Brickley M R, Shepherd J P
Department of Oral Surgery, Medicine and Pathology, Dental School, University of Wales College of Medicine, Heath Park, Cardiff.
Br Dent J. 1997 Jan 25;182(2):59-63. doi: 10.1038/sj.bdj.4809299.
To compare the performance of a computer based decision support system (a neural network) and consultant oral and maxillofacial surgeons in making decisions about the need to remove lower third molars.
Receiver operating characteristic (ROC) analysis at a hospital department of oral and maxillofacial surgery.
Three consultant oral and maxillofacial surgeons indicated on a six-point rating scale how certain they were that each of 50 documented lower third molars required removal. Similar data were obtained from the neural network following appropriate coding of the clinical information. These data were compared with gold standard treatment decisions for each tooth based on National Institutes of Health Concensus criteria using ROC analysis.
The area beneath each operator ROC curve (varying between zero and one with greater areas indicating better performance).
The network performed as well a two consultants (P = 0.12/0.18, NS) and significantly better than the third (z = 526, P < 0.01).
This work suggests that this computer based neural network could play a useful role in supporting dental practitioners making third molar referral decisions.
比较基于计算机的决策支持系统（一种神经网络）与口腔颌面外科顾问医生在决定是否需要拔除下颌第三磨牙方面的表现。
在一家医院的口腔颌面外科进行受试者操作特征（ROC）分析。
三位口腔颌面外科顾问医生采用六点评分量表表明他们对50例记录在案的下颌第三磨牙中每一颗是否需要拔除的确定程度。在对临床信息进行适当编码后，从神经网络获得类似数据。使用ROC分析将这些数据与基于美国国立卫生研究院共识标准的每颗牙齿的金标准治疗决策进行比较。
每个操作者ROC曲线下的面积（范围在0到1之间，面积越大表明表现越好）。
该神经网络的表现与两位顾问医生相当（P = 0.12/0.18，无显著性差异），且显著优于第三位顾问医生（z = 5.26，P < 0.01）。
这项研究表明，这种基于计算机的神经网络在支持牙科医生做出第三磨牙转诊决策方面可以发挥有益作用。
