Superior performance of artificial intelligence-assisted preoperative planning for total knee arthroplasty in patients under 60 years: a retrospective cross-sectional comparative study

ZENG Ke; YU Shangwei; LIU Liming; GUO Lin

doi:10.16016/j.2097-0927.202512155

您当前的位置：

首页 >

文章列表页 >

Superior performance of artificial intelligence-assisted preoperative planning for total knee arthroplasty in patients under 60 years: a retrospective cross-sectional comparative study

Intelligent Medicine and Prediction Model | 更新时间：2026-03-30

- Superior performance of artificial intelligence-assisted preoperative planning for total knee arthroplasty in patients under 60 years: a retrospective cross-sectional comparative study
- Journal of Army Medical University Vol. 48, Issue 6, Pages: 822-830(2026)
- 作者机构：
  
  1.陆军军医大学（第三军医大学）第一附属医院运动医学中心
  2.陆军军医大学第一附属医院江北院区骨科，重庆
- 作者简介：
- 基金信息：
  
  the National Natural Science Foundation of China(82502964);the Clinical Incubation Project of First Affiliated Hospital of Army Medical University(2024IITZDB16);the Innovative Talent Cultivation Fund of Jiangbei Branch of First Affiliated Hospital of Army Medical University(2025YG009)
- DOI：10.16016/j.2097-0927.202512155
  CLC： R687.4;R319;R445
- Received：29 December 2025，
  
  Revised：2026-02-01，
  
  Published：30 March 2026
- 稿件说明：
移动端阅览
曾科，余尚委，刘力铭，等.人工智能辅助全膝关节置换术前规划在60岁以下患者中的优势表现：一项回顾性横断面对比研究［J］.陆军军医大学学报，2026，48（06）：822-830.DOI：10.16016/j.2097-0927.202512155.

ZENG K，YU S W，LIU L M，et al.Superior performance of artificial intelligence-assisted preoperative planning for total knee arthroplasty in patients under 60 years： a retrospective cross-sectional comparative study［J］.J Army Med Univ，2026，48（06）：822-830.DOI：10.16016/j.2097-0927.202512155.
曾科，余尚委，刘力铭，等.人工智能辅助全膝关节置换术前规划在60岁以下患者中的优势表现：一项回顾性横断面对比研究［J］.陆军军医大学学报，2026，48（06）：822-830.DOI：10.16016/j.2097-0927.202512155. DOI：

ZENG K，YU S W，LIU L M，et al.Superior performance of artificial intelligence-assisted preoperative planning for total knee arthroplasty in patients under 60 years： a retrospective cross-sectional comparative study［J］.J Army Med Univ，2026，48（06）：822-830.DOI：10.16016/j.2097-0927.202512155. DOI：

摘要

目的

探究人工智能（artificial intelligence， AI）辅助全膝关节置换（total knee arthroplasty， TKA）术前规划的准确性是否不劣于三维工程师和医生合作完成的人工TKA术前规划，并评估年龄对AI规划精准度的影响。

方法

本研究采用回顾性、横断面比较设计，回顾性收集127名在2022年12月至2023年9月于陆军军医大学第一附属医院行TKA的患者资料，根据年龄分为≤60岁组（40-60岁，

=22）和

60岁组（61~80岁，

=105）。对所有患者分别进行AI辅助术前规划（AI规划）与计算机辅助人工术前规划（传统规划）。对比患者AI规划、传统规划及术中真实的股骨远端截骨角（hip-knee-shaft angle， HKS）、股骨截骨差、胫骨截骨差、股骨旋转角和假体型号数据，以及AI规划和传统规划的时间、人力及经济成本。非劣效界值设定为截骨角度差≤1°、截骨厚度差≤1 mm、假体型号差≤1个。

结果

与传统规划相比，AI规划HKS平均偏大（0.8±1.2）°，Cohen’s d =0.4（95%

：0.2~0.7）；股骨截骨差平均偏大（1.1±1.8） mm，Cohen’s d=0.5（95%

为0.3~0.8）；胫骨截骨差平均偏大（0.6±1.7）mm，Cohen’s d =0.3（95%

为0~0.5），以上“标准化平均差异”的95%

下限均大于其“负的非劣效界值”。与传统规划相比，≤60岁组AI规划在HKS、胫骨截骨差和股骨旋转角无显著差异（

0.05），

60岁组AI规划仅股骨截骨差的差异超过非劣效性界值（平均偏大1.1 mm，

0.05）。假体型号预测方面，AI规划有73.2%的股骨假体和87.4%的胫骨假体预测型号差异未超过1个型号，传统规划有81.9%的股骨假体和90.6%的胫骨假体预测型号差异未超过1个型号，二者无显著差异。AI规划耗时显著短于传统规划［（27.4±4.1） min

. （45.3±8.5） min，

0.05］，且无需额外人力与设备成本

（患者费用为0元

/例vs.

3 000元/例）。

结论

TKA的AI术前规划具有不劣于传统规划模式的精准度，尤其在60岁以下患者中表现更优，同时具备显著的时间与经济成本优势。

Abstract

Objective

To investigate whether the accuracy of artificial intelligence (AI)-assisted preoperative planning for total knee arthroplasty (TKA) is non-inferior to computer-assisted manual preoperative planning completed collaboratively by 3D engineers and orthopedic surgeons

and to evaluate the impact of age on the accuracy of AI-based planning.

Methods

This study adopted a retrospective

cross-sectional comparative design. Data were retrospectively collected from 127 patients who underwent TKA at the First Affiliated Hospital of Army Medical University between December 2022 and September 2023. They were divided into a ≤60 years group (40 to 60 years old

=22) and an

60 years group (61 to 80 years old

=105) based on age. All patients underwent both AI-assisted preoperative planning (AI planning) and computer-assisted manual preoperative planning (conventional planning). Hip-knee-shaft angle (HKS)

femoral resection difference

tibial resection difference

femoral rotation angle

and prosthesis size data from AI planning

conventional planning

and actual intraoperative measurements

as well as time

manpower

and economic costs of AI planning and conventional planning were compared between the 2 planning methods. The non-inferiority margin was set as resection angle difference ≤1°

resection thickness difference ≤1 mm

and prosthesis size difference ≤1.

Results

Compared with the conventional planning

the AI planning showed a mean increase of 0.8°±1.2° in HKS (Cohen’s d=0.4

95%

: 0.2 to 0.7)

a mean increase of 1.1±1.8 mm in femoral resection difference (Cohen’s d=0.5

95%

: 0.3 to 0.8)

and a mean increase of 0.6±1.7 mm in tibial resection diff

erence (Cohen’s d=0.3

95%

: 0.0 to 0.5). The lower limits of 95%

for these above standardized mean differences were all greater than their corresponding negative non-inferiority margins. In comparison with the conventional planning

the AI planning in the ≤60 years group showed no significant differences in HKS

tibial resection difference

and femoral rotation angle (

0.05)

whereas in the

60 years group

only femoral resection difference of AI planning exceeded the non-inferiority margin (with a mean increase of 1.1 mm

0.05). For prosthesis size prediction

the AI planning achieved 73.2% femoral prosthesis and 87.4% tibial prosthesis predictions with size differences not exceeding 1

while conventional planning achieved 81.9% femoral prosthesis and 90.6% tibial prosthesis predictions with size differences not exceeding 1

with no significant difference between the 2 planning methods (

0.05). The time consumed for AI planning was significantly shorter than that for conventional planning (27.4±4.1

45.3±8.5 min

0.05). Moreover

AI planning required no additional labor and equipment costs

with no additional manpower or equipment costs (0

3 000 Yuan/case).

Conclusion

AI-assisted preoperative planning for TKA s demonstrates non-inferior accuracy compared with conventional planning

with superior performance particularly in patients under 60 years

and significant advantages in time and economic costs.

关键词

Keywords

references

ROBBINS G M ， MASRI B A ， GARBUZ D S ， et al . Preoperative planning to prevent instability in total knee arthroplasty ［J］. Orthop Clin North Am ， 2001 ， 32 （ 4 ）： 611 - 626 ， viii. DOI： 10.1016/s0030-5898（05）70231-5 http://dx.doi.org/10.1016/s0030-5898（05）70231-5 .

GOYAL N ， STULBERG S D . Evaluating the precision of preoperative planning in patient specific instrumentation： can a single MRI yield different preoperative plans？［J］. J Arthroplasty ， 2015 ， 30 （ 7 ）： 1250 - 1253 . DOI： 10.1016/j.arth.2015.02.021 http://dx.doi.org/10.1016/j.arth.2015.02.021 .

文材，尹立 . 人工膝关节置换术的发展概况与进展［J］. 中国医药指南， 2018 ， 16 （ 31 ）： 31 - 34 . DOI： 10.15912/j.cnki.gocm.2018.31.021 http://dx.doi.org/10.15912/j.cnki.gocm.2018.31.021 .

WEN C ， YIN L . Development and progress of artificial knee replacement ［J］. Guide China Med ， 2018 ， 16 （ 31 ）： 31 - 34 . DOI： 10.15912/j.cnki.gocm.2018.31.021 http://dx.doi.org/10.15912/j.cnki.gocm.2018.31.021 .

LEI K ， LIU L M ， YANG P F ， et al . Robotics versus personalized 3D preoperative planning in total knee arthroplasty： a propensity score-matched analysis ［J］. J Orthop Surg Res ， 2022 ， 17 （ 1 ）： 227 . DOI： 10.1186/s13018-022-03115-3 http://dx.doi.org/10.1186/s13018-022-03115-3 .

HE R ， SUN M L ， XIONG R ， et al . A newly designed “SkyWalker” robot applied in total knee arthroplasty： a retrospective cohort study for femoral rotational alignment restoration ［J］. Orthop Surg ， 2022 ， 14 （ 8 ）： 1681 - 1694 . DOI： 10.1111/os.13365 http://dx.doi.org/10.1111/os.13365 .

刘国彬，刘森，王立飞，等 . 一种基于“H”点的全新3D打印个性化截骨导板辅助胫骨高位截骨术的尸体研究［J］. 实用骨科杂志， 2021 ， 27 （ 10 ）： 941 - 946， 950 . DOI： 10.13795/j.cnki.sgkz.2021.10.017 http://dx.doi.org/10.13795/j.cnki.sgkz.2021.10.017 .

LIU G B ， LIU S ， WANG L F ， et al . A novel 3D-printed patient-specific instrument based on “H” point for medial opening-wedge high tibial osteotomy： a cadaver study ［J］. J Pract Orthop ， 2021 ， 27 （ 10 ）： 941 - 946， 950 . DOI： 10.13795/j.cnki.sgkz.2021.10.017 http://dx.doi.org/10.13795/j.cnki.sgkz.2021.10.017 .

VON EISENHART-ROTHE R ， HINTERWIMMER F ， GRAICHEN H ， et al . Artificial intelligence and robotics in TKA surgery： promising options for improved outcomes？［J］. Knee Surg Sports Traumatol Arthrosc ， 2022 ， 30 （ 8 ）： 2535 - 2537 . DOI： 10.1007/s00167-022-07035-x http://dx.doi.org/10.1007/s00167-022-07035-x .

SCHWARZ G M ， SIMON S ， MITTERER J A ， et al . Artificial intelligence enables reliable and standardized measurements of implant alignment in long leg radiographs with total knee arthroplasties ［J］. Knee Surg Sports Traumatol Arthrosc ， 2022 ， 30 （ 8 ）： 2538 - 2547 . DOI： 10.1007/s00167-022-07037-9 http://dx.doi.org/10.1007/s00167-022-07037-9 .

FERNANDES L R ， ARCE C ， MARTINHO G ， et al . Accuracy， reliability， and repeatability of a novel artificial intelligence algorithm converting two-dimensional radiographs to three-dimensional bone models for total knee arthroplasty ［J］. J Arthroplasty ， 2023 ， 38 （ 10 ）： 2032 - 2036 . DOI： 10.1016/j.arth.2022.12.007 http://dx.doi.org/10.1016/j.arth.2022.12.007 .

LIU L M ， LEI K ， CHEN X ， et al . Proximal external femoral torsion increases lateral femoral shaft bowing： a study based on 3D CT reconstruction models ［J］. Knee Surg Phys Traumatol Arthrosc ， 2023 ， 31 （ 4 ）： 1524 - 1532 . DOI： 10.1007/s00167-021-06753-y http://dx.doi.org/10.1007/s00167-021-06753-y .

NAKANO N ， MATSUMOTO T ， HASHIMURA M ， et al . Coronal lower limb alignment in normal knees： a radiographic analysis of 797 normal knee subjects ［J］. Knee ， 2016 ， 23 （ 2 ）： 209 - 213 . DOI： 10.1016/j.knee. 2015. 12.004 http://dx.doi.org/10.1016/j.knee.2015.12.004 .

OTANI T ， WHITESIDE L A ， WHITE S E . Cutting errors in preparation of femoral components in total knee arthroplasty ［J］. J Arthroplasty ， 1993 ， 8 （ 5 ）： 503 - 510 .

HARUTA Y ， KAWAHARA S ， TSUCHIMOCHI K ， et al . Deviation of femoral intramedullary alignment rod influences coronal and sagittal alignment during total knee arthroplasty ［J］. Knee ， 2018 ， 25 （ 4 ）： 644 - 649 . DOI： 10.1016/j.knee. 2018.04.011 http://dx.doi.org/10.1016/j.knee.2018.04.011 .

KINZEL V ， SCADDAN M ， BRADLEY B ， et al . Varus / Valgus alignment of the femur in total knee arthroplasty. Can accuracy be improved by pre-operative CT scanning？［J］. Knee ， 2004 ， 11 （ 3 ）： 197 - 201 . DOI： 10.1016/S0968-0160（03）00106-6 http://dx.doi.org/10.1016/S0968-0160（03）00106-6 .

班吉鹤，李鹏鹏，彭礼禄，等 . 人工智能模拟技术在全膝关节置换术前规划中的应用［J］. 现代实用医学， 2025 ， 37 （ 4 ）： 405 - 407 . DOI： 10.3969/j.issn.1671-0800.2025.04.020 http://dx.doi.org/10.3969/j.issn.1671-0800.2025.04.020 .

BAN J H ， LI P P ， PENG L L ， et al . Application of artificial intelligence simulation technology in pre-planning of total knee replacement ［J］. Mod Pract Med ， 2025 ， 37 （ 4 ）： 405 - 407 . DOI： 10.3969/j.issn.1671-0800.2025.04.020 http://dx.doi.org/10.3969/j.issn.1671-0800.2025.04.020 .

杜浩源，陈达伊，姜嵩，等 . 人工智能三维规划辅助全膝关节置换术的研究［J］. 中文科技期刊数据库（引文版）医药卫生， 2024 （ 1 ）： 121 - 126 .

DU H Y ， CHEN D Y ， JIANG S ， et al . Study on artificial intelligence 3D planning assisted total knee arthroplasty ［J］. Chin Sci J Database（Cit Ed） Med Health ， 2024 （ 1 ）： 121 - 126 .

MAHONEY O M ， KINSEY T . Overhang of the femoral component in total knee arthroplasty： risk factors and clinical consequences ［J］. J Bone Joint Surg Am ， 2010 ， 92 （ 5 ）： 1115 - 1121 . DOI： 10.2106/JBJS.H.00434 http://dx.doi.org/10.2106/JBJS.H.00434 .

FACTOR S ， GUREL R ， DAN D ， et al . Validating a novel 2D to 3D knee reconstruction method on preoperative total knee arthroplasty patient anatomies ［J］. J Clin Med ， 2024 ， 13 （ 5 ）： 1255 . DOI： 10.3390/jcm13051255 http://dx.doi.org/10.3390/jcm13051255 .

吴东，刘星宇，张逸凌，等 . 人工智能辅助全髋关节置换术三维规划系统的研发及临床应用研究［J］. 中国修复重建外科杂志， 2020 ， 34 （ 9 ）： 1077 - 1084 . DOI： 10.7507/1002-1892.202005007 http://dx.doi.org/10.7507/1002-1892.202005007 .

WU D ， LIU X Y ， ZHANG Y L ， et al . Research and application of artificial intelligence based three-dimensional preoperative planning system for total hip arthroplasty ［J］. Chin J Reparative Reconstr Surg ， 2020 ， 34 （ 9 ）： 1077 - 1084 . DOI： 10.7507/1002-1892.202005007 http://dx.doi.org/10.7507/1002-1892.202005007 .

LI S L ， LIU X Y ， CHEN X ， et al . Development and validation of an artificial intelligence preoperative planning and patient-specific instrumentation system for total knee arthroplasty ［J］. Bioengineering ， 2023 ， 10 （ 12 ）： 1417 . DOI： 10.3390/bioengineering10121417 http://dx.doi.org/10.3390/bioengineering10121417 .

LIU L M ， LEI K ， CHEN X ， et al . Is Valgus cut angle based on radiographic measurements in total knee arthroplasty really inaccurate？ a comparison of two- and three-dimensional measurements ［J］. J Knee Surg ， 2022 ， 35 （ 14 ）： 1563 - 1570 . DOI： 10.1055/s-0041-1728785 http://dx.doi.org/10.1055/s-0041-1728785 .

LIU L M ， LEI K ， GUO L ， et al . Surgical transepicondylar axis is not a reliable reference when there was lateral femoral bowing ［J］. Orthop Surg ， 2022 ， 14 （ 12 ）： 3209 - 3215 . DOI： 10.1111/os.13545 http://dx.doi.org/10.1111/os.13545 .

MARCHAND R C ， SODHI N ， BHOWMIK-STOKER M ， et al . Does the robotic arm and preoperative CT planning help with 3D intraoperative total knee arthroplasty planning？［J］. J Knee Surg ， 2019 ， 32 （ 8 ）： 742 - 749 . DOI： 10.1055/s-0038-1668122 http://dx.doi.org/10.1055/s-0038-1668122 .

雷凯，刘力铭，熊然，等 . 全膝关节置换术中智能精准辅助技术的应用及研究进展［J］. 中华创伤杂志， 2022 ， 38 （ 8 ）： 760 - 768 . DOI： 10.3760/cma.j.cn501098-20220322-00206 http://dx.doi.org/10.3760/cma.j.cn501098-20220322-00206 .

LEI K ， LIU L M ， XIONG R ， et al . Application and research progress of intelligent accuracy technological aids in total knee arthroplasty ［J］. Chin J Trauma ， 2022 ， 38 （ 8 ）： 760 - 768 . DOI： 10.3760/cma.j.cn501098-20220322-00206 http://dx.doi.org/10.3760/cma.j.cn501098-20220322-00206 .

LI Z ， ZHANG X F ， DING L L ， et al . Deep learning approach for guiding three-dimensional computed tomography reconstruction of lower limbs for robotically-assisted total knee arthroplasty ［J］. Int J Med Robot ， 2021 ， 17 （ 5 ）： e2300 . DOI： 10.1002/rcs.2300 http://dx.doi.org/10.1002/rcs.2300 .

OETTL F C ， ZSIDAI B ， OEDING J F ， et al . Artificial intelligence and musculoskeletal surgical applications ［J］. HSS J ， 2025 ： 15563316251339596 . DOI： 10.1177/15563316251339596 http://dx.doi.org/10.1177/15563316251339596 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Intelligent neurosurgery: technological convergence, clinical transformation, and future challenges

Artificial intelligence reshaping vaccine development: a new paradigm of efficiency revolution and precision design

Application of artificial intelligence in histopathologic diagnosis and differentiation of extramammary Paget's disease

Establishment of a chest-CT-image-based classification deep learning model for pneumonia prediction

Application value of dual-source virtual non-contrast CT combined with AI in diagnosis of acute intracranial hemorrhage

Related Author

LÜ Shengqing

XIAO Jingjing

GU Jiang

LI Yuhang

Yiwei ZHU

Zhe WU

Xingcai CHEN

Yongjian NIAN

Related Institution

Bio-Med Informatics Research Center, Second Affiliated Hospital，Army Medical University （Third Military Medical University）

Department of Neurosurgery, Second Affiliated Hospital，Army Medical University （Third Military Medical University）

National Engineering Research Center of Immunological Products， Faculty of Pharmacy and Laboratory Medicine，Army Medical University（ Third Military Medical University）

Department of Digital Medicine, Faculty of Biomedical Engineering and Medical Imaging, Army Medical University (Third Military Medical University)

Department of Dermatology, First Affiliated Hospital, Army Medical University (Third Military Medical University)

⁰