exhibited the highest at 13.0% (95% CI: 10.3% to 16.3%). In the others group, the FPF of the four large language models ranged from 2.8% (95% CI: 1.7% to 4.7%) to 3.8% (95% CI: 2.4% to 5.9%), both of which were significantly lower than RobotSearch's rate of 22.2% (95% CI: 18.8% to 26.1%). In terms of screening efficiency, the mean time used for screening per article was 1.3 s for ChatGPT, 6.0 s for Claude, 1.2 s for Gemini, and 2.6 s for DeepSeek. Conclusions: The AI tools assessed in this study demonstrated commendable performance in literature screening; however, they are not yet suitable as standalone solutions. These tools can serve as effective auxiliary aids, and a hybrid approach that integrates human expertise with AI may enhance both the efficiency and accuracy of the literature screening process. Graphical
- Open Access
- 2 August 2025
- Published by Springer Nature in BMC Cancer
- Vol. 25 (1) , 1-10
The role of prognostic nutrition index in the prognosis of patients with advanced hepatocellular carcinoma who received first-line therapy
To explore the relationship between the prognostic nutritional index (PNI) and the anti-tumor efficacy and prognosis of patients with advanced hepatocellular carcinoma (HCC) who received first-line therapy. A total of 234 patients with advanced HCC were included in this study, all of whom received first-line therapy. The clinical and pathological data of patients were collected. Patients were divided into high PNI group and low PNI group according to the median value of PNI. Kaplan–Meier method was used to describe the curves of overall survival (OS) and progression-free survival (PFS), and the multivariate Cox analyses were performed to identify the independent risk factors for OS and PFS. The median PNI of all patients was 46.2, and all patients were divided into low PNI group (n = 117) and high PNI group (n = 117). Multivariate Cox analysis showed that PNI (hazard ratio (HR): 0.584, 95 confidence interval (CI): 0.426–0.802; HR: 0.630, 95%CI: 0.482–0.825) was a prognostic factor of OS and PFS, and the prognosis of patients with high PNI was better than that of patients with low PNI. Subgroup analysis showed the similar results for patients receiving lenvatinib or atezolizumab plus bevacizumab (T + A). The overall response rate (ORR) of patients with high PNI was higher than that of patients with low PNI (P = 0.005). There was no statistical difference in the incidence of adverse reactions between the two groups. High PNI is a prognostic factor affecting OS and PFS for patients with advanced HCC who received first-line therapy. Patients with high PNI have higher ORR and better prognosis. There was no significant difference in the incidence of adverse reactions among patients with high or low PNI.
- 2 August 2025
- Published by Springer Nature in BMC Cancer
- Vol. 25 (1) , 1-10
Open AccessThe role of prognostic nutrition index in the prognosis of patients with advanced hepatocellular carcinoma who received first-line therapy
To explore the relationship between the prognostic nutritional index (PNI) and the anti-tumor efficacy and prognosis of patients with advanced hepatocellular carcinoma (HCC) who received first-line therapy. A total of 234 patients with advanced HCC were included in this study, all of whom received first-line therapy. The clinical and pathological data of patients were collected. Patients were divided into high PNI group and low PNI group according to the median value of PNI. Kaplan–Meier method was used to describe the curves of overall survival (OS) and progression-free survival (PFS), and the multivariate Cox analyses were performed to identify the independent risk factors for OS and PFS. The median PNI of all patients was 46.2, and all patients were divided into low PNI group (n = 117) and high PNI group (n = 117). Multivariate Cox analysis showed that PNI (hazard ratio (HR): 0.584, 95 confidence interval (CI): 0.426–0.802; HR: 0.630, 95%CI: 0.482–0.825) was a prognostic factor of OS and PFS, and the prognosis of patients with high PNI was better than that of patients with low PNI. Subgroup analysis showed the similar results for patients receiving lenvatinib or atezolizumab plus bevacizumab (T + A). The overall response rate (ORR) of patients with high PNI was higher than that of patients with low PNI (P = 0.005). There was no statistical difference in the incidence of adverse reactions between the two groups. High PNI is a prognostic factor affecting OS and PFS for patients with advanced HCC who received first-line therapy. Patients with high PNI have higher ORR and better prognosis. There was no significant difference in the incidence of adverse reactions among patients with high or low PNI.
- Open Access
- 1 August 2024
- Published by AME Publishing Company in Journal of Gastrointestinal Oncology
- Vol. 15 (4) , 1712-1722
YAP-based nomogram predicts poor prognosis in patients with hepatocellular carcinoma after curative surgery
Background: Hepatocellular carcinoma (HCC) ranks prominently in cancer-related mortality globally. Surgery remains the main therapeutic option for the treatment of HCC, but high post-operative recurrence rate makes prognostic prediction challenging. The quest for a reliable model to predict HCC recurrence continues to enhance prognosis. We aim to develop a nomogram with multiple factors to accurately estimate the risk of post-operative recurrence in patients with HCC. Methods: A single-center retrospective study on 262 patients who underwent partial hepatectomy for HCC at the Eastern Hepatobiliary Surgery Hospital from May 2010 to April 2013 was conducted where immunohistochemistry assessed Yes-associated protein (YAP) expression in HCC. In the training cohort, a nomogram that incorporated YAP expression and clinicopathological features was constructed to predict 2-, 3-, and 5-year recurrence-free survival (RFS). The performance of the nomogram was assessed with respect to discrimination calibration, and clinical usefulness with external validation. Results: A total of 262 patients who underwent partial hepatectomy for HCC at the Eastern Hepatobiliary Surgery Hospital were included in our study. HCC patients with high YAP expression exhibited significantly higher recurrence and reduced overall survival (OS) rates compared to those with low YAP expression (P<0.001). YAP was significantly associated with alpha-fetoprotein (AFP) (P=0.03), microvascular invasion (MVI) (P<0.001), and tumor differentiation grade (P<0.001). In the training cohort, factors like YAP expression, hepatitis B surface antigen (HBsAg), hepatitis B virus deoxyribonucleic acid (HBV-DNA), Child- Pugh stage, tumor size, MVI, and tumor differentiation were identified as key elements for the predictive model. Two YAP-centric Nomograms were developed, with one focused on predicting postoperative OS and the other on RFS. The calibration curve further confirmed the model's accuracy in the training cohort. The validation cohort confirmed the model's predictive accuracy. Conclusions: The proposed nomogram combining the YAP, a predictor of HCC progression, and clinical features achieved more-accurate prognostic prediction for patients with HCC after partial hepatectomy, which may help clinicians implement more appropriate interventions.
- 1 August 2024
- Published by AME Publishing Company in Journal of Gastrointestinal Oncology
- Vol. 15 (4) , 1712-1722
Open AccessYAP-based nomogram predicts poor prognosis in patients with hepatocellular carcinoma after curative surgery
Background: Hepatocellular carcinoma (HCC) ranks prominently in cancer-related mortality globally. Surgery remains the main therapeutic option for the treatment of HCC, but high post-operative recurrence rate makes prognostic prediction challenging. The quest for a reliable model to predict HCC recurrence continues to enhance prognosis. We aim to develop a nomogram with multiple factors to accurately estimate the risk of post-operative recurrence in patients with HCC. Methods: A single-center retrospective study on 262 patients who underwent partial hepatectomy for HCC at the Eastern Hepatobiliary Surgery Hospital from May 2010 to April 2013 was conducted where immunohistochemistry assessed Yes-associated protein (YAP) expression in HCC. In the training cohort, a nomogram that incorporated YAP expression and clinicopathological features was constructed to predict 2-, 3-, and 5-year recurrence-free survival (RFS). The performance of the nomogram was assessed with respect to discrimination calibration, and clinical usefulness with external validation. Results: A total of 262 patients who underwent partial hepatectomy for HCC at the Eastern Hepatobiliary Surgery Hospital were included in our study. HCC patients with high YAP expression exhibited significantly higher recurrence and reduced overall survival (OS) rates compared to those with low YAP expression (P<0.001). YAP was significantly associated with alpha-fetoprotein (AFP) (P=0.03), microvascular invasion (MVI) (P<0.001), and tumor differentiation grade (P<0.001). In the training cohort, factors like YAP expression, hepatitis B surface antigen (HBsAg), hepatitis B virus deoxyribonucleic acid (HBV-DNA), Child- Pugh stage, tumor size, MVI, and tumor differentiation were identified as key elements for the predictive model. Two YAP-centric Nomograms were developed, with one focused on predicting postoperative OS and the other on RFS. The calibration curve further confirmed the model's accuracy in the training cohort. The validation cohort confirmed the model's predictive accuracy. Conclusions: The proposed nomogram combining the YAP, a predictor of HCC progression, and clinical features achieved more-accurate prognostic prediction for patients with HCC after partial hepatectomy, which may help clinicians implement more appropriate interventions.
- Open Access
- 1 December 2023
- Published by AME Publishing Company in Journal of Gastrointestinal Oncology
- Vol. 14 (6) , 2479-2499
ACTB may serve as a predictive marker for the efficacy of lenvatinib in patients with HBV-related early-stage hepatocellular carcinoma following partial hepatectomy: a retrospective cohort study
Background: The lack of effective biomarkers for the treatment of postoperative recurrence in hepatocellular carcinoma (HCC) persists despite lenvatinib therapy. This study aims to identify beta-actin (ACTB) as a predictive biomarker for lenvatinib that can facilitate individualized treatment for HCC. Methods: This retrospective study included a subset of patients with HCC who underwent partial hepatectomy, with some receiving postoperative lenvatinib treatment and others not receiving lenvatinib treatment. A propensity score matching (PSM) analysis of patients who underwent treatment with or without lenvatinib following HCC partial hepatectomy was performed. Immunohistochemistry was employed to determine the levels of ACTB expression in HCC samples obtained from matched patients (n=225) enrolled in this study. The X-Tile was employed to determine the optimal cut-off point of ACTB levels for predicting time to recurrence (TTR). To assess the correlation between ACTB levels and lenvatinib efficacy, a subgroup analysis of TTR was conducted. A Cox regression model with an interaction term was utilized to assess the predictive significance of the model. Subsequently, a nomogram was developed and its discriminative ability and predictive accuracy were assessed using the concordance index (C-index) and calibration curve. For the investigation of the ACTB expression, HCC and para-tumoral normal tissues were employed. The patient-derived xenograft (PDX) model was utilized to validate the correlation between ACTB levels and lenvatinib responsiveness. Results: After PSM, a total of 76 patients who underwent postoperative lenvatinib treatment were included in the analysis, with a median TTR of 24.35 months. Early-stage HCC patients with lower levels of ACTB exhibited a more favorable response to lenvatinib therapy compared to those with higher levels. The reduced expression of ACTB was indicative of the benefits of lenvatinib, as opposed to higher levels {hazard ratio (HR) =0.243 [95% confidence interval (CI): 0.096–0.619], PACTB. Multivariate analysis of the lenvatinib cohort revealed Child-Pugh [HR =5.416 (95% CI: 1.390–21.104), P=0.015], Barcelona Clinic Liver Cancer (BCLC) stage [HR =2.508 (95% CI: 1.116–5.639), P=0.026], and ACTB [HR =5.879 (95% CI: 2.424–14.259), PACTB expression demonstrated a heightened sensitivity to lenvatinib treatment. Conclusions: In patients with tumors treated with lenvatinib, low ACTB expression can predict a lower risk of recurrence. The validation of this potential biomarker in independent cohorts is necessary prior to its implementation for precision treatment stratification in patients undergoing partial hepatectomy for early-stage HCC.
- 1 December 2023
- Published by AME Publishing Company in Journal of Gastrointestinal Oncology
- Vol. 14 (6) , 2479-2499
Open AccessACTB may serve as a predictive marker for the efficacy of lenvatinib in patients with HBV-related early-stage hepatocellular carcinoma following partial hepatectomy: a retrospective cohort study
Background: The lack of effective biomarkers for the treatment of postoperative recurrence in hepatocellular carcinoma (HCC) persists despite lenvatinib therapy. This study aims to identify beta-actin (ACTB) as a predictive biomarker for lenvatinib that can facilitate individualized treatment for HCC. Methods: This retrospective study included a subset of patients with HCC who underwent partial hepatectomy, with some receiving postoperative lenvatinib treatment and others not receiving lenvatinib treatment. A propensity score matching (PSM) analysis of patients who underwent treatment with or without lenvatinib following HCC partial hepatectomy was performed. Immunohistochemistry was employed to determine the levels of ACTB expression in HCC samples obtained from matched patients (n=225) enrolled in this study. The X-Tile was employed to determine the optimal cut-off point of ACTB levels for predicting time to recurrence (TTR). To assess the correlation between ACTB levels and lenvatinib efficacy, a subgroup analysis of TTR was conducted. A Cox regression model with an interaction term was utilized to assess the predictive significance of the model. Subsequently, a nomogram was developed and its discriminative ability and predictive accuracy were assessed using the concordance index (C-index) and calibration curve. For the investigation of the ACTB expression, HCC and para-tumoral normal tissues were employed. The patient-derived xenograft (PDX) model was utilized to validate the correlation between ACTB levels and lenvatinib responsiveness. Results: After PSM, a total of 76 patients who underwent postoperative lenvatinib treatment were included in the analysis, with a median TTR of 24.35 months. Early-stage HCC patients with lower levels of ACTB exhibited a more favorable response to lenvatinib therapy compared to those with higher levels. The reduced expression of ACTB was indicative of the benefits of lenvatinib, as opposed to higher levels {hazard ratio (HR) =0.243 [95% confidence interval (CI): 0.096–0.619], PACTB. Multivariate analysis of the lenvatinib cohort revealed Child-Pugh [HR =5.416 (95% CI: 1.390–21.104), P=0.015], Barcelona Clinic Liver Cancer (BCLC) stage [HR =2.508 (95% CI: 1.116–5.639), P=0.026], and ACTB [HR =5.879 (95% CI: 2.424–14.259), PACTB expression demonstrated a heightened sensitivity to lenvatinib treatment. Conclusions: In patients with tumors treated with lenvatinib, low ACTB expression can predict a lower risk of recurrence. The validation of this potential biomarker in independent cohorts is necessary prior to its implementation for precision treatment stratification in patients undergoing partial hepatectomy for early-stage HCC.