Validation of the usefulness of artificial neural networks for risk prediction of adverse drug reactions used for individual patients in clinical practice
Validation of the usefulness of artificial neural networks for risk prediction of adverse drug reactions used for individual patients in clinical practice
复制标题
DOI：
10.1371/journal.pone.0236789
复制
发表时间：
2020-07-29
期刊：
影响因子：
3.7
通讯作者：
Sugawara, Mitsuru
中科院分区：
文献类型：
--
作者：
Imai, Shungo;Takekuma, Yoh;Sugawara, Mitsuru
人工神经网络是数据挖掘的主要工具，受到人脑和神经系统的启发。研究证明了它们在医学上的用途。然而，还没有研究使用人工神经网络来预测药物不良反应。我们的目的是验证人工神经网络在预测药物不良反应方面的有用性，并重点关注万古霉素引起的肾毒性。为了构建人工神经网络，采用了多层感知器算法。采用 10 倍交叉验证方法来评估所得的人工神经网络。总共招募了1141名2011年11月至2019年2月在北海道大学医院接受万古霉素治疗的患者。在这些患者中，179 名（15.7%）出现了万古霉素引起的肾毒性。在人工神经网络中相对重要的万古霉素肾毒性前三位危险因素是平均万古霉素谷浓度>=13.0mg/L和同时使用哌拉西林-他唑巴坦和血管加压药物。人工神经网络的预测准确率为86.3%，多元逻辑回归模型（传统统计方法）的预测准确率为85.1%。此外，人工神经网络的受试者工作特征曲线下面积（AUROC）为0.83。在10倍交叉验证中，获得的准确率为86.0%，AUROC为0.82。预测万古霉素肾毒性的人工神经网络模型表现出良好的预测性能。这似乎是人工神经网络在药物不良反应风险预测模型中的有用性的第一份报告。
Artificial neural networks are the main tools for data mining and were inspired by the human brain and nervous system. Studies have demonstrated their usefulness in medicine. However, no studies have used artificial neural networks for the prediction of adverse drug reactions. We aimed to validate the usefulness of artificial neural networks for the prediction of adverse drug reactions and focused on vancomycin -induced nephrotoxicity. For constructing an artificial neural network, a multilayer perceptron algorithm was employed. A 10-fold cross validation method was adopted for evaluating the resultant artificial neural network. In total, 1141 patients who received vancomycin at Hokkaido University Hospital from November 2011 to February 2019 were enrolled. Among these patients, 179 (15.7%) developed vancomycin -induced nephrotoxicity. The top three risk factors of vancomycin -induced nephrotoxicity which are relatively important in the artificial neural networks were average vancomycin trough concentration >= 13.0 mg/L and concomitant use of piperacillin-tazobactam and vasopressor drugs. The predictive accuracy of the artificial neural network was 86.3% and that of the multiple logistic regression model (conventional statistical method) was 85.1%. Moreover, area under the receiver operating characteristic curve (AUROC) of the artificial neural network was 0.83. In the 10-fold cross-validation, the accuracy obtained was 86.0% and AUROC was 0.82. The artificial neural network model predicting the vancomycin -induced nephrotoxicity showed good predictive performance. This appears to be the first report of the usefulness of artificial neural networks for an adverse drug reactions risk prediction model.