Department of Neurosurgery, University Hospital Halle (Saale), Ernst-Grube Str. 40, 06120, Halle, Germany.
Department of Neurosurgery, University Hospital Erlangen, Schwabachanlage 6, 91054, Erlangen, Germany.
J Clin Monit Comput. 2023 Apr;37(2):575-583. doi: 10.1007/s10877-022-00928-9. Epub 2022 Nov 4.
Facial nerve damage in vestibular schwannoma surgery is associated with A-train patterns in free-running EMG, correlating with the degree of postoperative facial palsy. However, anatomy, preoperative functional status, tumor size and occurrence of A-trains clusters, i.e., sudden A-trains in most channels may further contribute. In the presented study, we examine neural networks to estimate postoperative facial function based on such features.
Data from 200 consecutive patients were used to train neural feed-forward networks (NN). Estimated and clinical postoperative House and Brackmann (HB) grades were compared. Different input sets were evaluated.
Networks based on traintime, preoperative HB grade and tumor size achieved good estimation of postoperative HB grades (chi = 54.8), compared to using tumor size or mean traintime alone (chi = 30.6 and 31.9). Separate intermediate nerve or detection of A-train clusters did not improve performance. Removal of A-train cluster traintime improved results (chi = 54.8 vs. 51.3) in patients without separate intermediate nerve.
NN based on preoperative HB, traintime and tumor size provide good estimations of postoperative HB. The method is amenable to real-time implementation and supports integration of information from different sources. NN could enable multimodal facial nerve monitoring and improve postoperative outcomes.
前庭神经鞘瘤手术中的面神经损伤与自由运行 EMG 中的 A 波模式相关，与术后面瘫的程度相关。然而，解剖结构、术前功能状态、肿瘤大小以及 A 波簇的出现，即大多数通道中突然出现 A 波，可能进一步起作用。在本研究中，我们检查神经网络，以基于这些特征估计术后的面神经功能。
使用 200 例连续患者的数据来训练神经前馈网络 (NN)。比较了估计的和临床术后 House 和 Brackmann (HB) 分级。评估了不同的输入集。
与单独使用肿瘤大小或平均训练时间（chi=30.6 和 31.9）相比，基于训练时间、术前 HB 分级和肿瘤大小的网络能够很好地估计术后 HB 分级（chi=54.8）。单独的中间神经或检测到 A 波簇并不能提高性能。在没有单独中间神经的患者中，去除 A 波簇训练时间可改善结果（chi=54.8 比 51.3）。
基于术前 HB、训练时间和肿瘤大小的 NN 可很好地估计术后 HB。该方法适合实时实现，并支持来自不同来源的信息的整合。NN 可以实现多模态面神经监测并改善术后结果。
