文献速递药物不良反应与药物警戒

无监督机器学习在药物警戒中检测多系统不良事件模式:氟喹诺酮类FAERS报告的概念验证分析

Unsupervised machine learning for multi-system adverse event pattern detection in pharmacovigilance: A proof-of-concept analysis of fluoroquinolone reports in FAERS.
PubMed 文献 · Br J Clin Pharmacol · 2026-09-30

在PT层面最优为两簇,其中多系统簇占10.1%,富集神经精神、肌肉骨骼和感觉相关术语,事后分析显示该簇致残比例更高(43.0% vs 11.7%)。固定特征在氟喹诺酮类中分类14.9%,高于大环内酯类5.3%和阿莫西林3.9%,结论为假设生成性。

要点

  • 无监督聚类可在无先验临床输入下识别氟喹诺酮类多系统不良事件模式。
  • 多系统簇占10.1%,事后致残比例43.0% vs 11.7%。
  • 固定特征分类率氟喹诺酮类14.9%,大环内酯类5.3%,阿莫西林3.9%。

核心结论

  • 无监督聚类在FAERS氟喹诺酮类报告中识别出可重复的多系统不良事件模式,支持药物警戒中无监督探索性模式检测的可行性,但结果严格为假设生成性。

研究设计与样本

  • 以多重对应分析联合k-means为主方法,k-modes和层次聚类验证,聚类数k=2-15通过内部效度指数和bootstrap稳定性评估。

主要发现

  • PT层面轮廓系数和Calinski-Harabasz指数在兩簇时最优(Davies-Bouldin在三簇最优;轮廓系数0.560)。
  • 多系统簇包含4072份报告(10.1%),富集神经精神、肌肉骨骼和感觉术语(lift:记忆障碍8.6、肌肉萎缩8.3、干眼7.8)。
  • 排除严重性和结局后聚类基本不变(保留91.4%;κ 0.95),独立算法在不同粒度下恢复相同亚组。
  • 事后分析显示该簇致残比例显著更高(43.0% vs 11.7%)。
  • 固定特征分类氟喹诺酮类报告的14.9%,大环内酯类5.3%,阿莫西林3.9%。

临床怎么用

  • 提示临床药学人员可关注氟喹诺酮类多系统不良事件模式(神经精神、肌肉骨骼、感觉相关),但仅作为假设生成信号。

局限性

  • 基于自发报告数据库的固有局限性, findings严格为假设生成性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

AIMS: Traditional pharmacovigilance detects single drug-event associations but cannot readily characterize multi-system adverse-event patterns such as fluoroquinolone-associated disability. We evaluated unsupervised machine learning for this purpose, using fluoroquinolones as an exemplar. METHODS: We analysed 40 127 adult fluoroquinolone primary-suspect reports from the FDA Adverse Event Reporting System (FAERS, 2004-2025). Events were encoded as binary MedDRA Preferred Term (PT) and System Organ Class matrices; seriousness and outcome were excluded from clustering and used only post hoc. Multiple correspondence analysis with k-means was primary, validated by k-modes and hierarchical clustering. Cluster number (k = 2-15) was assessed by internal validity indices with bootstrap stability. Comparators were macrolides (n = 39 948) and amoxicillin (n = 16 310). RESULTS: At PT level, silhouette and Calinski-Harabasz indices were optimal at two clusters (Davies-Bouldin at three; silhouette 0.560), separating a multi-system cluster (4072 reports; 10.1%) enriched for neuropsychiatric, musculoskeletal and sensory terms (lifts: memory impairment 8.6, muscle atrophy 8.3, dry eye 7.8). Excluding seriousness and outcome left the cluster essentially unchanged (91.4% retained; κ 0.95), indicating definition by event topology, not case severity; independent algorithms recovered the same subgroup across granularities. Post hoc, the cluster was disproportionately disabling (43.0% vs. 11.7%). The fixed signature classified 14.9% of fluoroquinolone reports vs. 5.3% (macrolides) and 3.9% (amoxicillin). CONCLUSIONS: Unsupervised clustering of FAERS data identified, without prior clinical input, a reproducible multi-system adverse-event pattern among fluoroquinolone reports, potentially supporting the feasibility of unsupervised exploratory pattern detection in pharmacovigilance. Given the limitations of spontaneous reporting databases, the findings are strictly hypothesis-generating.

来源:Br J Clin Pharmacol,查看原文。版权归原作者所有。

引用

  1. Chalabianloo N, Abdullah SS, Sedig K, et al. Unsupervised machine learning for multi-system adverse event pattern detection in pharmacovigilance: A proof-of-concept analysis of fluoroquinolone reports in FAERS. Br J Clin Pharmacol. 2026. PMID: 42815949. doi:10.1002/bcp.70853

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。