AimThe aim of this analysis was to compare a clinical periodontal prognostic system and a developed and externally validated artificial intelligence (AI)‐based model for the prediction of tooth loss in periodontitis patients under supportive periodontal care (SPC) for 10 years.Materials and MethodsClinical and radiographic parameters were analysed to assign tooth prognosis with a tooth prognostic system (TPS) by two calibrated examiners from different clinical centres (London and Pittsburgh). The prediction model was developed on the London dataset. A logistic regression model (LR) and a neural network model (NN) were developed to analyse the data. These models were externally validated on the Pittsburgh dataset. The primary outcome was 10‐year tooth loss in teeth assigned with ‘unfavourable’ prognosis.ResultsA total of 1626 teeth in 69 patients were included in the London cohort (development cohort), while 2792 teeth in 116 patients were included in the Pittsburgh cohort (external validated dataset). While the TPS in the validation cohort exhibited high specificity (99.96%), moderate positive predictive value (PPV = 50.0%) and very low sensitivity (0.85%), the AI‐based model showed moderate specificity (NN = 52.26%, LR = 67.59%), high sensitivity (NN = 98.29%, LR = 91.45%), and high PPV (NN = 89.1%, LR = 88.6%).ConclusionsAI‐based models showed comparable results with the clinical prediction model, with a better performance in specific prognostic risk categories, confirming AI prediction model as a promising tool for the prediction of tooth loss.

中文翻译：

---

探索临床牙周预后系统和机器学习预后模型之间牙齿脱落预测的准确性


目的该分析的目的是比较临床牙周预后系统和开发且经过外部验证的基于人工智能 （AI） 的模型，用于预测接受支持性牙周护理 （SPC） 10 年的牙周炎患者的牙齿脱落。材料和方法分析临床和影像学参数，由来自不同临床中心 （伦敦和匹兹堡） 的两名校准检查员使用牙齿预后系统 （TPS） 分配牙齿预后。预测模型是在 London 数据集上开发的。开发了 logistic 回归模型 （LR） 和神经网络模型 （NN） 来分析数据。这些模型在 Pittsburgh 数据集上进行了外部验证。主要结局是预后为 “不良 ”的牙齿的 10 年牙齿脱落。结果London 队列 （development cohort） 共纳入 69 例患者的 1626 颗牙齿，而 Pittsburgh 队列 （外部验证数据集） 纳入 116 例患者的 2792 颗牙齿。虽然验证队列中的 TPS 表现出高特异性 （99.96%）、中等阳性预测值 （PPV = 50.0%） 和极低敏感性 （0.85%），但基于 AI 的模型显示出中等特异性 （NN = 52.26%， LR = 67.59%）、高敏感性 （NN = 98.29%， LR = 91.45%） 和高 PPV （NN = 89.1%， LR = 88.6%）。结论基于 AI 的模型显示出与临床预测模型相当的结果，在特定的预后风险类别中表现更好，证实了 AI 预测模型是预测牙齿脱落的有前途的工具。