Nomogram model based on MRI features for predicting schistosomiasis-associated colorectal cancer

Abstract Background Schistosoma japonicuminfection is epidemiologically linked to aggressive schistosomiasis-associated colorectal cancer (SA-CRC). Current preoperative diagnosis relies on invasive endoscopy and histopathology, which may miss early lesions. MRI offers non-invasive visualization of CRC features but lacks exploration in SA-CRC prediction. Methods A retrospective analysis was performed on 182 colorectal cancer patients who underwent MRI examinations at our institution from October 2018 to March 2024. These patients were randomly divided into a training set (n = 127) and an internal test set (n = 55) at a ratio of 7:3. Univariate logistic regression analysis was used to screen factors associated with SA-CRC. Independent risk factors for SA-CRC were selected through the least absolute shrinkage and selection operator (LASSO) regression and multivariate logistic regression analysis to construct a prediction model and draw a nomogram. The discrimination, calibration, and clinical applicability of the prediction model were evaluated using the receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA). Results Age ≥ 60 years, mucin content within the tumor > 50%, positive mrEMVI (extramural vascular invasion on MRI), and early enhancement rate (EER) < 220.73% were identified as independent risk factors for schistosomiasis-associated colorectal cancer (SA-CRC) (p < 0.05). The nomogram incorporating these factors demonstrated excellent predictive performance. In the training set and test set of the nomogram prediction model, the area under the curve (AUC) values were 0.910 (95% CI: 0.787–0.984) and 0.832 (95% CI: 0.747–0.906). The calibration curve of the model indicated good agreement between the predicted and actual prevalence rates of the disease. DCA demonstrated that this nomogram model has good clinical utility. Conclusion The SA-CRC nomogram model incorporating both clinical parameters and MRI characteristics exhibits strong predictive accuracy, facilitating early diagnosis and personalized monitoring for SA-CRC.