Construction of a risk prediction model for postoperative gastrointestinal dysfunction and prevention in patients with gastrointestinal tumors

Figure 1 Receiver operating characteristic curves of different biomarkers and joint diagnosis for predicting postoperative gastrointestinal dysfunction in patients with gastrointestinal tumors. AUC: Area under the receiver operating characteristic curve; BMI: Body mass index; TPR: True positive rate; FPR: False positive rate.

Figure 2 Nomogram for predicting postoperative gastrointestinal dysfunction in patients with gastrointestinal tumors. This nomogram is constructed based on the multivariate Logistic regression model. To use the nomogram: (1) Locate the value of each risk factor (age, gender, body mass index, tumor stage, operative duration, preoperative hemoglobin, preoperative albumin) on the corresponding axis; (2) Draw a vertical line upward to the "points" axis to obtain the score for each factor; (3) Sum the scores of all factors to get the total score; and (4) Draw a vertical line downward from the “total points” axis to the “risk probability” axis to obtain the individual risk of postoperative gastrointestinal dysfunction. A ruler can be used to assist in reading scores and risk probabilities. BMI: Body mass index.