Predicting clozapine-induced adverse drug reaction biomarkers using machine learning
Bibliographic record
Abstract
Clozapine is an atypical antipsychotic used for patients with treatment-resistant schizophrenia. This drug has serious adverse drug reactions (ADRs), including the risk of severe neutropenia (agranulocytosis). Patients who could benefit from clozapine may not be administered it due to concerns about monitoring ADRs. In addition, traditional toxicological assessments cannot predict clozapine-induced agranulocytosis. Predicting agranulocytosis could improve patient safety. Our study aimed to develop and validate machine learning (ML) models for predicting agranulocytosis in clozapine-prescribed patients using the Canada Vigilance Adverse Reaction Online Database (n = 9395 reports). We addressed the class imbalance (337 agranulocytosis-positive cases vs. 9058 agranulocytosis-negative cases) through systematically evaluating resampling techniques and selecting appropriate performance metrics for rare event prediction. Five ML algorithms were evaluated on a hold-out test set. The best-performing model was the Gradient Boosting with Synthetic Minority Over-sampling technique (GB-SMOTE), achieving recall (sensitivity) of 0.85, AUC-PR (area under the precision-recall (PR) curve) of 0.77, PPV (Positive Predictive Value) of 0.40 and a Matthews Correlation Coefficient of 0.56. SHAP feature analysis identified blood and lymphatic system disorders, leukocytosis, and neutropenia as the strongest predictors. Our results demonstrate the potential of ML for predicting clozapine-induced agranulocytosis and provide a framework for developing pharmacovigilance prediction models. This is clinically important and relevant to the management of schizophrenia, which remains a chronic disease with high morbidity and mortality.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".