Abstract:Objective To construct a prediction model for the risk of falls during the rehabilitation period of patients with motor dysfunction after cerebral infarction (CI) and verify its predictive efficacy. Methods A retrospective selection was conducted on 144 patients with post CI motor dysfunction admitted from May 2023 to June 2024 in Puyang Huimin Hospital. 68 patients who experienced falls were divided into an observation group, and 76 patients who did not experience falls were divided into a control group. The clinical data of the two groups were compared, and a logistic regression model was used to construct a fall risk prediction model during the rehabilitation period. The predictive performance of the model was validated by receiver operating characteristic (ROC) analysis. Results The age of the observation group [(69.74±3.57) years old], body mass index(BMI) [(30.57±2.57) kg/m2], proportion of patients with physical pain (30.88%), proportion of patients with a history of falls (22.06%), depression score [(53.83±5.28) points], and anxiety score [(51.72±6.24) points] were higher than those of the control group [(64.26 ±3.86) years old, (27.46±2.35) kg/m2, 11.84%, 6.58%, (46.37 ±8.73) points, (45.84 ±6.82) points] (P<0.05); multivariate Logsitc regression analysis showed that patient age (OR=1.867), history of falls (OR=2.582), and depression score (OR=2.246) were the main influencing factors for falls (P <0.05); The study constructed a fall risk model based on logistic regression analysis results: Logit(P)= -2.472+1.219 X1+1.414 X4+1.324 X5; ROC analysis showed that the area under curve (AUC) value of the fall risk prediction model for patients with after CI motor dysfunction during the rehabilitation period was 0.905 (95% CI: 0.878 ~ 0.936, P<0.05), with a sensitivity of 92.73% and a specificity of 84.25%. Conclusion Establishing a rehabilitation fall risk prediction model based on the age, fall history, and depression status of patients with motor dysfunction after CI can effectively predict the risk of falls in patients and provide a basis for clinical intervention.