Dichter Abigail, Bhatt Khushi, Liu Mohan, Park Timothy, Djalilian Hamid R, Abouzari Mehdi
Division of Neurotology and Skull Base Surgery, Department of Otolaryngology-Head and Neck Surgery, University of California, Irvine, CA 92697, USA.
J Pers Med. 2024 Dec 22;14(12):1170. doi: 10.3390/jpm14121170.
This study aimed to develop a machine learning (ML) algorithm that can predict unplanned reoperations and surgical/medical complications after vestibular schwannoma (VS) surgery. All pre- and peri-operative variables available in the American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) database (n = 110), except those directly related to our outcome variables, were used as input variables. A deep neural network model consisting of seven layers was developed using the Keras open-source library, with a 70:30 breakdown for training and testing. The feature importance of input variables was measured to elucidate their relative permutation effect in the ML model. Of the 1783 patients with VS undergoing surgery, unplanned reoperation, surgical complications, and medical complications were seen in 8.5%, 5.2%, and 6.2% of patients, respectively. The deep neural network model had area under the curve of receiver operating characteristics (ROC-AUC) of 0.6315 (reoperation), 0.7939 (medical complications), and 0.719 (surgical complications). Accuracy, specificity, and negative predictive values of the model for all outcome variables ranged from 82.1 to 96.6%, while positive predictive values and sensitivity ranged from 16.7 to 51.5%. Variables such as the length of stay post-operation until discharge, days from operation to discharge, and the total hospital length of stay had the highest permutation importance. We developed an effective ML algorithm predicting unplanned reoperation and surgical/medical complications post-VS surgery. This may offer physicians guidance into potential post-surgical outcomes to allow for personalized medical care plans for VS patients.
本研究旨在开发一种机器学习（ML）算法，该算法能够预测前庭神经鞘瘤（VS）手术后的非计划再次手术以及手术/医疗并发症。美国外科医师学会国家外科质量改进计划（ACS-NSQIP）数据库（n = 110）中所有术前和围手术期变量，除了那些与我们的结局变量直接相关的变量外，均用作输入变量。使用Keras开源库开发了一个由七层组成的深度神经网络模型，训练和测试的比例为70:30。测量输入变量的特征重要性，以阐明它们在ML模型中的相对排列效应。在1783例接受VS手术的患者中，分别有8.5%、5.2%和6.2%的患者出现了非计划再次手术、手术并发症和医疗并发症。深度神经网络模型的受试者操作特征曲线下面积（ROC-AUC）分别为0.6315（再次手术）、0.7939（医疗并发症）和0.719（手术并发症）。该模型对所有结局变量的准确性、特异性和阴性预测值范围为82.1%至96.6%，而阳性预测值和敏感性范围为16.7%至51.5%。诸如术后直至出院的住院时间、从手术到出院的天数以及总住院时间等变量具有最高的排列重要性。我们开发了一种有效的ML算法，可预测VS手术后的非计划再次手术以及手术/医疗并发症。这可能为医生提供有关潜在术后结局的指导，以便为VS患者制定个性化的医疗护理计划。
