Influencing factors and establishment of a prediction model for the efficacy of neoadjuvant chemoradiotherapy in locally advanced rectal cancer

Purpose: To analyze the influencing factors of neoadjuvant chemoradiotherapy for locally advanced rectal cancer and construct an efficacy prediction model. Methods A total of 158 LARC patients who underwent total mesenteric excision after receiving neoadjuvant chemoradiotherapy treatment at the First Hospital Affiliated to Air Force Medical University from January 2016 to December 2020 were enrolled. Baseline clinical indicators before neoadjuvant therapy were collected, including laboratory data, tumor markers and MRI. The efficacy prediction model was constructed through the R language, the predictive performance of the model was evaluated using DCA curves and calibration curves, and the accuracy of the model was tested through 10-fold cross-validation. Results Ninety-eight patients achieved complete response (CR) or partial response (PR), with an overall response rate was 62%. Sixty patients had a poor neoadjuvant chemoradiotherapy response, either stable disease (SD) or progressive disease (PD). Pretreatment tumor diameter, time to surgery after neoadjuvant therapy, D-dimer, Prognostic Nutritional Index (PNI), carcinoembryonic antigen (CEA), and extramural vascular invasion (EMVI) were included in the prediction model. The area under the ROC curve (AUC) of the LARC neoadjuvant radiotherapy prediction model was 0.84 (95% CI: 0.780–0.899), with a sensitivity of 85% and a specificity of 72%.In the calibration curve, the predicted results are in good agreement with the actual results, with good prediction accuracy; the DCA curve shows that the efficacy prediction model can bring clinical net benefit to diagnosis. Conclusion Pretreatment tumor diameter, time to surgery after neoadjuvant therapy, D-dimer, PNI, CEA and EMVI are independent risk factors for the efficacy of neoadjuvant chemoradiotherapy in LARC patients. The efficacy prediction model based on the above factors has good predictive efficacy for the efficacy of neoadjuvant chemoradiotherapy in LARC patients.