人工智能术前规划辅助人工全髋关节置换应用效果评价

Effectivenes evaluation of preoperative planning assisted by artificial intelligence for total hip arthroplasty

目的探究人工智能(Artificial intelligence,AI)术前规划辅助人工全髋关节置换术的应用效果。方法回顾性分析自2017-08—2022-04于笔者所在医院行初次单侧人工全髋关节置换者共68例,根据术前规划方式不同进行分组,观察组35例采用AI辅助术前规划,对照组33例采用常规X线片术前规划。比较两组手术时间、术中出血量、术前规划假体准确率以及术后1个月、3个月、6个月、1年、2年髋关节功能Harris评分。结果所有患者均顺利完成手术并获得至少2年随访,所有患者均未出现假体松动、感染、骨折等并发症。观察组手术时间、术中出血量明显少于对照组,差异有统计学意义(P<0.05)。观察组髋臼侧假体准确率为65.7%(23/35)及股骨侧假体准确率为77.1%(27/35),对照组髋臼侧假体准确率为33.3%(11/33)及股骨侧假体准确率为39.4%(13/33);观察组髋臼侧假体准确率、股骨侧假体准确率明显高于对照组,差异均有统计学意义(P<0.05)。观察组术后1个月、3个月、6个月髋关节功能Harris评分明显高于对照组,差异有统计学意义(P<0.05);而两组术后1年、2年髋关节功能Harris评分差异无统计学意义(P>0.05)。结论AI术前规划在人工全髋关节置换术中具有较高的假体预测准确度,能够减少手术时间和术中出血量,有利于患者早期髋关节功能恢复,但是对术后远期髋关节功能影响不明显,仍需进一步研究评价。

Objective To investigate the effectiveness of artificial intelligence(AI)preoperative planning for total hip arthroplasty(THA).Methods A total of 68 cases of primary unilateral total hip arthroplasty from August 2017 to April 2022 at the author's hospital were retrospectively analyzed and grouped according to different preoperative planning methods.Thirty-five cases with AI preoperative planning were categorized into the observation group,and 33 cases with conventional radiographic preoperative planning were categorized into the control group.Surgery time,intraoperative blood loss,accuracy of preoperative planning and post-operative Harris scores of hip function at 1 month,3 months,6 months,1 year,and 2 years were compared between the two groups.Results All patients successfully completed the surgery and received at least 2 years of follow-up,and none of the patients had complications such as loosening of the prosthesis,infection,or fracture.The surgery time and intraoperative blood loss of the observation group were significantly less than those of the control group,and the difference was statistically significant(P<0.05).The accuracy rate of the acetabular component and the femoral component was 65.7%(23/35)and 77.1%(27/35)respectively in the observation group,and 33.3%(11/33)and 39.4%(13/33)respectively in the control group;the accuracy rate in the observation group was significantly higher than that in the control group,and the differences were statistically significant(P<0.05).The Harris scores of hip function in the observation group were significantly higher than those in the control group at 1month,3 months,and 6 months postoperatively,and the difference was statistically significant(P<0.05),while there was no statistically significant difference between the two groups at 1 year and 2 years after surgery(P>0.05).Conclusion AI preoperative planning has a high accuracy of prosthesis prediction intotal hip arthroplasty,which can reduce the surgery time and intraoperative blood loss,and is favorable to the early recovery of hip function of the patients,but the effects on the postoperative long-term hip function are not obvious,and further research is still needed.