Abstract: BACKGROUND: With the widespread application of total knee arthroplasty in China, non-infectious prosthesis loosening has become one of the main reasons for postoperative revision. For complex loosening cases, traditional revision techniques are relatively complex and difficult. The application of artificial intelligence-assisted preoperative planning combined with Sleeve extension rods and mobile bearing tray prostheses provides a new solution for precisely reconstructing joint stability and mechanical alignment, which is expected to improve the long-term outcomes of revision surgeries.
OBJECTIVE: To explore the mid-and early-term clinical efficacy of revision surgery for non-infectious total knee prosthesis loosening using Sleeve extension rods combined with mobile bearing tray prostheses under the assistance of artificial intelligence-assisted preoperative planning.
METHODS: A retrospective analysis was conducted on 17 patients with non-infectious prosthesis loosening after total knee arthroplasty in Department of Orthopedics and Traumatology, Jiangsu Provincial Hospital of Traditional Chinese Medicine from January 2021 to September 2024. There were 6 males and 11 females, aged from 59 to 81 years old, with an average age of (72.06±6.10) years. There were 8 cases on the left side and 9 cases on the right side. The service life of the prosthesis ranged from 2 to 22 years, with an average of (10.53±4.60) years. All cases were revisions after primary replacement. The reasons for revision included periprosthetic osteolysis with liner wear in 15 cases, old femoral condyle fracture leading to prosthesis loosening in 1 case, and tibial plateau prosthesis fracture in 1 case. Among them, 13 cases were of AORI type IIB and 4 cases were of AORI type IIA. The prosthesis models designed by artificial intelligence before surgery were recorded and compared with the models actually used during surgery. The visual analog scale scores, American Knee Society knee scores, knee hip-knee-ankle angles, and knee joint ranges of motion of the patients before surgery, 1 week, 6, and 12 months after surgery were compared and the surgical efficacy was assessed. 
RESULTS AND CONCLUSION: (1) Except for 1 case with poor wound healing 1 month after surgery, the rest of the patients recovered well without adverse events such as deep vein thrombosis of the lower extremities, infection, periprosthetic fracture, and prosthesis loosening. (2) The follow-up time ranged from 6 to 41 months, with an average of (23.63±12.50) months. At the last follow-up, two patients had slight soreness and discomfort after activity, and one patient had obvious pain during activity. (3) After revision treatment, the visual analog scale pain scores of the patients, rest pain, exercise pain, the range of motion of the affected side, hip-knee-ankle angle, and American Knee Society knee score were significantly improved (P < 0.01), with statistically significant differences. (4) The matching rate of the femoral condyle and tibial plateau prostheses designed by artificial intelligence pre-operatively was 85%; the matching rate of the remaining components was 62%. (5) It is concluded that the use of Sleeve extension rods combined with mobile bearing tray prostheses for non-infectious knee revision surgery can effectively correct the joint alignment, fill bone defects, relieve pain, improve the range of motion of the knee joint, and enhance the quality of life of patients with severe bone defects. The mid-and early-term postoperative efficacy is good. Artificial intelligence-assisted preoperative planning can help improve surgical accuracy, reduce surgical difficulty, minimize surgical risks, and promote postoperative recovery of patients.

Key words: knee prosthesis loosening, knee revision, artificial intelligence preoperative planning, bone defect, outcome analysis