Objective To construct and validate an ICU acquired weakness (ICUAW) risk prediction model, and to provide an effective tool for early screening of ICUAW-risk population. Methods Meta-analysis was conducted to calculate the risk factors of ICUAW, the natural logarithm of the comprehensive risk of each risk factor was taken as the β coefficient, and the natural logarithm of the ratio of ICUAW incidence rate to non-incidence rate during a certain period was taken as the α coefficient to construct a risk prediction model of ICUAW.Then the data of 137 ICU patients were collected to evaluate the predictive performance of the model. Results The model of ICUAW was logit(P)=-0.781+0.039age+0.077APACHE+0.940shock+0.122duration of mechanical ventilation+0.971sepsis+0.756neuromuscular blocker+1.311vasoactive drugs+1.308corticosteroids+0.747gender+0.626 hyperglycemia+1.973renal replacement therapy.The area under the receiver operating characteristic curve of the model was 0.752, 95%CI was (0.672,0.833).The cut-off value of probability function (P) was 0.998, the sensitivity was 0.930, and specificity was 0.489. Conclusion The ICUAW risk prediction model based on Meta-analysis can be used as a tool for early prediction of ICUAW risk population.