The final, formatted version of the article will be published soon.
ORIGINAL RESEARCH article
Front. Surg.
Sec. Orthopedic Surgery
Volume 12 - 2025 |
doi: 10.3389/fsurg.2025.1490091
Application of Artificial Intelligence Planning and patient-specific instrument in Total Knee Arthroplasty
Provisionally accepted- 1 Zhongshan Hospital, Fudan University, Shanghai, China
- 2 Tsinghua University, Beijing, Beijing, China
Background: The main objective of this study was to develop an artificial intelligence (AI) preoperative planning and patient-specific instrumentation (PSI) system verify whether PSI could accurately implement preoperative planning and improve femoral prosthesis in terms of coronal alignment and short-term postoperative clinical outcomes compared to traditional Total knee arthroplasty (TKA).Results: Forty-two cases underwent conventional TKA (conventional group), including 18 males and 24 females. The postoperative HKA angle was (178.5±1.4) °, showing significant improvement compared to preoperative values, with statistical significance (t=16.854, P<0.05). Both the navigation group and the conventional group patients successfully underwent surgery and were followed up for at least 3 months. The hemoglobin decrease in the PSI group was (13.50 ± 5.78) g/L, compared to (17.32 ± 9.09) g/L in the manual group (P < 0.05). In the PSI group, the deviation of planned and actual angles at the lateral condyle of the femur was (0-1.8) °(0.7±0.5) °, and at the medial condyle of the tibia was (0-2.1) °(0.9±0.6) °. The planned thickness of the femoral medial condyle resection was (9.1±0.4) mm, and the actual thickness was (7.9±0.3) mm, with a statistically significant difference (t=6.371, P<0.05). The planned thickness of the tibial lateral condyle resection was (9.0±1.1) mm, and the actual thickness was (8.8±1.3) mm, with a statistically significant difference (t=8.981, P<0.05). There was no statistically significant difference between the two groups in terms of HKA, MPTA, and LDFA. There was a statistically significant difference in PCA between the two groups (P=0.021). Comparison of HSS and AKS scores between the two groups showed no statistically significant differences in functional scores before and 3 months after surgery (P>0.05).The use of AI preoperative planning and PSI to assist TKA can improve preoperative planning and achieve precise alignment of the lower limbs, while also reducing intraoperative blood loss. However, no significant differences were observed in coronal alignment and short-term postoperative follow-up results.
Keywords: artificial intelligence, patient-specific instrumentation, Total knee arthoplasty, Preoperative planning, HKA angle
Received: 02 Sep 2024; Accepted: 03 Feb 2025.
Copyright: © 2025 LI, Wang, Cao, Wan, Zhang and Guo. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Zixiang Wang, Zhongshan Hospital, Fudan University, Shanghai, China
Lu Cao, Zhongshan Hospital, Fudan University, Shanghai, China
Shengcheng Wan, Zhongshan Hospital, Fudan University, Shanghai, China
Yiling Zhang, Tsinghua University, Beijing, 100084, Beijing, China
Changan Guo, Zhongshan Hospital, Fudan University, Shanghai, China
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.