Construction and validation of a predictive model for prolonged length of stay after PCI for patients with acute myocardial infarction.

Abstract Objective To construct and validate of a predictive model for prolonged length of stay after PCI for patients with acute myocardial infarction. Methods A retrospective analysis was conducted on the clinical data of 592 patients with acute myocardial infarction who underwent PCI treatment. They were divided into a modeling group (414 cases) and a validation group (178 cases) in a ratio of 7:3.Define prolonged length of stay as hospitalization for more than 7 days after surgery.Single-factor and multi-factor logistic regression analysis were used to construct a predictive model and it was validated. Results Female gender (OR = 5.72, 95%CI: 2.10-15.58), smoking(OR = 4.41, 95%CI:1.76–11.02), hypertension(OR = 2.32, 95%CI:1.27–4.24), hs-cTnT(OR = 1.12, 95%CI:1.02–1.26)and Killip functional classification were identified as independent factors associated with prolonged length of hospital stay after PCI in patients with acute myocardial infarction (P < 0.05).A column line graph predictive model was built using the aforementioned independent factors. The area under the curve (AUC) for predicting prolonged length of hospital stay after surgery was 0.852 for the modeling group and 0.831 for the validation group.The calibration curve of the predictive model showed good consistency in both groups. Conclusion This model can effectively predict the risk of prolonged length of hospital stay after PCI in patients with acute myocardial infarction, providing a basis for clinical management and nursing guidance.