Zezhou Wang

Zezhou Wang

Auto-generated profile, based on publicly available information

Zezhou Wang

Department of Oncology, Shanghai Medical College, Fudan University, Shanghai, China

Research Focus & Metrics

Academic Career Length

27Years (2000-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 February 2022 in JMIR Medical Informatics
Verified
Journal Article
Open access
JXJialong Xiao
Jialong Xiao
MMMiao Mo
Miao Mo
ZWZezhou Wang
Zezhou Wang
CZChangming Zhou
Changming Zhou
JSJie Shen
Jie Shen
YZYing Zheng
Ying Zheng
Background: Over the recent years, machine learning methods have been increasingly explored in cancer prognosis because of the appearance of improved machine learning algorithms. These algorithms can use censored data for modeling, such as support vector machines for survival analysis and random survival forest (RSF). However, it is still debated whether traditional (Cox proportional hazard regression) or machine learning-based prognostic models have better predictive performance. Objective: This study aimed to compare the performance of breast cancer prognostic prediction models based on machine learning and Cox regression. Methods: This retrospective cohort study included all patients diagnosed with breast cancer and subsequently hospitalized in Fudan University Shanghai Cancer Center between January 1, 2008, and December 31, 2016. After all exclusions, a total of 22,176 cases with 21 features were eligible for model development. The data set was randomly split into a training set (15,523 cases, 70%) and a test set (6653 cases, 30%) for developing 4 models and predicting the overall survival of patients diagnosed with breast cancer. The discriminative ability of models was evaluated by the concordance index (C-index), the time-dependent area under the curve, and D-index; the calibration ability of models was evaluated by the Brier score. Results: The RSF model revealed the best discriminative performance among the 4 models with 3-year, 5-year, and 10-year time-dependent area under the curve of 0.857, 0.838, and 0.781, a D-index of 7.643 (95% CI 6.542, 8.930) and a C-index of 0.827 (95% CI 0.809, 0.845). The statistical difference of the C-index was tested, and the RSF model significantly outperformed the Cox-EN (elastic net) model (C-index 0.816, 95% CI 0.796, 0.836; P=.01), the Cox model (C-index 0.814, 95% CI 0.794, 0.835; P=.003), and the support vector machine model (C-index 0.812, 95% CI 0.793, 0.832; P<.001). The 4 models’ 3-year, 5-year, and 10-year Brier scores were very close, ranging from 0.027 to 0.094 and less than 0.1, which meant all models had good calibration. In the context of feature importance, elastic net and RSF both indicated that TNM staging, neoadjuvant therapy, number of lymph node metastases, age, and tumor diameter were the top 5 important features for predicting the prognosis of breast cancer. A final online tool was developed to predict the overall survival of patients with breast cancer. Conclusions: The RSF model slightly outperformed the other models on discriminative ability, revealing the potential of the RSF method as an effective approach to building prognostic prediction models in the context of survival analysis.

2 January 2024 in Cancer Imaging
Verified
Journal Article
Open access
PDF file
JGJing Gong
Jing Gong
TWTing Wang
Ting Wang
ZWZezhou Wang
Zezhou Wang
XCXiao Chu
Xiao Chu
THTingdan Hu
Tingdan Hu
YGYajia Gu
Yajia Gu
Background: Brain metastasis (BM) is most common in non-small cell lung cancer (NSCLC) patients. This study aims to enhance BM risk prediction within three years for advanced NSCLC patients by using a deep learning-based segmentation and computed tomography (CT) radiomics-based ensemble learning model. Methods: This retrospective study included 602 stage IIIA-IVB NSCLC patients, 309 BM patients and 293 non-BM patients, from two centers. Patients were divided into a training cohort (N = 376), an internal validation cohort (N = 161) and an external validation cohort (N = 65). Lung tumors were first segmented by using a three-dimensional (3D) deep residual U-Net network. Then, a total of 1106 radiomics features were computed by using pretreatment lung CT images to decode the imaging phenotypes of primary lung cancer. To reduce the dimensionality of the radiomics features, recursive feature elimination configured with the least absolute shrinkage and selection operator (LASSO) regularization method was applied to select the optimal image features after removing the low-variance features. An ensemble learning algorithm of the extreme gradient boosting (XGBoost) classifier was used to train and build a prediction model by fusing radiomics features and clinical features. Finally, Kaplan‒Meier (KM) survival analysis was used to evaluate the prognostic value of the prediction score generated by the radiomics–clinical model. Results: The fused model achieved area under the receiver operating characteristic curve values of 0.91 ± 0.01, 0.89 ± 0.02 and 0.85 ± 0.05 on the training and two validation cohorts, respectively. Through KM survival analysis, the risk score generated by our model achieved a significant prognostic value for BM-free survival (BMFS) and overall survival (OS) in the two cohorts (P < 0.05). Conclusions: Our results demonstrated that (1) the fusion of radiomics and clinical features can improve the prediction performance in predicting BM risk, (2) the radiomics model generates higher performance than the clinical model, and (3) the radiomics-clinical fusion model has prognostic value in predicting the BMFS and OS of NSCLC patients.

7 March 2025 in Clinical Cancer Research
Verified
Journal Article
Open access
ITIhsuan Tseng
Ihsuan Tseng
YCYun Chen
Yun Chen
DADashan Ai
Dashan Ai
ZZZhengfei Zhu
Zhengfei Zhu
WZWeixin Zhao
Weixin Zhao
KZKuaile Zhao
Kuaile Zhao
Purpose: A preclinical model found that elective nodal irradiation attenuated the efficacy of radiotherapy (RT) and radio-immunotherapy. However, limited clinical studies have explored the correlation between radiation dose–volume parameters of negative tumor-draining lymph nodes (TDLN) and T-cell activation/prognosis for patients with cancer treated with definitive radiochemotherapy. Experimental Design: Patients with locally advanced esophageal cancer undergoing definitive chemoradiotherapy (CRT) were selected from two prospective trials. Dose–volume parameters of TDLN as well as other lymphocyte-related organs at risk and lymphocyte subsets such as CD3−CD19+ B cells, CD8+CD28+ T cells, and activated T cells (CD3+CD8+HLA-DR+) before and at the end of RT were collected. Logistic analysis was utilized to correlate dose–volume parameters with reductions in lymphocyte subsets. Prognosis of TDLN irradiation was investigated through Kaplan–Meier analysis and Cox hazards models. Results: Among 512 patients, the median mean dose of TDLN and negative non-TDLN was 25.6 and 15.1 Gy, respectively. Multivariable analyses indicated that TDLN V15 >50% was an independent predictor of poorer local recurrence–free survival (HR, 1.31; P = 0.029) and distant metastasis–free survival (HR, 1.39; P < 0.001), as well as greater reductions in CD3−CD19+ B cells (OR, 1.98; P = 0.002), CD8+CD28+ T cells (OR, 3.42; P < 0.001), and CD3+CD8+HLA-DR+ T cells (OR, 4.67; P = 0.002) after RT. Conclusions: A higher radiation dose–volume parameter of TDLNs in patients with esophageal cancer undergoing CRT was significantly associated with suppression of T-cell activation and a worse prognosis. Limiting the percentage of TDLN V15 may be beneficial for improving the prognosis of CRT with or without PD-1 inhibitors.

2 November 2017 in The Journal of Sex Research
Verified
Journal Article
Closed access
ZWZezhou Wang
Zezhou Wang
XZXu Zhao
Xu Zhao
ZZZhan Zhang
Zhan Zhang
MLMengyun Luo
Mengyun Luo
QSQiuming Shen
Qiuming Shen
JMJin Ma
Jin Ma
We aimed to apply syndemic theory to verify the association and reinforcing effects between psychosocial problems and multiple sexual partners (MSP) of men who have sex with men (MSM) in Shanghai, China. A cross-sectional study was conducted among 547 MSM in Shanghai, China using a face-to-face survey. Sociodemographic and psychosocial data were collected, as well as information on MSP and condomless anal sex. In the 6 months prior to the survey, 54.3% of the MSM sample had had MSP. Univariate analysis showed that self-esteem, depression, loneliness, sexual compulsivity, and involuntary subordination (IS) were associated with MSP. Sexual compulsivity (multivariate odds ratio [ORm] = 2.94, 95% CI = 1.76–4.91) and IS (ORm = 1.79, 95% CI = 1.14–2.81) remained significant in multivariate analysis. MSM with five or more psychosocial problems had greater odds of (adjusted odds ratios = 3.06, 95% CI = 1.49–6.25) having MSP in the previous 6 months than the non-syndemic group. Our findings provide preliminary confirmation of the additive relationship of syndemic psychosocial health conditions and MSP among MSM in Shanghai, China. An integrated intervention with special focus on sexual compulsivity and IS is needed.

1 October 2025 in Radiology
Verified
Journal Article
Closed access
YFYaru Feng
Yaru Feng
THTingdan Hu
Tingdan Hu
WGwenchao gu
wenchao gu
WDWeixing Dai
Weixing Dai
SMShaobo Mo
Shaobo Mo
TTTong Tong
Tong Tong
Mesorectal fascia involvement caused by tumor deposits or extramural vascular invasion at pretreatment MRI predicts poor prognosis in patients with locally advanced rectal cancer.