{
  "abstract": "Background: Active pharmacovigilance in low-prevalence settings requires review of large electronic health record cohorts. We evaluated a pharmacist-supervised workflow combining electronic triggers with large language model (LLM)-assisted review. Objective: To assess candidate enrichment and stage-specific performance for adverse drug reaction (ADR) surveillance. Methods: In this retrospective cohort study, two pharmacists established a blinded reference standard for 7950 exposure episodes from 7950 unique inpatients. A prespecified Chinese Hospital Pharmacovigilance System trigger selected candidates for Qwen3-4B-Instruct and an institution-specific low-rank adaptation (LoRA)-fine-tuned model trained on 410 patient-disjoint cases involving other medicines. Paired errors were compared using exact McNemar tests. Results: Twenty-eight episodes were ADR-positive. The trigger selected 167 candidates (2.10%), with 100.0% sensitivity (95% confidence interval, 87.66–100.0%) and 98.25% specificity. For the base versus LoRA-fine-tuned model, sensitivity was 82.14% versus 92.86%, specificity 88.49% versus 94.96%, positive predictive value 58.97% versus 78.79%, and F1 score 68.66% versus 85.25%. LoRA reduced false positives from 16 to 7 (9 corrected, 0 new; P = 0.0039). The numerical increase in sensitivity was not statistically significant ( P = 0.250), with only 28 ADR-positive episodes available for evaluation. Conclusions: Trigger-first screening reduced review volume, while LoRA fine-tuning improved false-positive control. LLM classifications should support pharmacist review and should not be used as an autonomous exclusion rule.",
  "abstract_shown": true,
  "affiliations": [
    "School of Electromechanical Engineering, Guangdong University of Technology, Guangzhou, Guangdong, 510006, China",
    "Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, Guangdong, 510120, China",
    "Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, Guangdong, 510120, China; Corresponding author."
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Canhui Liao"
    },
    {
      "affs": [
        0
      ],
      "name": "Xinjun Lai"
    },
    {
      "affs": [
        0
      ],
      "name": "Wenge Chen"
    },
    {
      "affs": [
        1
      ],
      "name": "Jianxiong He"
    },
    {
      "affs": [
        2
      ],
      "name": "Xiaoxia Yu"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/fbcgtddk7tyk5.bib",
  "cited_by": 0,
  "doi": "10.1016/j.rcsop.2026.100866",
  "fulltext_url": "http://www.sciencedirect.com/science/article/pii/S2667276626001642",
  "id": "fbcgtddk7tyk5",
  "issns": [
    "2667-2766"
  ],
  "landing_url": "https://doi.org/10.1016/j.rcsop.2026.100866",
  "language": "en",
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "heading",
      "Article"
    ],
    [
      "lcc",
      "RS1-441"
    ],
    [
      "openalex",
      "3005|Pharmacovigilance and Adverse Drug Reactions"
    ]
  ],
  "openalex": "W7223015685",
  "pdf_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13718469/pdf/?tool=EBI",
  "pmcid": "PMC13718469",
  "pmid": "42959829",
  "published": "2026-10-20",
  "publisher": "Elsevier",
  "ris": "https://research.draconitic.com/paper/fbcgtddk7tyk5.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T13:44:35Z",
      "native_id": "a73603922b6c40beb58d206ce6b58b8f",
      "source": "doaj",
      "url": "https://doi.org/10.1016/j.rcsop.2026.100866"
    },
    {
      "first_seen": "2026-10-31T00:20:38Z",
      "native_id": "PMC:PMC13718469",
      "source": "europepmc",
      "url": "https://europepmc.org/article/PMC/PMC13718469"
    },
    {
      "first_seen": "2026-10-31T12:21:46Z",
      "native_id": "MED:42959829",
      "source": "europepmc",
      "url": "https://europepmc.org/article/MED/42959829"
    },
    {
      "first_seen": "2026-11-02T12:22:29Z",
      "native_id": "PMC13718469",
      "source": "pmc",
      "url": "https://doi.org/10.1016/j.rcsop.2026.100866"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:3005|Pharmacovigilance and Adverse Drug Reactions",
      "subfield": "pharmacology-toxicology"
    }
  ],
  "title": "Trigger-first large language model-assisted adverse drug reaction surveillance: A pharmacist-supervised retrospective cohort study",
  "title_text": "Trigger-first large language model-assisted adverse drug reaction surveillance: A pharmacist-supervised retrospective cohort study",
  "type": "peer-reviewed",
  "updated_at": "2026-11-02T12:22:29Z",
  "url": "https://research.draconitic.com/paper/fbcgtddk7tyk5",
  "venue": "Exploratory Research in Clinical and Social Pharmacy",
  "versions": []
}