Validation of the usefulness of artificial neural networks for risk prediction of adverse drug reactions used for individual patients in clinical practice

Abstract

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.

Predicting Prolonged Length of ICU Stay through Machine Learning

“…Compared to complex DL architecture such as CNN, MLP has a relatively small number of parameters and is less complex. Prediction models based on MLP is expected to be more acceptable in clinical practice than CNN [ 51 ]. The sklearn.MLPClassifier package in Python was used for model development [ 41 ].…”

Key use cases for artificial intelligence to reduce the frequency of adverse drug events: a scoping review

“…14,15 15 (44%) of 34 studies assessed the performance of a single AI model. 13,14,16,17,20,26,[30][31][32]34,36,37,41,42,44 The other studies compared the performance of multiple models with neural networks and tree-based algorithms demonstrating the best performance based on accuracy and AUC-ROC, or other metrics reported in the studies. One study showed similar performance between federated learning (ie, training algorithms using multiple decentralised databases) and centralised approaches for development of AI-based ADE prediction models.…”

Cancer classification and biomarker selection via a penalized logsum network-based logistic regression model

“…The cross-validation (CV) technique has been widely used in parameter tuning. Here, we use a 10-CV method [ 21 , 22 ] to identify the optimal tuning parameters for the training set. Genes with zero coefficients in the predicated model will be considered irrelevant to the predictor variables [ 23 ].…”