Predictive Modeling of Drug-Related Adverse Events with Real-World Data: A Case Study of Linezolid Hematologic Outcomes

Using Machine Learning to Predict Linezolid-Associated Thrombocytopenia

Objective

Using artificial intelligence and machine learning to predict linezolid-induced thrombocytopenia helps identify related risk factors in patients.

Methods

Between January 2020 and December 2023, 284 patients receiving linezolid from Beijing Chaoyang Hospital were enrolled. The data underwent filtering to ensure completeness and quality. The filtered data were then randomly divided into training and validation sets at a 3:1 ratio using stratified sampling. Four machine learning methods-logistic regression, Lasso regression, support vector machine (SVM), and random forest-were employed to develop predictive models on the training set, with optimal hyperparameters determined through grid search. Model performance was assessed via 10 - fold cross - validation on the training set, and the model with the highest AUC was selected. The chosen model was further validated on the independent validation set, with AUC, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) calculated.

Results

During treatment with linezolid, 42 (14.8%) of the 284 patients developed thrombocytopenia, with an average onset of 12.0±5.6 days after starting linezolid therapy. The random forest model demonstrated the best performance, with an AUC of 0.902 (95% CI 0.814-0.991) in the validation set. This model achieved a sensitivity of 81.8%, specificity of 86.9%, positive predictive value (PPV) of 52.9%, and negative predictive value (NPV) of 96.4%.

Conclusion

We developed a machine learning model to predict linezolid-associated thrombocytopenia, with the random forest model achieving an AUC of 0.902. This model can help clinicians assess patient risk and optimize treatment plans. Future work should validate the model in multicenter studies and explore its integration into clinical decision support systems.

Predicting adverse drug event using machine learning based on electronic health records: a systematic review and meta-analysis

Introduction

Adverse drug events (ADEs) pose a significant challenge in current clinical practice. Machine learning (ML) has been increasingly used to predict specific ADEs using electronic health record (EHR) data. This systematic review provides a comprehensive overview of the application of ML in predicting specific ADEs based on EHR data.

Methods

A systematic search of PubMed, Web of Science, Embase, and IEEE Xplore was conducted to identify relevant articles published from the inception to 20 May 2024. Studies that developed ML models for predicting specific ADEs or ADEs associated with particular drugs were included using EHR data.

Results

A total of 59 studies met the inclusion criteria, covering 15 drugs and 15 ADEs. In total, 38 machine learning algorithms were reported, with random forest (RF) being the most frequently used, followed by support vector machine (SVM), eXtreme gradient boosting (XGBoost), decision tree (DT), and light gradient boosting machine (LightGBM). The performance of the ML models was generally strong, with an average area under the curve (AUC) of 76.68% ± 10.73, accuracy of 76.00% ± 11.26, precision of 60.13% ± 24.81, sensitivity of 62.35% ± 20.19, specificity of 75.13% ± 16.60, and an F1 score of 52.60% ± 21.10. The combined sensitivity, specificity, diagnostic odds ratio (DOR), and AUC from the summary receiver operating characteristic (SROC) curve using a random effects model were 0.65 (95% CI: 0.65-0.66), 0.89 (95% CI: 0.89-0.90), 12.11 (95% CI: 8.17-17.95), and 0.8069, respectively. The risk factors associated with different drugs and ADEs varied.

Discussion

Future research should focus on improving standardization, conducting multicenter studies that incorporate diverse data types, and evaluating the impact of artificial intelligence predictive models in real-world clinical settings.

Systematic Review Registration

https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42024565842, identifier CRD42024565842.