Objective To develop and apply artificial intelligence-based (AI-based)two closed-loop systems for automatic early warning of thrombosis, in order to improve the work efficiency of medical staff and reduce the incidence of venous thromboembolism (VTE) in hospitalized patients. Methods A total of 47148 inpatients in the hospital from January 2020 to December 2020 were selected as the control group, and 95184 patients from January 2021 to December 2021 were selected as the observation group. The control group used routine computer systems to evaluate and implement prevention programs. The AI-based automatic thrombus early warning and two closed-loop systems were used for evaluation and intervention in the observation group. The accuracy of VTE risk assessment, time spent on evaluation, implementation rate of basic, physical and drug prevention, VTE-related inspection rate, and VTE incidence were compared between the two groups. Results Compared with the control group, the accuracy rate of VTE risk assessment, the implementation rates of basic, physical and drug prevention, the rate of VTE-related examinations and proportion of patients with time spent on evaluation less than 1 minutes in the observation group were significantly increased (P