Based on the adaptive algorithm model, this paper proposes two special model structures of randomized fusion and an optimized convolution kernel and uses it for image recognition. It combined with the adaptive algorithm model image-guided electroacupuncture combined with a continuous femoral nerve block to prevent deep vein thrombosis after total knee replacement. 200 patients after total knee replacement were randomly divided into 4 groups. We observe the incidence of postoperative lower limb deep vein thrombosis, platelet count before and after surgery. Electroacupuncture combined with continuous femoral nerve block can reduce the incidence and has obvious advantages in multi-mode prevention. The effective analgesia provided by electroacupuncture combined with continuous femoral nerve block can not only relieve postoperative pain. It enabled patients to train joint activities and lower limb muscle strength as soon as possible, which is conducive to postoperative functional recovery, but also reduces the body stress response triggered by pain and the hypercoagulable state. At the same time, electroacupuncture stimulation of acupuncture points can reduce the inflammatory edema associated with surgery, improve blood circulation at the surgical site and activate the body’s anticoagulation mechanism. It provides new ideas and references for formulating multi-mode prevention and control strategies.Copyright © 2020 Elsevier Inc. All rights reserved.