Construction and validation of a nomogram model for predicting rebleeding in high-risk peptic ulcer bleeding patients based on lasso regression: A single center retrospective research

Objective To construct a Nomogram prediction model for high-risk Peptic Ulcer Bleeding (PUB) rebleeding using Lasso regression analysis and verify its predictive performance. Methods Retrospective research was performed on 279 cases with PUB admitted from January 2020 to December 2023 in a hospital's medical record information system. Clinical data were collected and randomly separated into a modeling group and a validation group in a 7:3. The overfitting in the constructed model was verified by comparing the clinical data. According to the clinical data of the modeling group, Lasso regression analysis was used to screen variables and conduct multiple factor analysis. A Nomogram model was constructed accordingly, and its predictive performance was validated. Results Among 279 patients included in this study, 45 cases had rebleeding, with an incidence rate of 16.13 %. The Lasso regression analysis demonstrated that a total of 15 variables were screened, taking λ_min as the standard. Multivariate analysis showed that diastolic blood pressure, hematocrit, blood transfusion volume, GBS score, endoscopic examination, and mechanical hemostasis were all independent risk factors for rebleeding in PUB cases. The Nomogram model based on multiple factor analysis demonstrated that the AUC of the modeling group and the validation group were 0.832 (95 %CI = 0.744-0.921) and 0.814 (95 %CI = 0.672-0.956), and Hosmer-Lemeshow χ² = 13.520 (P = 0.095). The DCA and CIC curve analysis results showed that using this model for patient intervention achieved positive benefits and relatively accurately predicted the rebleeding in PUB patients. Conclusion This research constructs a Nomogram model based on Lasso regression analysis that can effectively predict the rebleeding in PUB patients, providing reference for early prevention of clinical PUB rebleeding.