Advertisement
Journal of Prosthetic Dentistry

Comments on “Artificial intelligence applications in restorative dentistry: A systematic review”

Published:September 04, 2021DOI:https://doi.org/10.1016/j.prosdent.2021.08.003
      To the Editor:
      We read the article entitled as “Artificial intelligence (AI) applications in restorative dentistry: A systematic review” by Revilla-León et al
      • Revilla-León M.
      • Gómez-Polo M.
      • Vyas S.
      • Barmak B.A.
      • Özcan M.
      • Att W.
      • et al.
      Artificial intelligence applications in restorative dentistry: a systematic review.
      e-published in the Journal of Prosthetic Dentistry https://doi.org/10.1016/j.prosdent.2021.02.010 with great interest as it familiarized the scientific community with the application of AI in restorative dentistry. However, we would like to highlight certain shortcomings, which should have been taken into consideration to increase the scientific value of this article.
      In their article, the authors conformed to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. However, because the systematic review aimed to evaluate the diagnostic performance of AI in dentistry, it would have been better to use an extension of the PRISMA statement, that is, the PRISMA-Diagnostic Test Accuracy. This extension was introduced to increase the transparency of Diagnostic Test Accuracy systemic reviews.
      • Salameh J.-P.
      • Bossuyt P.M.
      • McGrath T.A.
      • Thombs B.D.
      • Hyde C.J.
      • Macaskill P.
      • et al.
      Preferred reporting items for systematic review and meta-analysis of diagnostic test accuracy studies (PRISMA-DTA): explanation, elaboration, and checklist.
      In the section of Material and Methods, we noted the authors targeted a very wide and heterogenous population under the heading of PICOS model. As restorative dentistry is a very vast term, its application ranges from a simple cavity filling to more complex procedures such as implant-supported prosthesis. Moreover, the purpose of conducting a systematic review is to answer a targeted and specific question to generate high-quality evidence.
      • Fazalare J.A.
      • Griesser M.J.
      • Siston R.A.
      • Flanigan D.C.
      The use of continuous passive motion following knee cartilage defect surgery: a systematic review.
      The authors did not include a control group in their PICOS model; in our opinion, considering a human annotator or reference standard (ground truth) as a control (comparator) would have been better for comparative analysis.
      Furthermore, we noticed the author did not register the review protocol on PROSPERO or any other registry. In line with the PRIMSA guidelines, it is recommended the registration of all systematic reviews on the registry before the start of review.
      • Moher D.
      • Liberati A.
      • Tetzlaff J.
      • Altman D.G.
      • PRISMA Group
      Preferred reporting items for systematic reviews and meta-analyses: the PRISMA statement.
      This is performed to decrease the probability of duplication on a specific scientific query. In addition, this process add significant value to the quality, transparency and reporting of systematic reviews.
      • Booth A.
      • Clarke M.
      • Dooley G.
      • Ghersi D.
      • Moher D.
      • Petticrew M.
      • et al.
      The nuts and bolts of PROSPERO: an international prospective register of systematic reviews.
      For the methodological quality assessment of included studies, the authors used the Joanna Briggs Institute critical appraisal checklist for quasi-experimental studies. However, of 9 questions of this tool, only 4 questions were used to assess the quality of included articles. Because no validated tool is available to assess the quality of AI-related studies, we recommend QUADAS-2
      • Whiting P.F.
      • Rutjes A.W.
      • Westwood M.E.
      • Mallett S.
      • Deeks J.J.
      • Reitsma J.B.
      • et al.
      QUADAS-2: a revised tool for the quality assessment of diagnostic accuracy studies.
      tool for the quality assessment of diagnostic accuracy studies which has been previously used by Mahmood et al.
      • Mahmood H.
      • Shaban M.
      • Indave B.
      • Santos-Silva A.R.
      • Rajpoot N.
      • Khurram S.A.
      Use of artificial intelligence in diagnosis of head and neck precancerous and cancerous lesions: A systematic review.
      We also noted that the literature search strategy could have been more comprehensive. As only 2 studies, which tested an AI model for the detection of vertical root fracture were included,
      • Johari M.
      • Esmaeili F.
      • Andalib A.
      • Garjani S.
      • Saberkari H.
      Detection of vertical root fractures in intact and endodontically treated premolar teeth by designing a probabilistic neural network: an ex vivo study.
      ,
      • Kositbowornchai S.
      • Plermkamon S.
      • Tangkosol T.
      Performance of an artificial neural network for vertical root fracture detection: an ex vivo study.
      the authors did not included the study of Fukuda et al,
      • Fukuda M.
      • Inamoto K.
      • Shibata N.
      • Ariji Y.
      • Yanashita Y.
      • Kutsuna S.
      • et al.
      Evaluation of an artificial intelligence system for detecting vertical root fracture on panoramic radiography.
      which tested an AI model for the detection of vertical root fractures on panoramic radiographs. Sample data set of Fukuda et al comprised 300 panoramic radiographs having 330 teeth with vertical root fractures. By including this study, the results of the review might have been different.

      References

        • Revilla-León M.
        • Gómez-Polo M.
        • Vyas S.
        • Barmak B.A.
        • Özcan M.
        • Att W.
        • et al.
        Artificial intelligence applications in restorative dentistry: a systematic review.
        J Prosthet Dent. 9 April 2021; (https://doi.org/10.1016/j.prosdent.2021.02.010.[Epub ahead of print])
        • Salameh J.-P.
        • Bossuyt P.M.
        • McGrath T.A.
        • Thombs B.D.
        • Hyde C.J.
        • Macaskill P.
        • et al.
        Preferred reporting items for systematic review and meta-analysis of diagnostic test accuracy studies (PRISMA-DTA): explanation, elaboration, and checklist.
        BMJ. 2020; 370: m2632
        • Fazalare J.A.
        • Griesser M.J.
        • Siston R.A.
        • Flanigan D.C.
        The use of continuous passive motion following knee cartilage defect surgery: a systematic review.
        Orthopedics. 2010; 33: 878
        • Moher D.
        • Liberati A.
        • Tetzlaff J.
        • Altman D.G.
        • PRISMA Group
        Preferred reporting items for systematic reviews and meta-analyses: the PRISMA statement.
        J Clin Epidemiol. 2009; 62: 1006-1012
        • Booth A.
        • Clarke M.
        • Dooley G.
        • Ghersi D.
        • Moher D.
        • Petticrew M.
        • et al.
        The nuts and bolts of PROSPERO: an international prospective register of systematic reviews.
        Syst Rev. 2012; 1: 2
        • Whiting P.F.
        • Rutjes A.W.
        • Westwood M.E.
        • Mallett S.
        • Deeks J.J.
        • Reitsma J.B.
        • et al.
        QUADAS-2: a revised tool for the quality assessment of diagnostic accuracy studies.
        Ann Intern Med. 2011; 155: 529-536
        • Mahmood H.
        • Shaban M.
        • Indave B.
        • Santos-Silva A.R.
        • Rajpoot N.
        • Khurram S.A.
        Use of artificial intelligence in diagnosis of head and neck precancerous and cancerous lesions: A systematic review.
        Oral Oncol. 2020; 110: 104885
        • Johari M.
        • Esmaeili F.
        • Andalib A.
        • Garjani S.
        • Saberkari H.
        Detection of vertical root fractures in intact and endodontically treated premolar teeth by designing a probabilistic neural network: an ex vivo study.
        Dentomaxillofac Radiol. 2017; 46: 20160107
        • Kositbowornchai S.
        • Plermkamon S.
        • Tangkosol T.
        Performance of an artificial neural network for vertical root fracture detection: an ex vivo study.
        Dent Traumatol. 2013; 29: 151-155
        • Fukuda M.
        • Inamoto K.
        • Shibata N.
        • Ariji Y.
        • Yanashita Y.
        • Kutsuna S.
        • et al.
        Evaluation of an artificial intelligence system for detecting vertical root fracture on panoramic radiography.
        Oral Radiol. 2020; 36: 337-343