To further verify the clinical application accuracy of the three-dimensional planning system assisted by artificial intelligence(AI HIP) in total hip arthroplasty (THA)by investigating the accuracy of AI HIP system for prosthesis size prediction before primary THA.

Patients who were scheduled for primary THA at PLA General Hospital First Medical Center, Peking Union Medical College Hospital, the Third Hospital of Hebei Medical University, and the Third Affiliated Hospital of Southern Medical University from August 2021 to August 2022 were included as research subjects. A total of 80 patients who needed primary THA due to hip joint diseases were included, and their preoperative imaging met the planning requirements. The patients who were pregnant or lactating and other reasons not suitable for the experiment were excluded. Finally, 75 patients completed the experiment. The experimental group used AI HIP system for pre-operative planning of THA, while the control group used the traditional X-ray template measurement method. The pre-operative planning results were compared with the actual prosthesis size used during surgery. Statistical tests such as chi square test and Fisher's exact test were used to evaluate the accuracy of the AI HIP system in planning the acetabular cup and femoral stem size.

There were 37 cases in the experimental group: 22 males and 15 females, 20 left hips and 17 right hips, median age 52 (38, 65) years. There were 38 cases in the control group: 25 males and 13 females, 18 left hips and 20 right hips, median age 56 (39, 62) years. The overall accuracy rate of the experimental group in planning the acetabular cup and femoral stem prosthesis size was 89.19% (33/37); the acetabular cup size accuracy rate was 97.30% (36/37), and the femoral stem size accuracy rate was 89.19% (33/37). The overall accuracy rate of the control group in pre-operative planning was 2.63% (1/38); the acetabular cup size accuracy rate was 42.11% (16/38), and the femoral stem size accuracy rate was 21.05% (8/38). The difference in the overall accuracy rates between the two groups was statistically significant (χ²=35.12, P<0.05).

Compared to the traditional Xray template measurement method, the AI HIP system has higher accuracy and reproducibility in planning prosthesis size for pre-operative THA. It can accurately predict the prosthesis size used in primary THA in adults.