PDF(Pubmed)
Abstract：
The diagnosis of oral lichen planus (OLP) poses many challenges due to its nonspecific clinical symptoms and histopathological features. Therefore, the diagnostic process should include a thorough clinical history, immunological tests, and histopathology. Our study aimed to enhance the diagnostic accuracy of OLP by integrating direct immunofluorescence (DIF) results with clinical data to develop a multivariate predictive model based on the Artificial Neural Network. Eighty patients were assessed using DIF for various markers (immunoglobulins of classes G, A, and M; complement 3; fibrinogen type 1 and 2) and clinical characteristics such as age, gender, and lesion location. Statistical analysis was performed using machine learning techniques in Statistica 13. The following variables were assessed: gender, age on the day of lesion onset, results of direct immunofluorescence, location of white patches, locations of erosions, treatment history, medications and dietary supplement intake, dental status, smoking status, flossing, and using mouthwash. Four statistically significant variables were selected for machine learning after the initial assessment. The final predictive model, based on neural networks, achieved 85% in the testing sample and 71% accuracy in the validation sample. Significant predictors included stress at onset, white patches under the tongue, and erosions on the mandibular gingiva. In conclusion, while the model shows promise, larger datasets and more comprehensive variables are needed to improve diagnostic accuracy for OLP, highlighting the need for further research and collaborative data collection efforts.
摘要：
口腔扁平苔藓（OLP）的诊断由于其非特异性临床症状和组织病理学特征而面临许多挑战。因此,诊断过程应包括全面的临床病史，免疫学测试,和组织病理学。我们的研究旨在通过将直接免疫荧光（DIF）结果与临床数据相结合来开发基于人工神经网络的多变量预测模型，从而提高OLP的诊断准确性。使用DIF评估了80例患者的各种标记（G类免疫球蛋白，A,和M；补体3；纤维蛋白原1型和2型）和临床特征，如年龄，性别,和病变位置。使用Statistica13中的机器学习技术进行统计分析。评估了以下变量：性别，病变发作当天的年龄，直接免疫荧光的结果，白色斑块的位置，侵蚀的位置，治疗史,药物和膳食补充剂的摄入量，牙齿状况,吸烟状况,使用牙线,用漱口水.在初始评估后，为机器学习选择了四个具有统计学意义的变量。最终的预测模型，基于神经网络，在测试样本中达到85%，在验证样本中达到71%的准确率。重要的预测因素包括发作时的压力，舌头下面的白色斑点，和下颌牙龈上的糜烂。总之,虽然模型显示出希望，需要更大的数据集和更全面的变量来提高OLP的诊断准确性，强调需要进一步研究和协作数据收集工作。
