The benefit of radiotherapy for rectal cancer is largely based on a balance between decrease in local recurrence and increase in bowel dysfunction. Predicting postoperative disability is helpful for recovery plans and early intervention. We aimed to develop and validate a risk model to improve the prediction of major bowel dysfunction after restorative rectal cancer resection with neoadjuvant radiotherapy using perioperative features.Eligible patients more than one year after restorative resection following radiotherapy were invited to complete the low anterior resection syndrome (LARS) score in three national hospitals of China. Clinical characteristics and imaging parameters were assessed with machine learning algorithms. The post-radiotherapy LARS prediction model (PORTLARS) was constructed by logistic regression on the basis of key factors with proportional weighs. The accuracy of model for major LARS prediction was internally and externally validated.A total of 868 patients reported mean LARS score of 28.4 after average time of 4.7 years since surgery. Key predictors for major LARS included the length of distal rectum, anastomotic leakage, proximal colon of neorectum, and pathological nodal-stage. PORTLARS had a favorable area under the curve for predicting major LARS in the internal dataset (0.835, 95% confidence interval (CI) 0.800-0.870, n=521) and external dataset (0.884, 95% CI 0.848-0.921, n=347). The model achieved both sensitivity and specificity over 0.83 in the external validation. Additionally, PORTLARS outperformed the pre-operative LARS score for prediction of major events.PORTLARS could predict major bowel dysfunction after rectal cancer resection following radiotherapy with high accuracy and robustness. It may serve as a useful tool to highlight patients who need additional support for long-term dysfunction in the early stage.Copyright © 2023 AGA Institute. Published by Elsevier Inc. All rights reserved.