Cooper John-Paul, Chue Pierre, Siraki Arno G, Tonoyan Lusine
Faculty of Pharmacy and Pharmaceutical Sciences, College of Health Sciences, University of Alberta, Edmonton, AB, T6G 2R3, Canada.
Faculty of Medicine and Dentistry, College of Health Sciences, University of Alberta, Edmonton, AB, T6G 2R3, Canada.
Sci Rep. 2025 Jul 15;15(1):25572. doi: 10.1038/s41598-025-09472-3.
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.
氯氮平是一种用于治疗难治性精神分裂症患者的非典型抗精神病药物。这种药物有严重的药物不良反应（ADR），包括严重中性粒细胞减少（粒细胞缺乏症）的风险。由于担心监测药物不良反应，那些可能从氯氮平治疗中获益的患者可能无法使用该药物。此外，传统的毒理学评估无法预测氯氮平引起的粒细胞缺乏症。预测粒细胞缺乏症可以提高患者安全性。我们的研究旨在利用加拿大药物警戒不良反应在线数据库（n = 9395份报告）开发并验证用于预测服用氯氮平患者粒细胞缺乏症的机器学习（ML）模型。我们通过系统评估重采样技术并为罕见事件预测选择合适的性能指标来解决类别不平衡问题（337例粒细胞缺乏症阳性病例与9058例粒细胞缺乏症阴性病例）。在一个留出测试集上评估了五种ML算法。表现最佳的模型是采用合成少数过采样技术的梯度提升（GB - SMOTE），召回率（敏感性）为0.85，精确召回率（PR）曲线下面积（AUC - PR）为0.77，阳性预测值（PPV）为0.40，马修斯相关系数为0.56。SHAP特征分析确定血液和淋巴系统疾病、白细胞增多症和中性粒细胞减少症为最强预测因素。我们的结果证明了ML在预测氯氮平引起的粒细胞缺乏症方面的潜力，并为开发药物警戒预测模型提供了一个框架。这在临床上很重要，并且与精神分裂症的管理相关，精神分裂症仍然是一种发病率和死亡率都很高的慢性疾病。
