Adverse drug events (ADEs) significantly impact patient safety and health outcomes. Manual ADE detection from clinical narratives is time-consuming, labor-intensive, and costly. Recent advancements in large language models (LLMs), including transformer-based architectures such as Bidirectional Encoder Representations from Transformers (BERT) and Generative Pretrained Transformer (GPT) series, offer promising methods for automating ADE extraction from clinical data. These models have been applied to various aspects of pharmacovigilance and clinical decision support, demonstrating potential in extracting ADE-related information from real-world clinical data. Additionally, chatbot-assisted systems have been explored as tools in clinical management, aiding in medication adherence, patient engagement, and symptom monitoring. This narrative review synthesizes the current state of LLMs in ADE detection from a clinical perspective, organizing studies into categories such as human-facing decision support tools, immune-related ADE detection, cancer-related and non-cancer-related ADE surveillance, and personalized decision support systems. In total, 39 articles were included in this review. Across domains, LLM-driven methods have demonstrated promising performances, often outperforming traditional approaches. However, critical limitations persist, such as domain-specific variability in model performance, interpretability challenges, data quality and privacy concerns, and infrastructure requirements. By addressing these challenges, LLM-based ADE detection could enhance pharmacovigilance practices, improve patient safety outcomes, and optimize clinical workflows.

This review examines the use of large language models (LLMs) in cancer, analysing articles sourced from PubMed, Embase, and Ovid Medline, published between 2017 and 2024. Our search strategy included terms related to LLMs, cancer research, risks, safeguards, and ethical issues, focusing on studies that utilized text-based data. 59 articles were included in the review, categorized into 3 segments: quantitative studies on LLMs, chatbot-focused studies, and qualitative discussions on LLMs on cancer. Quantitative studies highlight LLMs’ advanced capabilities in natural language processing (NLP), while chatbot-focused articles demonstrate their potential in clinical support and data management. Qualitative research underscores the broader implications of LLMs, including the risks and ethical considerations. Our findings suggest that LLMs, notably ChatGPT, have potential in data analysis, patient interaction, and personalized treatment in cancer care. However, the review identifies critical risks, including data biases and ethical challenges. We emphasize the need for regulatory oversight, targeted model development, and continuous evaluation. In conclusion, integrating LLMs in cancer research offers promising prospects but necessitates a balanced approach focusing on accuracy, ethical integrity, and data privacy. This review underscores the need for further study, encouraging responsible exploration and application of artificial intelligence in oncology.

Preventable medication harm in oncology is often driven by drug-related adverse events (AEs) that trigger order changes such as holds, dose reductions, delays, rechallenges, and enhanced monitoring. Much of the evidence needed to make these decisions lives in unstructured clinical texts, where large language models (LLMs), a type of artificial intelligence (AI), now offer extraction and reasoning capabilities. In this narrative review, we synthesize empirical studies evaluating LLMs and related NLP systems applied to clinical text for oncology AEs, focusing on three decision-linked tasks: (i) AE detection from clinical documentation, (ii) Common Terminology Criteria for Adverse Events (CTCAE) grade assignment, and (iii) grade-aligned actions. We also consider how these findings can inform pharmacist-facing recommendations for order-level safety. We conducted a narrative review of English-language studies indexed in PubMed, Ovid MEDLINE, and Embase. Eligible studies used LLMs on clinical narratives and/or authoritative guidance as model inputs or reference standards; non-text modalities and non-empirical articles were excluded. Nineteen studies met inclusion criteria. LLMs showed the potential to detect oncology AEs from routine notes and often outperformed diagnosis codes for surveillance and cohort construction. CTCAE grading was feasible but less stable than detection; performance improved when outputs were constrained to CTCAE terms/grades, temporally anchored, and aggregated at the patient level. Direct evaluation of grade-aligned actions was uncommon; most studies reported proxies (e.g., steroid initiation or drug discontinuation) rather than formal grade-to-action correctness. While prospective, real-world impact reporting remained sparse, several studies quantified scale advantages and time savings, supporting an initial role as high-recall triage with pharmacist adjudication. Overall, the evidence supports near-term, pharmacist-in-the-loop use of AI for AE surveillance and review, with CTCAE-structured, citation-backed outputs delivered into the pharmacist’s electronic health record order-verification workspace as reviewable artifacts. Future work must standardize reporting and CTCAE/version usage, and measure grade-to-action correctness prospectively, to advance toward order-level decision support.

Opioid-related iatrogenic harms, including opioid use disorder, overdose, and opioid-induced respiratory depression, constitute a major patient safety challenge. Although clinicians document key safety signals in unstructured clinical narratives, many of these indicators are not readily captured by conventional surveillance approaches that rely on structured administrative data. This clinically focused narrative review synthesizes 47 empirical studies published between 2009 and 2025 that applied artificial intelligence (AI) methods to identify opioid-related harms from clinical text and to address the resulting ascertainment gap. Across studies, administrative coding systems, including ICD-10, often under-ascertain opioid-related events, whereas text-based AI can identify additional cases and contextual details often documented primarily in narrative records, such as fluctuating mental status, suspected drug causality, and responses to naloxone. Methodologically, the literature has progressed from interpretable rule-based lexicons to machine learning and deep learning models and, more recently, to transformer-based approaches, including large language models (LLMs) for classification and schema-driven extraction. Rule-based systems established the feasibility of transparent surveillance and frequently recovered clinically documented cases missed by billing codes. Subsequent supervised and deep learning approaches expanded scalability and, in a smaller subset of studies, were integrated into electronic health record workflows with operational metrics reported. More recent transformer- and LLM-based studies emphasize richer extraction schemas and benchmark development, including characterization of overdose context and intentionality and identification of potential prodromal neurocognitive signals, although external validation, calibration, and prospective outcome evaluation remain inconsistently reported. Given that the evidence base is predominantly retrospective and that clinical workflow studies remain comparatively few, a pragmatic near-term clinical role is to provide detection-to-triage decision support rather than autonomous diagnosis, in which systems surface candidate cases with reviewable evidence for clinician adjudication. Future progress will require greater standardization of phenotype definitions, routine equity auditing and subgroup reporting, stronger external validation and calibration at operational thresholds, and a shift from retrospective discrimination metrics toward prospective assessments of the clinical workflow impact, clinical utility, and patient-centered outcomes.