AUTHOR=Shao Zhuce , Liang Zhipeng , Hu Peng , Bi Shuxiong TITLE=A nomogram based on radiological features of MRI for predicting the risk of severe pain in patients with osteoarthritis of the knee JOURNAL=Frontiers in Surgery VOLUME=Volume 10 - 2023 YEAR=2023 URL=https://www.frontiersin.org/journals/surgery/articles/10.3389/fsurg.2023.1030164 DOI=10.3389/fsurg.2023.1030164 ISSN=2296-875X ABSTRACT=The aim of this study was to develop and validate a nomogram used to predict the probability of occurrence of severe pain in patients with knee osteoarthritis. a total of 150 patients with knee osteoarthritis were collected from our hospital, where the nomogram was created by a validation cohort (n = 150), while an additional external validation cohort (n = 64) was collected for validation of the model. Eight variables of significance were first screened by LASSO, and then, factors in the nomogram were identified by Logistcs regression analysis. We tested the accuracy of the nomogram through C-index, calibration plots, and ROC (Receiver Operating Characteristic) curves, and finally, decision curves were plotted to assess the benefits of the nomogram to aid in clinical decision making. We used a very large number of variables to predict severe pain in knee osteoarthritis, including sex, age, height body mass index (BMI), affected side, K-L degree, K-L grade, pain during walking, pain going up and down stairs, pain sitting or lying down, pain standing, pain sleeping, cartilage score, BML score, synovitis score, patellofemoral synovitis, bone wear score, patellofemoral bone wear, and bone wear scores.Finally, LASSO regression results showed that BMI, affected side, duration of knee osteoarthritis, meniscus score, meniscus displacement, BML score, synovitis score, and bone wear score were the most meaningful influences to predict severe pain. Based on these eight factors, a nomogram model was developed. The C-index of the model is 0.892 (95% CI :0.839 -----0.945) and the C-index of the external validation is 0.822 (95% CI 0.722-0.922).Analysis of the ROC curve of the nomogram showed high accuracy in predicting the occurrence of severe pain (AUC=0.868) in patients with KOA. The calibration curves showed that the prediction model was very consistent. Decision curve analysis (DCA) showed a higher net benefit for decision making using this nomogram, especially in the >1% and <86% threshold probability intervals. The morphogram can predict patient prognosis and guide personalized treatment.