机器学习在神经外科手术部位感染预测中的应用。
Machine learning applications for the prediction of surgical site infection in neurological operations.
出版信息
Neurosurg Focus. 2019 Aug 1;47(2):E7. doi: 10.3171/2019.5.FOCUS19241.
OBJECTIVE
Surgical site infection (SSI) following a neurosurgical operation is a complication that impacts morbidity, mortality, and economics. Currently, machine learning (ML) algorithms are used for outcome prediction in various neurosurgical aspects. The implementation of ML algorithms to learn from medical data may help in obtaining prognostic information on diseases, especially SSIs. The purpose of this study was to compare the performance of various ML models for predicting surgical infection after neurosurgical operations.
METHODS
A retrospective cohort study was conducted on patients who had undergone neurosurgical operations at tertiary care hospitals between 2010 and 2017. Supervised ML algorithms, which included decision tree, naive Bayes with Laplace correction, k-nearest neighbors, and artificial neural networks, were trained and tested as binary classifiers (infection or no infection). To evaluate the ML models from the testing data set, their sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV), as well as their accuracy, receiver operating characteristic curve, and area under the receiver operating characteristic curve (AUC) were analyzed.
RESULTS
Data were available for 1471 patients in the study period. The SSI rate was 4.6%, and the type of SSI was superficial, deep, and organ/space in 1.2%, 0.8%, and 2.6% of cases, respectively. Using the backward stepwise method, the authors determined that the significant predictors of SSI in the multivariable Cox regression analysis were postoperative CSF leakage/subgaleal collection (HR 4.24, p < 0.001) and postoperative fever (HR 1.67, p = 0.04). Compared with other ML algorithms, the naive Bayes had the highest performance with sensitivity at 63%, specificity at 87%, PPV at 29%, NPV at 96%, and AUC at 76%.
CONCLUSIONS
The naive Bayes algorithm is highlighted as an accurate ML method for predicting SSI after neurosurgical operations because of its reasonable accuracy. Thus, it can be used to effectively predict SSI in individual neurosurgical patients. Therefore, close monitoring and allocation of treatment strategies can be informed by ML predictions in general practice.
目的
神经外科手术后的手术部位感染（SSI）是一种影响发病率、死亡率和经济学的并发症。目前，机器学习（ML）算法被用于各种神经外科方面的结果预测。从医学数据中学习的 ML 算法的实施可能有助于获得疾病的预后信息，特别是 SSI。本研究的目的是比较各种 ML 模型预测神经外科手术后手术感染的性能。
方法
对 2010 年至 2017 年期间在三级保健医院接受神经外科手术的患者进行了回顾性队列研究。监督 ML 算法，包括决策树、拉普拉斯校正的朴素贝叶斯、k-最近邻和人工神经网络，作为二进制分类器（感染或未感染）进行训练和测试。为了从测试数据集评估 ML 模型，分析了它们的敏感性、特异性、阳性预测值（PPV）和阴性预测值（NPV），以及准确性、接收者操作特征曲线和接收者操作特征曲线下面积（AUC）。
结果
在研究期间，有 1471 名患者的数据可用。SSI 发生率为 4.6%，SSI 类型分别为 1.2%、0.8%和 2.6%的浅表、深部和器官/间隙感染。使用逐步后退法，作者在多变量 Cox 回归分析中确定 SSI 的显著预测因子是术后脑脊液漏/皮下积液（HR 4.24，p < 0.001）和术后发热（HR 1.67，p = 0.04）。与其他 ML 算法相比，朴素贝叶斯算法具有最高的性能，敏感性为 63%，特异性为 87%，PPV 为 29%，NPV 为 96%，AUC 为 76%。
结论
朴素贝叶斯算法是一种准确的 ML 方法，可用于预测神经外科手术后的 SSI，因为它具有合理的准确性。因此，它可以用于有效地预测个别神经外科患者的 SSI。因此，在一般实践中，ML 预测可以为 SSI 提供信息，以便进行密切监测和治疗策略的分配。
Zotero 插件