.png){kind=icon}
.png){kind=icon}
Return
A Simplified Nomogram for Primary Population-Based Screening of Esophageal Cancer: An Internally Validated Shandong Cohort Study Addressing Data Imbalance
.png){kind=icon}
OA
AI
J
X
F
T
L
X
DOI：10.2147/rmhp.s607198.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Junjun Hou,1,* Xiuyu He,2,* Fei Gao,2 Ting Ren,2 Lijin Ren,3 Xianguo Wang4 1Department of Medical Oncology I, Tai’ an Cancer Hospital, Tai’ an, Shandong, 271099, People’s Republic of China; 2Department of Office of Cancer Center, Tai’ an Cancer Hospital, Tai’ an, Shandong, 271099, People’s Republic of China; 3Department of Traditional Chinese Medicine I, Tai’ an Cancer Hospital, Tai’ an, Shandong, 271099, People’s Republic of China; 4Department of Medical Oncology II, Tai’ an Cancer Hospital, Tai’ an, Shandong, 271099, People’s Republic of China *These authors contributed equally to this work Correspondence: Xianguo Wang, Department of Medical Oncology II, Tai’ an Cancer Hospital, No. 390, Lingshan Street, Taishan District, Tai’an, Shandong, 271099, People’s Republic of China, Tel +86 13562898761, Email Wangxianguo55@163.com Lijin Ren, Department of Traditional Chinese Medicine I, Tai’ an Cancer Hospital, No. 390, Lingshan Street, Taishan District, Tai’an, Shandong, 271099, People’s Republic of China, Email renlijing3@21cn.com Objective: To develop and validate a user-friendly nomogram for predicting the risk of esophageal squamous cell carcinoma (ESCC) and high-grade intraepithelial neoplasia (HGIN), designed for initial screening settings while addressing variable complexity and class imbalance in traditional models. Methods: Based on a screening cohort of 23,257 participants from Tai’an, Shandong, between 2024 and 2025 (positive rate: 1.54%), a 1:10 case–control sampling method was applied to address the low event rate (positive rate: 1.54%) and correct class imbalance. Predictors were initially screened using LASSO regression with 10-fold cross-validation (λ.min criterion) and further refined via multivariable logistic regression to establish the final model, which was presented as a nomogram and evaluated via internal split-sample validation. Results: Seven easily accessible predictors were identified: age, sex, education level, BMI, smoking history, hot-food consumption, and family history of esophageal cancer. The model showed strong discriminatory performance, with an AUC of 0.823 (95% CI: 0.798– 0.848) in the training set and 0.835 (95% CI: 0.805– 0.865) in the internal validation set. Calibration curves indicated high consistency between predicted and observed risks. Decision curve analysis demonstrated net clinical benefit across risk thresholds of 0– 0.6. Conclusion: The proposed simplified nomogram demonstrates promising potential for risk stratification in primary ESCC/HGIN screening. However, prospective external validation in diverse cohorts is necessary before its large-scale clinical implementation. Keywords: esophageal squamous cell carcinoma, precancerous conditions, early detection of cancer, predictive learning models
Keywords:
esophageal squamous cell carcinoma
precancerous conditions
early detection of cancer
predictive learning models
Journal
IF:
2
Papers:
269
Citations:
4.1K
Organization
Cited Papers