Construction and evaluation of the prediction model for advanced disease in well-differentiated colorectal neuroendocrine neoplasms less than 2 cm in diameter

Hongda Yin; Yanan Chen; Wei Zhao; Fuqiang Zhao; Zhijun Huang; Aimin Yue; Zhijie Wang

doi:10.1016/j.heliyon.2024.e41197

Construction and evaluation of the prediction model for advanced disease in well-differentiated colorectal neuroendocrine neoplasms less than 2 cm in diameter

Heliyon. 2024 Dec 13;11(1):e41197. doi: 10.1016/j.heliyon.2024.e41197. eCollection 2025 Jan 15.

Authors

Hongda Yin¹, Yanan Chen², Wei Zhao³, Fuqiang Zhao³, Zhijun Huang⁴, Aimin Yue¹, Zhijie Wang⁵

Affiliations

¹ Abdominal Surgical Oncology Ward, Xinxiang Central Hospital, The Forth Clinical College of Xinxiang Medical University, Xinxiang, 453000, China.
² Department of Gastroenterology, Nanchong Central Hospital, The Second Clinical Medical College of North Sichuan Medical College, Nanchong, 637000, China.
³ Department of Colorectal Surgery, National Cancer Center, National Clinical Research Center for Cancer, Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100021, China.
⁴ Outpatient Department, Strategic Support Force Medical Center, Beijing, 100101, China.
⁵ Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education, Beijing), Department of Gastrointestinal Cancer Center, Peking University Cancer Hospital & Institute, Beijing, 100142, China.

Abstract

Objective: Advanced lesions are often ignored in well-differentiated colorectal neuroendocrine neoplasms (NENs) smaller than 2 cm, and we aimed to develop an effective nomogram for these lesions.

Methods: We extracted data from the Surveillance, Epidemiology, and End Results (SEER) database and used a logistic regression model to identify independent risk factors for advanced disease. All these identified factors were included to construct the prediction model, and the receiver operating characteristic (ROC) curve, calibration plot and DCA curve were utilized to assess the predictive value. The data obtained from the National Cancer Center were utilized for external validation.

Results: In total, 3223 patients were enrolled in the training set, including 2947 (91.4 %) with early disease and 276 (8.6 %) with advanced disease. The logistic analysis showed that age (odds ratio (OR) = 1.486, 95 % confidence interval (CI): 1.102-2.003, P = 0.009), tumor size (OR = 11.071, 95 % CI: 8.229-14.893, P < 0.001), tumor location (OR = 7.882, 95 % CI: 5.784-10.743, P < 0.001) and tumor grade (OR = 1.768, 95 % CI: 1.206-2.593, P = 0.004) were independent variables for advanced disease. All of them were included in the final prediction model. The area under the ROC curve (AUC) was 0.838 (95 % CI: 0.807-0.868). The calibration plot and Hosmer‒Lemeshow test (P = 0.108) indicated favorable consistency between the predicted probabilities and actual probabilities of advanced disease. The Brier score was 0.108, indicating acceptable overall performance. The DCA curve presented a significant clinical net benefit. In the validation set, both the ROC curve and calibration plot exhibited an acceptable discrimination ability (AUC = 0.807 (95 % CI 0.702-0.913) and calibration (Hosmer Lemeshow P = 0.997), respectively.

Conclusions: The prediction model had good value for identifying advanced disease from well-differentiated colorectal NENs smaller than 2 cm.

Keywords: Colon; Neoplasm; Neuroendocrine; Nomogram; Rectum.