Exploring the Potential of the PerioAI System to Support Periodontal Clinical Decision Making: A Proof-of-Principle Study.

IF 6.8 1区医学 Q1 DENTISTRY, ORAL SURGERY & MEDICINE

Journal of Clinical Periodontology Pub Date : 2026-05-03 DOI:10.1111/jcpe.70138

Hairui Li, Yuan Li, Minhui Tan, Zhiming Cui, Dinggang Shen, Andrea Roccuzzo, Maurizio S Tonetti

{"title":"Exploring the Potential of the PerioAI System to Support Periodontal Clinical Decision Making: A Proof-of-Principle Study.","authors":"Hairui Li, Yuan Li, Minhui Tan, Zhiming Cui, Dinggang Shen, Andrea Roccuzzo, Maurizio S Tonetti","doi":"10.1111/jcpe.70138","DOIUrl":null,"url":null,"abstract":"Aim: To explore the potential of PerioAI, an artificial intelligence system integrating intraoral scanning and cone-beam CT, to automatically measure gingival margin-to-bone distance (GBD) and convert it into AI-derived probing depth (AI-PD), and to evaluate whether AI-PD may provide additional information to support periodontal clinical decision making when radiographic imaging represents the primary source of available periodontal information.Materials and methods: This cross-sectional proof-of-principle study included 53 patients with periodontitis (1298 teeth, 7788 sites). GBD measurements were converted to AI-PD using validated formulas. Clinical decision making (prognosis and treatment planning) was evaluated by one periodontist under three information conditions: (i) orthopantomogram (OPG) + original periodontal chart (used to establish the reference clinical decision); (ii) OPG-only; and (iii) OPG + AI-PD. Using the reference clinical decision, agreement rates for clinical decisions obtained under the two information conditions (OPG-only and OPG + AI-PD) were calculated and compared, and the risk of overtreatment was also assessed.Results: Compared with OPG-only, the OPG + AI-PD condition showed higher agreement rate with the reference clinical decision, indicating that PerioAI may provide additional information for clinical decision making. Patient-level average agreement rates increased from 77.6% to 84.7% for prognosis (p < 0.05) and from 78.2% to 84.3% for treatment planning (p < 0.05). Tooth-level agreement rates improved from 78.1% to 86.0% for prognosis (p < 0.05) and from 78.8% to 85.4% for treatment planning (p < 0.05). The addition of AI-PD was associated with a 42.3% reduction in overtreatment risk (Steps 1-2 vs. Step 3) and a 98.5% reduction in the risk of tooth extraction (Step 3 vs. extraction).Conclusions: When combined with radiographic information, PerioAI shows potential to provide incremental information for clinical decision making. Future research should integrate additional periodontal parameters and validate the approach in larger and more diverse populations.","PeriodicalId":15380,"journal":{"name":"Journal of Clinical Periodontology","volume":" ","pages":""},"PeriodicalIF":6.8000,"publicationDate":"2026-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Clinical Periodontology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1111/jcpe.70138","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"DENTISTRY, ORAL SURGERY & MEDICINE","Score":null,"Total":0}

引用次数: 0

Abstract

Aim: To explore the potential of PerioAI, an artificial intelligence system integrating intraoral scanning and cone-beam CT, to automatically measure gingival margin-to-bone distance (GBD) and convert it into AI-derived probing depth (AI-PD), and to evaluate whether AI-PD may provide additional information to support periodontal clinical decision making when radiographic imaging represents the primary source of available periodontal information.

Materials and methods: This cross-sectional proof-of-principle study included 53 patients with periodontitis (1298 teeth, 7788 sites). GBD measurements were converted to AI-PD using validated formulas. Clinical decision making (prognosis and treatment planning) was evaluated by one periodontist under three information conditions: (i) orthopantomogram (OPG) + original periodontal chart (used to establish the reference clinical decision); (ii) OPG-only; and (iii) OPG + AI-PD. Using the reference clinical decision, agreement rates for clinical decisions obtained under the two information conditions (OPG-only and OPG + AI-PD) were calculated and compared, and the risk of overtreatment was also assessed.

Results: Compared with OPG-only, the OPG + AI-PD condition showed higher agreement rate with the reference clinical decision, indicating that PerioAI may provide additional information for clinical decision making. Patient-level average agreement rates increased from 77.6% to 84.7% for prognosis (p < 0.05) and from 78.2% to 84.3% for treatment planning (p < 0.05). Tooth-level agreement rates improved from 78.1% to 86.0% for prognosis (p < 0.05) and from 78.8% to 85.4% for treatment planning (p < 0.05). The addition of AI-PD was associated with a 42.3% reduction in overtreatment risk (Steps 1-2 vs. Step 3) and a 98.5% reduction in the risk of tooth extraction (Step 3 vs. extraction).

Conclusions: When combined with radiographic information, PerioAI shows potential to provide incremental information for clinical decision making. Future research should integrate additional periodontal parameters and validate the approach in larger and more diverse populations.

查看原文本刊更多论文

探索牙周系统支持牙周临床决策的潜力：一项原理证明研究。

目的：探讨结合口腔内扫描和锥形束CT的人工智能系统PerioAI在自动测量牙龈边缘到骨距离（GBD）并将其转换为人工智能探测深度（AI-PD）方面的潜力，并评估AI-PD是否可以在x线影像学是可用牙周信息的主要来源时提供额外的信息，以支持牙周临床决策。材料和方法：这项横断面原理验证研究包括53例牙周炎患者（1298颗牙齿，7788个部位）。使用经过验证的公式将GBD测量值转换为AI-PD。临床决策（预后和治疗计划）由一名牙周病医生在三种信息条件下进行评估：(i)骨科断层扫描(OPG) +原始牙周图（用于建立参考临床决策）；(2) OPG-only;（iii） OPG + AI-PD。使用参考临床决策，计算并比较两种信息条件下（OPG-only和OPG + AI-PD）获得的临床决策的符合率，并评估过度治疗的风险。结果：与单纯OPG相比，OPG + AI-PD与参考临床决策的符合率更高，提示PerioAI可为临床决策提供额外信息。患者水平对预后的平均认同率从77.6%增加到84.7%。结论：当与影像学信息相结合时，PerioAI显示出为临床决策提供增量信息的潜力。未来的研究应该整合更多的牙周参数，并在更大、更多样化的人群中验证这种方法。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Journal of Clinical Periodontology 医学-牙科与口腔外科

CiteScore

13.30

自引率

10.40%

发文量

175

审稿时长

3-8 weeks

期刊介绍： Journal of Clinical Periodontology was founded by the British, Dutch, French, German, Scandinavian, and Swiss Societies of Periodontology. The aim of the Journal of Clinical Periodontology is to provide the platform for exchange of scientific and clinical progress in the field of Periodontology and allied disciplines, and to do so at the highest possible level. The Journal also aims to facilitate the application of new scientific knowledge to the daily practice of the concerned disciplines and addresses both practicing clinicians and academics. The Journal is the official publication of the European Federation of Periodontology but wishes to retain its international scope. The Journal publishes original contributions of high scientific merit in the fields of periodontology and implant dentistry. Its scope encompasses the physiology and pathology of the periodontium, the tissue integration of dental implants, the biology and the modulation of periodontal and alveolar bone healing and regeneration, diagnosis, epidemiology, prevention and therapy of periodontal disease, the clinical aspects of tooth replacement with dental implants, and the comprehensive rehabilitation of the periodontal patient. Review articles by experts on new developments in basic and applied periodontal science and associated dental disciplines, advances in periodontal or implant techniques and procedures, and case reports which illustrate important new information are also welcome.