Use of artificial intelligence to identify data elements for The Japanese Orthopaedic Association National Registry from operative records

Published:September 23, 2022DOI:



      The Japanese Orthopaedic Association National Registry (JOANR) was recently launched in Japan and is expected to improve the quality of medical care. However, surgeons must register ten detailed features for total hip arthroplasty, which is labor intensive. One possible solution is to use a system that automatically extracts information about the surgeries. Although it is not easy to extract features from an operative record consisting of free-text data, natural language processing has been used to extract features from operative records. This study aimed to evaluate the best natural language processing method for building a system that automatically detects some elements in the JOANR from the operative records of total hip arthroplasty.


      We obtained operative records of total hip arthroplasty (n = 2574) in three hospitals and targeted two items: surgical approach and fixation technique. We compared the accuracy of three natural language processing methods: rule-based algorithms, machine learning, and bidirectional encoder representations from transformers (BERT).


      In the surgical approach task, the accuracy of BERT was superior to that of the rule-based algorithm (99.6% vs. 93.6%, p < 0.001), comparable to machine learning. In the fixation technique task, the accuracy of BERT was superior to the rule-based algorithm and machine learning (96% vs. 74%, p < 0.0001 and 94%, p = 0.0004).


      BERT is the most appropriate method for building a system that automatically detects the surgical approach and fixation technique.


      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'


      Subscribe to Journal of Orthopaedic Science
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect


        • Rashed S.
        • Lakhani S.
        • Mann A.
        • Best L.M.J.
        • Shehzad S.
        • Saeed M.Z.
        The impact of the largest national Joint registry on current knee replacement longevity estimates: an analysis and review of knee prosthesis brand and fixation technique.
        J Arthroplasty. 2021 Sep; 36 (e1): 3168-3173
        • Lawson K.A.
        • Chen A.F.
        • Springer B.D.
        • Illgen R.L.
        • Lewallen D.G.
        • Huddleston J.I.
        • et al.
        Migration patterns for revision total knee arthroplasty in the United States as reported in the American Joint replacement registry.
        J Arthroplasty. 2021 Oct; 36: 3538-3542
        • Agarwal S.
        • Eckhard L.
        • Walter W.L.
        • Peng A.
        • Hatton A.
        • Donnelly B.
        • et al.
        The use of computer navigation in total hip arthroplasty is associated with a reduced rate of revision for dislocation: a study of 6,912 navigated THA procedures from the Australian orthopaedic association national Joint replacement registry.
        J Bone Joint Surg Am. 2021 Oct 20; 103 (–5): 1900
        • Rankin E.A.
        AJRR: becoming a national US Joint registry.
        Orthopedics. 2013 Mar; 36: 175-176
        • Prime M.S.
        • Palmer J.
        • Khan W.S.
        • Lindeque B.G.P.
        The national Joint registry of england and wales.
        Orthopedics. 2011 Feb; 34: 107-110
        • Graves S.E.
        • Davidson D.
        • Ingerson L.
        • Ryan P.
        • Griffith E.C.
        • McDermott B.F.J.
        • et al.
        The Australian orthopaedic association national Joint replacement registry.
        Med J Aust. 2004 Mar; 180 ([Internet]) (Available from:)
        • Fu S.
        • Wyles C.C.
        • Osmon D.R.
        • Carvour M.L.
        • Sagheb E.
        • Ramazanian T.
        • et al.
        Automated detection of periprosthetic Joint infections and data elements using natural language processing.
        J Arthroplasty. 2021 Feb; 36: 688-692
        • Karhade A.V.
        • Bongers M.E.R.
        • Groot O.Q.
        • Kazarian E.R.
        • Cha T.D.
        • Fogel H.A.
        • et al.
        Natural language processing for automated detection of incidental durotomy.
        Spine J. 2020 May; 20: 695-700
        • Sagheb E.
        • Ramazanian T.
        • Tafti A.P.
        • Fu S.
        • Kremers W.K.
        • Berry D.J.
        • et al.
        Use of natural language processing algorithms to identify common data elements in operative notes for knee arthroplasty.
        J Arthroplasty. 2021 Mar; 36: 922-926
        • Wyles C.C.
        • Tibbo M.E.
        • Fu S.
        • Wang Y.
        • Sohn S.
        • Kremers W.K.
        • et al.
        Use of natural language processing algorithms to identify common data elements in operative notes for total hip arthroplasty.
        J Bone Joint Surg Am. 2019 Nov; 101: 1931-1938
        • Devlin J.
        • Chang M.-W.
        • Lee K.
        • Toutanova K.
        BERT: pre-training of deep bidirectional transformers for language understanding.
        arXiv:181004805. 2019 May 24; ([cs] [Internet]) ([cited 2022 Mar 23]; Available from:)
        • Olthof A.W.
        • Shouche P.
        • Fennema E.M.
        • IJpma F.F.A.
        • Koolstra R.H.C.
        • Stirler V.M.A.
        • et al.
        Machine learning based natural language processing of radiology reports in orthopaedic trauma.
        Comput Methods Progr Biomed. 2021 Sep; 208106304
        • Nakamura Y.
        • Hanaoka S.
        • Nomura Y.
        • Nakao T.
        • Miki S.
        • Watadani T.
        • et al.
        Automatic detection of actionable radiology reports using bidirectional encoder representations from transformers.
        BMC Med Inf Decis Making. 2021 Sep 11; 21: 262
        • Petis S.
        • Howard J.L.
        • Lanting B.L.
        • Vasarhelyi E.M.
        Surgical approach in primary total hip arthroplasty: anatomy, technique and clinical outcomes.
        Can J Surg. 2015 Apr; 58: 128-139
        • Apostu D.
        • Lucaciu O.
        • Berce C.
        • Lucaciu D.
        • Cosma D.
        Current methods of preventing aseptic loosening and improving osseointegration of titanium implants in cementless total hip arthroplasty: a review.
        J Int Med Res. 2018 Jun; 46: 2104-2119
      1. MeCab: yet another part-of-speech and morphological analyzer [Internet]. 2006 (Available from:)
        • Ito K.
        • Nagai H.
        • Okahisa T.
        • Wakamiya S.
        • Iwao T.
        • Aramaki E.
        J-Medic: a Japanese disease name dictionary based on real clinical usage.
        • Sebastiani F.
        Machine learning in automated text categorization.
        ACM Comput Surv. 2002 Mar; 34: 1-47
        • Prokhorenkova L.
        • Gusev G.
        • Vorobev A.
        • Dorogush A.V.
        • Gulin A.
        CatBoost: unbiased boosting with categorical features.
        arXiv:170609516. 2019 Jan 20; ([cited 2022 Mar 23]; Available from:)
        • Kikuta Y.
        BERT pretrained model trained on Japanese Wikipedia articles. [Internet].
        2021 (Available from:)
        • Vaswani A.
        • Shazeer N.
        • Parmar N.
        • Uszkoreit J.
        • Jones L.
        • Gomez A.N.
        • et al.
        Attention is all you need.
        arXiv:170603762. 2017 Dec 5; ([cs] [Internet]) ([cited 2022 Mar 23]; Available from:)
        • Kudo T.
        • Richardson J.
        SentencePiece: a simple and language independent subword tokenizer and detokenizer for Neural Text Processing.
        ([cited 2022 Mar 23])in: Proceedings of the 2018 Conference on Empirical methods in natural language Processing: System Demonstrations. Association for Computational Linguistics, Brussels, Belgium2018: 66-71 (Available from:)
        • Kawazoe Y.
        • Shibata D.
        • Shinohara E.
        • Aramaki E.
        • Ohe K.
        A clinical specific BERT developed using a huge Japanese clinical text corpus.
        PLoS One. 2021; 16e0259763
        • Mutinda F.W.
        • Yada S.
        • Wakamiya S.
        • Aramaki E.
        Semantic textual similarity in Japanese clinical domain texts using BERT.
        Methods Inf Med. 2021 Jun; 60: e56-e64