文献速递牙体牙髓病

人工智能在牙髓病学中的应用现状与未来方向

Artificial Intelligence in Endodontics: Current Applications and Future Directions.
PubMed 文献 · J Endod · 2021-06-10

本文为叙述性综述,评估了人工智能在牙髓病学中的现有应用与未来方向。卷积神经网络和/或人工神经网络等AI模型已用于研究根管系统解剖、检测根尖周病变和根折、确定工作长度、预测牙髓干细胞活力及再治疗成功率。AI在检测、判断和疾病预测方面表现出准确性和精确性,但需进一步验证可靠性、适用性和成本效益后才能进入日常临床。

要点

  • AI模型已用于根管解剖研究、根尖周病变与根折检测、工作长度确定等牙髓任务。
  • AI在检测、判断和疾病预测方面表现出准确性和精确性。
  • AI模型进入日常临床前仍需验证可靠性、适用性和成本效益。

核心结论

  • AI在牙髓病学的检测、判断和疾病预测方面表现出准确性和精确性。
  • AI可帮助改善诊断和治疗,从而提高牙髓治疗成功率。
  • AI模型转入日常临床实践前仍需进一步验证可靠性、适用性和成本效益。

研究设计与样本

  • 叙述性综述,评估涉及AI在牙髓病学中应用的文章。

主要发现

  • AI模型(如卷积神经网络和/或人工神经网络)已用于研究根管系统解剖。
  • AI模型已用于检测根尖周病变和根折。
  • AI模型已用于确定工作长度测量。
  • AI模型已用于预测牙髓干细胞活力。
  • AI模型已用于预测再治疗程序的成败。

临床怎么用

  • AI可辅助牙髓病学的诊断与治疗决策,但暂不宜替代临床判断。
  • 将AI模型用于日常临床前应关注其可靠性、适用性和成本效益。

局限性

  • 将AI模型转入日常临床实践前仍需进一步验证其可靠性、适用性和成本效益。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

INTRODUCTION: Artificial intelligence (AI) has the potential to replicate human intelligence to perform prediction and complex decision making in health care and has significantly increased its presence and relevance in various tasks and applications in dentistry, especially endodontics. The aim of this review was to discuss the current endodontic applications of AI and potential future directions. METHODS: Articles that have addressed the applications of AI in endodontics were evaluated for information pertinent to include in this narrative review. RESULTS: AI models (eg, convolutional neural networks and/or artificial neural networks) have demonstrated various applications in endodontics such as studying root canal system anatomy, detecting periapical lesions and root fractures, determining working length measurements, predicting the viability of dental pulp stem cells, and predicting the success of retreatment procedures. The future of this technology was discussed in light of helping with scheduling, treating patients, drug-drug interactions, diagnosis with prognostic values, and robotic-assisted endodontic surgery. CONCLUSIONS: AI demonstrated accuracy and precision in terms of detection, determination, and disease prediction in endodontics. AI can contribute to the improvement of diagnosis and treatment that can lead to an increase in the success of endodontic treatment outcomes. However, it is still necessary to further verify the reliability, applicability, and cost-effectiveness of AI models before transferring these models into day-to-day clinical practice.

来源:J Endod,查看原文。版权归原作者所有。

引用

  1. Aminoshariae A, Kulild J, Nagendrababu V, et al. Artificial Intelligence in Endodontics: Current Applications and Future Directions. J Endod. 2021. PMID: 34119562. doi:10.1016/j.joen.2021.06.003

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。