Comparison of traditional template measurements and artificial intelligence (AI) preoperative planning in total knee arthroplasty

Meipeng Min Rafi Urba Wenjie Zhang Jia Gao Lei Fan ^*

• Second Affiliated Hospital, Nanjing Medical University, Nanjing, China

Background The poor reliability of preoperative planning measured by traditional X-ray templates increases the difficulty of osteotomy and prosthesis implantation during an operation, which to some extent affects the surgical outcome of total knee arthroplasty and postoperative satisfaction of patients. Objective To evaluate the accuracy and effectiveness of artificial intelligence (AI) preoperative planning in total knee arthroplasty (TKA). Methods We prospectively selected 48 patients who underwent primary total knee arthroplasty for knee osteoarthritis. The test group included 24 patients who underwent three-dimensional preoperative planning using artificial intelligence (AI), and the control group consisted of 24 patients who underwent two-dimensional preoperative planning using traditional template measurement. For analyzing the accuracy and application effect of the two preoperative planning methods, the intraoperative operation time, intraoperative blood loss, postoperative drainage volume, postoperative lower limb alignment angle, VAS score, and AKS score were compared between the two groups. Results All patients were followed for 6 to 8 months, and no postoperative complications or postoperative deaths occurred in either group. There was no statistically significant difference between the general data of patients in both groups (P>0.05). The complete matching rates of femoral component, tibial component, and tibial liner in the test group were significantly better than those in the control group (P<0.05). The operation time, intraoperative blood loss, and postoperative drainage volume in the test group were significantly less than those in the control group (P<0.05). There was a statistically significant difference in the postoperative lower limb alignment Angle between the two groups (P<0.05). The VAS score of the test group was significantly better than that of the control group within 2 weeks (P<0.05), but there was no statistically significant difference after 1 month (P>0.05). The AKS score of the test group was significantly higher than that of the control group at 3 months after operation (P<0.05). Conclusion Compared with traditional film planning, AI preoperative planning can improve the accuracy of intraoperative prosthesis implantation and the surgical outcome of TKA, which is worthy of further promotion and application in clinical practice.