Haibo Mou

Prof. Dr. Haibo Mou


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
21 March 2025 in Frontiers in Public Health
Verified
Journal Article
Open access
PDF file
SZShiqi Zhang
Shiqi Zhang
JJJianan Jin
Jianan Jin
BXBenfeng Xu
Benfeng Xu
QZQi Zheng
Qi Zheng
HMHaibo Mou
Haibo Mou
Introduction: Epigenetic biomarkers are molecular indicators of epigenetic changes, and some studies have suggested that these biomarkers have predictive power for disease risk. This study aims to analyze the relationship between 30 epigenetic biomarkers and the risk of diabetes and cancer using machine learning modeling.Methods: The data for this study were sourced from the NHANES database, which includes DNA methylation arrays and epigenetic biomarker datasets. Nine machine learning algorithms were used to build models: AdaBoost, GBM, KNN, lightGBM, MLP, RF, SVM, XGBoost, and logistics. Model stability was evaluated using metrics such as Accuracy, MCC, and Sensitivity. The performance and decision-making ability of the models were displayed using ROC curves and DCA curves, while SHAP values were used to visualize the importance of each epigenetic biomarker.Results: Epigenetic age acceleration was strongly associated with cancer risk but had a weaker relationship with diabetes. In the diabetes model, the top three contributing features were logA1Mort, family income-to-poverty ratio, and marital status. In the cancer model, the top three contributing features were gender, non-Hispanic White ethnicity, and PACKYRSMort.Conclusion: Our study identified the relationship between epigenetic biomarkers and the risk of diabetes and cancer, and used machine learning techniques to analyze the contributions of various epigenetic biomarkers to disease risk.

1 January 2024 in Cancer Control
Verified
Journal Article
Open access
JJJianan Jin
Jianan Jin
HMHaibo Mou
Haibo Mou
YZYibin Zhou
Yibin Zhou
SZShiqi Zhang
Shiqi Zhang
Background: Immune therapy, especially involving PD-1/PD-L1 inhibitors, has shown promise as a therapeutic option for cholangiocarcinoma. However, limited studies have evaluated survival outcomes in cholangiocarcinoma patients treated with immune therapy. This study aims to develop a predictive model to evaluate the survival benefits of immune therapy in patients with cholangiocarcinoma. Methods: This retrospective analysis included 120 cholangiocarcinoma patients from Shulan (Hangzhou) Hospital. Univariate and multivariate Cox regression analyses were conducted to identify factors associated with survival following immune therapy. A predictive model was constructed and validated using calibration curves (CC), decision curve analysis (DCA), concordance index (C-index), and receiver operating characteristic (ROC) curves. Results: Cox regression analysis identified several factors as potential predictors of survival post-immune therapy in cholangiocarcinoma: treatment cycle (<6 vs ≥ 6 months, 95% CI: 0.119-0.586, P = 0.001), neutrophil-to-lymphocyte ratio (NLR <3.08 vs ≥ 3.08, 95% CI: 1.864-9.624, P = 0.001), carcinoembryonic antigen (CEA <4.13 vs ≥ 4.13, 95% CI: 1.175-5.321, P = 0.017), and presence of bone metastasis (95% CI: 1.306-6.848, P = 0.010). The nomogram model achieved good predictive accuracy with a C-index of 0.811. CC indicated strong concordance between the predicted and observed outcomes. Multi-timepoint ROC curves at 1, 2, and 3 years validated the model’s performance (1-year AUC: 0.906, 2-year AUC: 0.832, 3-year AUC: 0.822). The multi-timepoint DCA curves also demonstrated a higher net benefit compared to extreme curves. Conclusion: The nomogram model, incorporating key risk factors for cholangiocarcinoma patients post-immune therapy, demonstrates robust predictive accuracy for survival outcomes, offering the potential for improved clinical decision-making.