在2024年,人工智能(AI)在人工髋膝关节外科领域的应用迎来了诸多令人振奋的进展。AI技术的快速发展,特别是在机器学习、计算机视觉和自然语言处理方面的突破,为关节置换手术的术前规划、手术操作、术后康复以及患者教育等多个环节带来了革命性的变化。从提高手术精准度到个性化治疗计划的制定,再到术后并发症的预测与管理,AI正在成为提升患者治疗效果和生活质量的关键因素。
(1)AI在DDH影像诊断中的应用新进展
图1根据文献规定的阈值,对髋关节进行分类的AI算法分类矩阵,以判断其是否为发育不良。
(2)AI在股骨头坏死影像诊断中的应用新进展
图2向量支持机算法与放射专家对比
(3)AI在膝骨关节炎影像诊断中的应用新进展
(4)AI在髋膝关节假体识别、测量、大小预测中的应用新进展
Antonson等采用计算机辅助设计建模和MATLAB处理和操作衍生成27,020张图像图像,用来训练、验证和测试一个可以实现自动评估的新型卷积神经网络模型。结果此模型区分9种假体的平均准确率达到为97.4%,敏感性88.4%,特异性为98.5%。作者认为,CNN算法检测技术可以准确识别放射学相似的假体。
图3 创建训练图像的过程总结。
图4新衍生生成的特殊图像
图5 THA-AID 识别假体流程
总之,2024年度人工智能(AI)技术在人工关节外科领域的应用正不断取得新的进展。不论是生成式AI对患者问题的回答,或者手术前规划预测假体大小、下肢力线和假体角度,或者在膝骨关节炎、股骨头坏死等骨关节疾病的影像识别,或者预测髋膝关节置换术后预后等等方面,均取得很多进展。A随着技术的不断发展,预计AI将在提高手术精度、优化患者治疗结果以及降低手术并发症发生率等方面发挥更大的潜力,也必将极大地提高了手术的成功率和患者的满意度。
中国人民解放军总医院 骨科医学部 关节外科
致力于机器人、人工智能等技术在骨关节领域的研究与临床应用。
擅长机器人辅助单髁、全膝和全髋置换,关节周围畸形、创伤骨折后遗症的截骨矫形以及肩肘踝关节置换等手术。
任中国生物医学工程学会医学人工智能分会智能外科学组 副组长
中国老年学与老年医学会骨科分会数智骨科学组委员
中国老年学与老年医学会骨科分会保膝学组委员
中国老年保健学会骨关节分会学组委员
北京市医学会骨科学分会关节外科学组青年委员
北京市医学会骨科学分会骨感染学组委员
北京市医学会解剖分会关节外科学组秘书等。
参考文献
1 Aleksander P Mika, J Ryan Martin, Stephen M Engstrom, Gregory G Polkowski, Jacob M Wilson.Assessing ChatGPT Responses to Common Patient Questions Regarding Total Hip Arthroplasty.J Bone Joint Surg Am.2023 Oct 4;105(19):1519-1526.doi: 10.2106/JBJS.23.00209.
2 Matthew L. Magruder; Ariel N. Rodriguez; Che Hang Jason Wong; Orry Erez; Nicolás S. Piuzzi; et alAssessing Ability for ChatGPT to Answer Total Knee Arthroplasty-Related QuestiThe Journal of Arthroplasty 10.1016/j.arth.2024.02.023
3 Sandeep S Bains,Jeremy A Dubin,Daniel Hameed,Oliver C Sax,Scott Douglas,Michael A Mont,et al.Use and Application of Large Language Models for Patient Questions Following Total Knee Arthroplasty.J Arthroplasty.2024 Sep;39(9):2289-2294.doi: 10.1016/j.arth.2024.03.017.
4 Siyuan Zhang, Zi Qiang Glen Liau, Kian Loong Melvin Tan, Wei Liang Chua.Evaluating the accuracy and relevance of ChatGPT responses to frequently asked questions regarding total knee replacement.Knee Surg Relat Res.2024 Apr 2;36(1):15.doi: 10.1186/s43019-024-00218-5.
5 Walter L. Taylor; Ryan Cheng; Aaron I. Weinblatt; Victoria Bergstein; William J. Long .An Artificial Intelligence Chatbot is an Accurate and Useful Online Patient Resource Prior to Total Knee Arthroplasty.The Journal of Arthroplasty.2024-02-11 https://doi.org/10.1016/j.arth.2024.02.005
6JaeWon Yang; Kyle S. Ardavanis; Katherine Slack; Navin D. Fernando; Craig J. Della Valle; et al. Chat Generative Pretrained Transformer (ChatGPT) and Bard: Artificial Intelligence Does not yet Provide Clinically Supported Answers for Hip and Knee Osteoarthritis.Journal of Arthroplasty. 2024 年 5 月;39(5):1184-1190.https://doi.org/10.1016/j.arth.2024.01.029.
7 Benjamín Wright; Michael S. Bodnar; Andrew Moore; Meghan Maseda; Michael P. Kucharik; et al .Is ChatGPT a trusted source of information for total hip and knee arthroplasty patients?Bone & Joint Open 2024 月;5(2):139-146.https://boneandjoint.org.uk/article/10.1302/2633-1462.52.BJO-2023-0113.R1/pdf
8 Xiaojun Hu , Marcel Niemann, Arne Kienzle , Karl Braun , David Alexander Back , Clemens Gwinner , Nora Renz , Ulrich Stoeckle , Andrej Trampuz , Sebastian Meller Evaluating ChatGPT responses to frequently asked patient questions regarding periprosthetic joint infection after total hip and knee arthroplasty.Digit Health.2024 Aug 9 doi: 10.1177/20552076241272620.
9 M Bortoli , M Fiore , S Tedeschi, V Oliveira , R Sousa , A Bruschi , D A Campanacci , P Viale , M De Paolis ,GPT-based chatbot tools are still unreliable in the management of prosthetic joint infections. A Sambri.Musculoskelet Surg,2024 Jul 2. doi: 10.1007/s12306-024-00846-w.
10Alexander Draschl , Georg Hauer , Stefan Franz Fischerauer , Angelika Kogler , Lukas Leitner , Are ChatGPT's Free-Text Responses on Periprosthetic Joint Infections of the Hip and Knee Reliable and Useful?J Clin Med. 2023 Oct 20;12(20):6655。doi: 10.3390/jcm12206655.
11 Omar Musbahi , Martine Nurek , Kyriacos Pouris , Martinique Vella-Baldacchino , Alex Bottle , Caroline Hing , Olga Kostopoulou , Justin P Cobb , Gareth G Jones. Can ChatGPT make surgical decisions with confidence similar to experienced knee surgeons?Knee. 2024 Sep 9:51:120-129.doi: 10.1016/j.knee.2024.08.015..
12 Ryan DeCook, Brian T Muffly, Sania Mahmood, Christopher T Holland, Ayomide M Ayeni, Michael P Ast, AI-Generated Graduate Medical Education Content for Total Joint Arthroplasty: Comparing ChatGPT Against Orthopaedic Fellows.Arthroplast Today. 2024 Jun 4:27:101412 doi: 10.1016/j.artd.2024.101412.
13 Martin Magnéli , Alireza Borjali , Eiji Takahashi , Michael Axenhus , Henrik Malchau, Orhun K Moratoglu , Kartik M Varadarajan.Application of deep learning for automated diagnosis and classification of hip dysplasia on plain radiographs.BMC Musculoskelet Disord. 2024 Feb 9;25(1):117.doi: 10.1186/s12891-024-07244-0.
14 Seong Jun Jang , Daniel A Driscoll , Christopher G Anderson , Ruba Sokrab , Dimitrios A Flevas , David J Mayman , Jonathan M Vigdorchik , Seth A Jerabek , Peter K Sculco Arthroplast Today.Radiographic Findings Associated With Mild Hip Dysplasia in 3869 Patients Using a Deep Learning Measurement Too. 2024 Jun 18:28:101398. doi: 10.1016/j.artd.2024.101398.
15 Min Chen , Ruyi Cai , Aixia Zhang , Xia Chi , Jun Qian l.The diagnostic value of artificial intelligence-assisted imaging for developmental dysplasia of the hip: a systematic review and meta-analysis.J Orthop Surg Res. 2024 Aug 29;19(1):522. doi: 10.1186/s13018-024-05003-4.
16 Xianyue Shen, Jia Luo, Xiongfeng Tang, Bo Chen, Yanguo Qin, You Zhou, Jianlin Xiao .Deep Learning Approach for Diagnosing Early Osteonecrosis of the Femoral Head Based on Magnetic Resonance Imaging.J Arthroplasty. 2023 Oct;38(10):2044-2050.doi: 10.1016/j.arth.2022.10.003. Epub 2022 Oct 13.
17 Xianyue Shen, Ziling He , Yi Shi , Tong Liu , Yuhui Yang , Jia Luo , Yanguo Qin.Development and Validation of an Automated Classification System for Osteonecrosis of the Femoral Head Using Deep Learning Approach: A Multicenter Study.J Arthroplasty. 2024 Feb;39(2):379-386.e2. doi: 10.1016/j.arth.2023.08.018. Epub 2023 Aug 11.
18 Nima Rakhshankhah, Mahdi Abbaszadeh, Atefeh Kazemi , Soroush Soltan Rezaei , Saeid Roozpeykar , Masoud Arabfard.Deep learning approach to femoral AVN detection in digital radiography: differentiating patients and pre-collapse stages.BMC Musculoskelet Disord. 2024 Jul 16;25(1):547。doi: 10.1186/s12891-024-07669-7.
19 Michael Fei, Sarah Lu, Jun Ho Chung, Sherif Hassan, Joseph Elsissy, Brian A Schneiderman.Diagnosing the Severity of Knee Osteoarthritis Using Regression Scores From Artificial Intelligence Convolution Neural Networks.Orthopedics. 2024 Sep-Oct;47(5):e247-e254. doi: 10.3928/01477447-20240718-02. Epub 2024 Jul 29.
20 Jaber Alyami.Identification of Severe Grading in Knee OsteoArthritis from MRI using Ensemble Deep Learning.Curr Med Imaging. 2024:20:e15734056289963.DOI: 10.2174/0115734056289963240318040945
21 Lacksaya Nagarajan , Aadyant Khatri , Arnav Sudan , Raju Vaishya , Sourabh Ghosh .Deep Learning Augmented Osteoarthritis Grading Standardization.Tissue Eng Part A. 2024 Oct;30(19-20):591-604. doi: 10.1089/ten.TEA.2023.0206. Epub 2023 Dec 15.
22 Neil W Antonson, Brandt C Buckner, Beau S Konigsberg, Curtis W Hartman, Kevin L Garvin, Beau J Kildow.Novel Technique for the Identification of Hip Implants Using Artificial Intelligence.J Arthroplasty.2024 May;39(5):1178-1183.doi: 10.1016/j.arth.2024.02.001. Epub 2024 Feb 7.
23 Jaret M Karnuta, Hashim J F Shaikh, Michael P Murphy, Nicholas M Brown, Artificial Intelligence for Automated Implant Identification in Knee Arthroplasty: A Multicenter External Validation Study Exceeding 3.5 Million Plain Radiographs.J Arthroplasty.2023 Oct;38(10):2004-2008.doi: 10.1016/j.arth.2023.03.039.
24 Yeuni Yu , Yoon Jae Cho, Sohee Park , Yun Hak Kim, Tae Sik Goh.Development of an artificial intelligence model for predicting implant size in total knee arthroplasty using simple X-ray images.J Orthop Surg Res. 2024 Aug 27;19(1):516. doi: 10.1186/s13018-024-05013-2.
25 Pouria Rouzrokh , John P Mickley , Bardia Khosravi , Shahriar Faghani , Mana Moassefi , William R Schulz , Bradley J Erickson , Michael J Taunton , Cody C Wyles.THA-AID: Deep Learning Tool for Total Hip Arthroplasty Automatic Implant Detection With Uncertainty and Outlier Quantification.J Arthroplasty. 2024 Apr;39(4):966-973.e17.doi: 10.1016/j.arth.2023.09.025. Epub 2023 Sep 26.
26 Loay A Salman, Harman Khatkar, Abdallah Al-Ani, Osama Z Alzobi , Abedallah Abudalou.Reliability of artificial intelligence in predicting total knee arthroplasty component sizes: a systematic review.Eur J Orthop Surg Traumatol. 2024 Feb;34(2):747-756. doi: 10.1007/s00590-023-03784-8. Epub 2023 Nov 27.
27 Varun Digumarthi , Tapan Amin, Samuel Kanu, Joshua Mathew, Bryan Edwards, Lisa A Peterson, Matthew E Lundy, Karen E Hegarty.Preoperative prediction model for risk of readmission after total joint replacement surgery: a random forest approach leveraging NLP and unfairness mitigation for improved patient care and cost-effectiveness.J Orthop Surg Res. 2024 May 10;19(1):287. doi: 10.1186/s13018-024-04774-0.
28 Joshua R Labott, Yining Lu, Harold I Salmons, Christopher L Camp, Cody C Wyles, Michael J Taunton.Health and Socioeconomic Risk Factors for Unplanned Hospitalization Following Ambulatory Unicompartmental Knee Arthroplasty: Development of a Patient Selection Tool Using Machine Learning.J Arthroplasty. 2023 Oct;38(10):1982-1989.doi: 10.1016/j.arth.2023.01.026. Epub 2023 Jan 26.
29 Mohamad Y Fares, Harry H Liu, Ana Paula Beck da Silva Etges, Benjamin Zhang, Jon J P Warner, Jeffrey J Olson, Catherine J Fedorka,Utility of Machine Learning, Natural Language Processing, and Artificial Intelligence in Predicting Hospital Readmissions After Orthopaedic Surgery: A Systematic Review and Meta-Analysis.JBJS Rev. 2024 Aug 22;12(8). doi: 10.2106/JBJS.RVW.24.00075.
30 Christian A Pean, Anirudh Buddhiraju, Michelle R Shimizu, Tony L-W Chen, John G Esposito, Young-Min Kwon.Prediction of 30-Day Mortality Following Revision Total Hip and Knee Arthroplasty: Machine Learning Algorithms Outperform CARDE-B, 5-Item, and 6-Item Modified Frailty Index Risk Scores. JArthroplasty.2024Nov;39(11):2824-2830.doi:10.1016/j.arth.2024.05.056.
31 Jennifer Hunter , Farzan Soleymani , Herna Viktor , Wojtek Michalowski , Stéphane Poitras , Paul E Beaulé.Using Unsupervised Machine Learning to Predict Quality of Life After Total Knee Arthroplasty.J Arthroplasty. 2024 Mar;39(3):677-682. doi: 10.1016/j.arth.2023.09.027. Epub 2023 Sep 26.
32 Yining Lu , Harold I Salmons , John P Mickley , Nicholas A Bedard, Michael J Taunton , Cody C Wyles.Defining Clinically Meaningful Subgroups for Risk Stratification in Patients Undergoing Revision Total Hip Arthroplasty: A Combined Unsupervised and Supervised Machine Learning Approach.J Arthroplasty.2023 Oct;38(10):1990-1997.e1. doi: 10.1016/j.arth.2023.06.027. Epub 2023 Jun 17.
33 Elan A Karlin , Charles C Lin , Morteza Meftah, James D Slover, Ran Schwarzkopf.The Impact of Machine Learning on Total Joint Arthroplasty Patient Outcomes: A Systemic Review.J Arthroplasty. 2023 Oct;38(10):2085-2095. doi: 10.1016/j.arth.2022.10.039. Epub 2022 Oct 29.