Construction of a risk nomogram model of postoperative malnutrition in patients with oral cancer

Objective To analyze the influencing factors of malnutrition after surgery in patients with oral cancer and construct a nomogram prediction model.

Methods A total of 117 patients with oral cancer were selected as the research subjects and divided into non-malnutrition group (n=46) and malnutrition group (n=71) based on whether they were malnourished. Logistic regression analysis was used to analyze the influencing factors of postoperative malnutrition in patients with oral cancer. A nomogram model was constructed to predict the risk of postoperative malnutrition in patients with oral cancer, and the application value of the nomogram model was evaluated using receiver operating characteristic (ROC) curve, calibration curve and Hosmer-Lemeshow goodness-of-fit test.

Results Among the 117 patients with oral cancer, 60.68% (71/117) were malnourished. Logistic regression analysis showed that age >60 years (95%CI, 2.220 to 29.647, P=0.002), nutritional risk screening result at admission indicating nutritional risk (95%CI, 2.586 to 39.175, P=0.001), tracheotomy (95%CI, 1.582 to 15.312, P=0.006), postoperative depression (95%CI, 2.253 to 27.327, P=0.001), postoperative sleep disorder (95%CI, 3.014 to 43.037, P<0.001) and postoperative swallowing disorder (95%CI, 2.943 to 38.493, P<0.001) were the influencing factors of postoperative malnutrition in patients with oral cancer. The area under the ROC curve of the constructed nomogram prediction model was 0.888 (95%CI, 0.823 to 0.953); the calibration curve showed that the predicted probability curve basically matched the actual probability curve, and the Hosmer-Lemeshow goodness-of-fit test was well (χ²=6.515, P=0.481).

Conclusion Age >60 years, nutritional risk screening result indicating nutritional risk at admission, tracheotomy, postoperative depression, postoperative sleep disorder and postoperative swallowing disorder are the influencing factors of postoperative malnutrition in patients with oral cancer. The nomogram model constructed based on the above factors has good discrimination and consistency.