Machine-learning-based adverse drug event prediction from observational health data: A review

Denck, Jonas; Özkırımlı, Elif; Wang, Ken

doi:10.1016/j.drudis.2023.103715

Cited by 5 publications

(1 citation statement)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To achieve generalisation, models are validated in independent samples not used for model building. Published machine learning models have used demographics, diagnoses, laboratory values and medication information across various drugs to predict side effects in clinical trials and electronic health record data 16 . For antidepressants, treatment response and improvement in depression severity have been mostly studied within groups of individuals receiving the same treatment 17 .…”

Section: Introductionmentioning

confidence: 99%

Prediction of antidepressant side effects in the Genetic Link to Anxiety and Depression Study

Li,

Lin,

Davies

et al. 2024

Preprint

View full text Add to dashboard Cite

Antidepressants are the most common treatment for moderate or severe depression. Side effects are crucial indicators for antidepressants, but their expression varies widely among individuals. In this study, we leveraged genetic and medical data from self-reported questionnaires in the Genetic Links to Anxiety and Depression (GLAD) study to build prediction models of side effects and subsequent discontinuation across three antidepressant classes (SSRI, SNRI, tricyclic antidepressant (TCA)) at the first and the last (most recent) year of prescription. We included 259 predictors spanning genetic, clinical, illness, demographic, and antidepressant information. Six prediction models were trained, and their performance was compared. The final dataset comprised 4354 individuals taking SSRI in the first prescription and 3414 taking SSRI, SNRI or TCA in the last year of prescription. In the first year, the best area under the receiver operating characteristic curve (AUROC) for predicting SSRI discontinuation and side effects were 0.65 and 0.60. In the last year of SSRI prescription, the highest AUROC reached 0.73 for discontinuation and 0.87 for side effects. Models for predicting discontinuation and side effects of SNRI and TCA showed comparable performance. The history of side effects and discontinuation of antidepressant use were the most influential predictors of the outcomes in the last year of prescription. When examining 30 common antidepressant side effect symptoms, most of them were differentially prevalent between antidepressant classes. Our findings suggested the feasibility of predicting antidepressant side effects using a self-reported questionnaire, particularly for the last prescription. These results could contribute valuable insights for the development of clinical decisions aimed at optimising treatment selection with enhanced tolerability.

show abstract

Section: Introductionmentioning

confidence: 99%

Prediction of antidepressant side effects in the Genetic Link to Anxiety and Depression Study

Li,

Lin,

Davies

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

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

Patel,

Doernberg,

Zack

et al. 2024

Clin Pharma and Therapeutics

View full text Add to dashboard Cite

Electronic health records (EHRs) provide meaningful knowledge of drug‐related adverse events (AEs) that are not captured in standard drug development and postmarketing surveillance. Using variables obtained from EHR data in the University of California San Francisco de‐identified Clinical Data Warehouse, we aimed to evaluate the potential of machine learning to predict two hematological AEs, thrombocytopenia and anemia, in a cohort of patients treated with linezolid for 3 or more days. Features for model input were extracted at linezolid initiation (index), and outcomes were characterized from index to 14 days post‐treatment. Random forest classification (RFC) was used for AE prediction, and reduced feature models were evaluated using cumulative importance (cImp) for feature selection. Grade 3+ thrombocytopenia and anemia occurred in 31% of 2,171 and 56% of 2,170 evaluable patients, respectively. Of the total 53 features, as few as 7 contributed at least 50% cImp, resulting in prediction accuracies of 70% or higher and area under the receiver operating characteristic curves of 0.886 for grade 3+ thrombocytopenia and 0.759 for grade 3+ anemia. Sensitivity analyses in strictly defined patient subgroups revealed similarly high predictive performance in full and reduced feature models. A logistic regression model with the same 50% cImp features showed similar predictive performance as RFC and good concordance with RFC probability predictions after isotonic calibration, adding interpretability. Collectively, this work demonstrates potential for machine learning prediction of AE risk in real‐world patients using few variables regularly available in EHRs, which may aid in clinical decision making and/or monitoring.

show abstract

A real-world pharmacovigilance study on cardiovascular adverse events of tisagenlecleucel using machine learning approach

Jung,

Kim,

Bae

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Chimeric antigen receptor T-cell (CAR-T) therapies are a paradigm-shifting therapeutic in patients with hematological malignancies. However, some concerns remain that they may cause serious cardiovascular adverse events (AEs), for which data are scarce. In this study, gradient boosting machine algorithm-based model was fitted to identify safety signals of serious cardiovascular AEs reported for tisagenlecleucel in the World Health Organization Vigibase up until February 2024. Input dataset, comprised of positive and negative controls of tisagenlecleucel based on its labeling information and literature search, was used to train the model. Then, we implemented the model to calculate the predicted probability of serious cardiovascular AEs defined by preferred terms included in the important medical event list from European Medicine Agency. There were 467 distinct AEs from 3,280 safety cases reports for tisagenlecleucel, of which 363 (77.7%) were classified as positive controls, 66 (14.2%) as negative controls, and 37 (7.9%) as unknown AEs. The prediction model had area under the receiver operating characteristic curve of 0.76 in the test dataset application. Of the unknown AEs, six cardiovascular AEs were predicted as the safety signals: bradycardia (predicted probability 0.99), pleural effusion (0.98), pulseless electrical activity (0.89), cardiotoxicity (0.83), cardio-respiratory arrest (0.69), and acute myocardial infarction (0.58). Our findings underscore vigilant monitoring of acute cardiotoxicities with tisagenlecleucel therapy.

show abstract

Machine-learning-based adverse drug event prediction from observational health data: A review

Cited by 5 publications

References 70 publications

Prediction of antidepressant side effects in the Genetic Link to Anxiety and Depression Study

Prediction of antidepressant side effects in the Genetic Link to Anxiety and Depression Study

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

A real-world pharmacovigilance study on cardiovascular adverse events of tisagenlecleucel using machine learning approach

Contact Info

Product

Resources

About