CoChat
Sign Up
Cited by 64Artificial Intelligence in Healthcare and EducationPharmacovigilance and Adverse Drug ReactionsPharmaceutical Practices and Patient Outcomes

A scoping review on generative AI and large language models in mitigating medication related harm

Open access
Ong, Jasmine Chiat Ling, Chen, Michael Hao, Ng, Ning, Elangovan, Kabilan, Tan, Nichole Yue Ting, Jin, Liyuan, Xie, Qihuang, Ting, Daniel Shu Wei +3 more·2025·npj Digital Medicine
DOI 10.1038/s41746-025-01565-7PMC PMC11953325
Open this paper in CoChat — free account

Abstract

Medication-related harm has a significant impact on global healthcare costs and patient outcomes. Generative artificial intelligence (GenAI) and large language models (LLM) have emerged as a promising tool in mitigating risks of medication-related harm. This review evaluates the scope and effectiveness of GenAI and LLM in reducing medication-related harm. We screened 4 databases for literature published from 1st January 2012 to 15th October 2024. A total of 3988 articles were identified, and 30 met the criteria for inclusion into the final review. Generative AI and LLMs were applied in three key applications: drug-drug interaction identification and prediction, clinical decision support, and pharmacovigilance. While the performance and utility of these models varied, they generally showed promise in early identification, classification of adverse drug events, and supporting decision-making for medication management. However, no studies tested these models prospectively, suggesting a need for further investigation into integration and real-world application.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41746-025-01565-7

Cites

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Ong et al. (2025) identified DDI detection as one of the most promising yet under-validated applications of generative AI for pharmacovigilance.

    “Likewise, Ong et al. (2025) [39], in a scoping review of generative AI for pharmacovigilance, identified DDI detection as one of the most promising yet under-validated applications-a limitation our study begins to address within the oral-surgery context.”

    From Comparing Artificial Intelligence (ChatGPT, Gemini, DeepSeek) and Oral Surgeons in Detecting Clinically Relevant Drug–Drug Interactions in Dental Therapy (2025) · cites this paper as Ong et al. (2025) [39]

    The Discussion (page unavailable) identifies DDI identification and prediction as a key GenAI application and says few studies reported validation performance; the Results add that none tested models prospectively. However, the review lists DDI work and automation of pharmacovigilance as separate applications, rather than identifying DDI detection specifically as a pharmacovigilance application. (LLM, conf=0.83)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

No citation lists for this paper

No citation lists for this paper yet — checked again daily.

References 70 · Cited by 64

Research works printed but not linked: 57

  1. [1]WHO Integrated Health Services MWH. Global burden of preventable medication-related harm in health care: a systematic review. Geneva: World Health Organization. 2023;Licence: CC BY-NC-SA 3.0 IGO.
  2. [2]Muthiah, V., George, A. M., Justine, V. T., Valentin, F. & Gregory, A. R. The global burden of cardiovascular diseases and risk: a compass for future health. J. Am. Coll. Cardiol. 80, 2361–2371 (2022). 36368511
  3. [3]Le, L. H. & Pitts, P. J. Twenty-first century global adr management: a need for clarification, redesign, and coordinated action. Ther. Innov. Regul. Sci. 57, 100–103 (2023). 35951160 PMC9368697
  4. [4]David, W. B. et al. Incidence of adverse drug events and potential adverse drug events. Implications for prevention. ADE Prev. Study Group. JAMA 274, 29–34 (1995). 7791255
  5. [5]David, W. B. et al. The potential of artificial intelligence to improve patient safety: a scoping review. NPJ Digit. Med. 4, 54 (2021). 33742085 PMC7979747
  6. [6]Giordano, C., Brennan, M., Mohamed, B., Rashidi, P. & Modave, F. Accessing artificial intelligence for clinical decision-making. Front. Digit. Health 25, 645232 (2021). PMC8521931 34713115
  7. [7]Choudhury, A. & Asan, O. Role of artificial intelligence in patient safety outcomes: systematic literature review. JMIR Med Inform. 8, e18599 (2020). 32706688 PMC7414411
  8. [8]Smith, J. C., Chen, Q., Denny, J. C., Roden, D. M. & Johnson, K. B. Evaluation of a novel system to enhance clinicians’ recognition of preadmission adverse drug reactions. Appl Clin. Inform. 9, 313–325 (2018). 29742757 PMC5943080
  9. [9]Huang, X. et al. Evaluating the performance of ChatGPT in clinical pharmacy: A comparative study of ChatGPT and clinical pharmacists. Br. J. Clin. Pharmacol. 90, 232–238 (2024). 37626010
  10. [10]Wang, X., Xu, X., Liu, Z. & Tong, W. Bidirectional Encoder Representations from Transformers-like large language models in patient safety and pharmacovigilance: A comprehensive assessment of causal inference implications. Exp. Biol. Med. 248, 1908–1917 (2022). PMC10798182 38084745
  11. [11]Roosan, D. et al. Effectiveness of ChatGPT in clinical pharmacy and the role of artificial intelligence in medication therapy management. J. Am. Pharm. Assoc. 64, 422–428.e8 (2023). 38049066
  12. [12]Ong, J. C. L. et al. Development and testing of a novel large language model-based clinical decision support systems for medication safety in 12 clinical specialties. Arxiv, retreived from: arXiv:2402.01741v2 Accessed on 10 Oct 2024. · arXiv
  13. [13]Al-Ashwal, F. Y., Zawiah, M., Gharaibeh, L., Abu-Farha, R. & Bitar, A. N. Evaluating the sensitivity, specificity, and accuracy of ChatGPT-3.5, ChatGPT-4, Bing AI, and Bard against conventional drug-drug interactions clinical tools. Drug Healthcare Patient Saf.20,137–147 (2023). PMC10518176 37750052
  14. [14]Sulaiman, D. M., Shaba, S. S., Almufty, H. B., Sulaiman, A. M. & Merza, M. A. Screening the drug-drug interactions between antimicrobials and other prescribed medications using Google Bard and Lexicomp® Online™ Database. Cureus 15, e44961 (2023). 37692178 PMC10492649
  15. [15]Ayesha, J. et al. The capability of ChatGPT in predicting and explaining common drug-drug interactions. Cureus 15, e36272 (2023). 37073184 PMC10105894
  16. [16]Yu, H. et al. DGANDDI: Double generative adversarial networks for drug-drug interaction prediction. IEEE/ACM Trans. Comput. Biol. Bioinforma. 20, 1854–1863 (2023). 36423315
  17. [17]Huang, L. et al. EGFI: drug-drug interaction extraction and generation with fusion of enriched entity and sentence information. Brief. Bioinforma. 23, bbab451 (2022). 34791012
  18. [18]Zhou, Y. & Minzhu, X. Polypharmacy side effect prediction based on semi-implicit graph variational auto-encoder. J. Bioinforma. Comput. Biol. 22, 2450020 (2024). 39262053
  19. [19]Zengqian D., Jie X., Yinfei F., Liangcheng D. & Yuanyuan Z. MAVGAE: a multimodal framework for predicting asymmetric drug-drug interactions based on variational graph autoencoder. Comput. Methods Biomech. Biomed. Eng. 10.1080/10255842.2024.2311315. (2024). 38314513 · DOI
  20. [20]Bužančić, I. et al. Clinical decision-making in benzodiazepine deprescribing by healthcare providers vs. AI-assisted approach. Br. J. Clin. Pharmacol. 9010.1111/bcp.15963. (2024). 37949663 · DOI
  21. [21]Sridharan, K. & Sivaramakrishnan, G. Unlocking the potential of advanced large language models in medication review and reconciliation: A proof-of-concept investigation. Explor. Res. Clin. Soc. Pharm. 15, 100492 (2024). 39257533 PMC11385755
  22. [22]Syed, J., Ramesh, M., Pramod Kumar, T. M., Patil, V. & Chalasani, S. H. Dose 4 you: dose division calculator-a tool to reduce calculation errors. Hosp. Pharm. 59, 223–227 (2024). 38450350 PMC10913884
  23. [23]Weidmann, A. E. & Watson, E. W. Novel opportunities for clinical pharmacy research: development of a machine learning model to identify medication related causes of delirium in different patient groups. Int. J. Clin. Pharm. 46, 992–995 (2024). 38594470 PMC11286716
  24. [24]Arya, R. et al. Proactive polypharmacy management using large language models: opportunities to enhance geriatric care. J. Med. Syst. 48, 41 (2024). 38632172 PMC12042286
  25. [26]François, M. et al. Will artificial intelligence chatbots replace clinical pharmacologists? An exploratory study in clinical practice. Eur. J. Clin. Pharmacol. 79, 1375–1384 (2023). 37566133
  26. [27]Elif, Ç., Berkan, A. Assessing the potential role of artificial intelligence in medication-related osteonecrosis of the jaw information sharing. J. Oral Maxillofac. Surg.8210.1016/j.joms.2024.03.001 (2024). 38527729 · DOI
  27. [28]Albogami, Y., Alfakhri, A. & Alaqil, A. Safety and quality of AI chatbots for drug-related inquiries: A real-world comparison with licensed pharmacists. Digit. Health 10, 20552076241253523 (2024). 38757086 PMC11097738
  28. [30]Lorenz, K. et al. Quality of drug allergy information obtained via an artificial intelligence bot versus clinical guidelines. J. Allergy Clin. Immunol. 15310.1016/j.jaci.2023.11.507. (2024). · DOI
  29. [33]Wei, J. et al. Evaluating drug risk using GAN and SMOTE based on CFDA’s spontaneous reporting data. J. Healthc. Eng. 10.1155/2021/6033860 (2021). PMC8418931 34493954 · DOI
  30. [34]Tiffet, T., Pikaar, A., Trombert-Paviot, B., Jaulent, M. C. & Bousquet, C. Comparing a large language model with previous deep learning models on named entity recognition of adverse drug events. Stud. Health Technol. Inform. 316, 781–785 (2024). 39176909
  31. [37]Tjong, E. F. & Sang, K. Introduction to the CoNLL-2003 shared task | Proceedings of the seventh conference on Natural language learning at HLT-NAACL 2003 - Volume 4,142–147. 10.3115/1119176.1119195 (2003). · DOI · Paper page
  32. [38]Li, J. et al. BioCreative V CDR task corpus: a resource for chemical disease relation extraction. Database 10.1093/database/baw068 (2016). PMC4860626 27161011 · DOI
  33. [39]Henry, S., Wang, Y., Shen, F., Uzuner, O. The 2019 National Natural language processing (NLP) Clinical Challenges (n2c2)/Open Health NLP (OHNLP) shared task on clinical concept normalization for clinical records. JAMIA27, 10.1093/jamia/ocaa106 (2020). PMC7647359 32968800 · DOI
  34. [41]Bhagavathula, A. S. et al. Prevalence and determinants of multimorbidity, polypharmacy, and potentially inappropriate medication use in the older outpatients: Findings from EuroAgeism H2020 ESR7 Project in Ethiopia. Pharmaceuticals 14, 844 (2021). 34577544 PMC8468438
  35. [42]Hussain S., Afzal H., Saeed R., Iltaf N. & Umair M. Y. Pharmacovigilance with Transformers: A Framework to Detect Adverse Drug Reactions Using BERT Fine-Tuned with FARM. Comput. Math. Methods Med. 5589829 (2021). PMC8378963 34422092
  36. [43]Grani, G., Lenzi, A. & Velardi, P. Supporting Personalized Health Care With Social Media Analytics: An Application to Hypothyroidism. https://dl.acm.org/doi/10.1145/3468781 (2021). · DOI
  37. [44]Ahmad, F., Abbasi, A., Kitchens, B., Adjeroh, D. A. & Zeng, D. Deep learning for adverse event detection from web search. IEEE Trans. Knowl. Data Eng. 34, 2681–2695 (2022).
  38. [45]Chang, C.-H. et al. in 2023 IEEE 11th International Conference on Healthcare Informatics (ICHI). 168–175 (IEEE Computer Society).
  39. [46]Shi, Y. et al. Leveraging GPT-4 for food effect summarization to enhance product-specific guidance development via iterative prompting. J. Biomed. Inform. 148, 104533 (2023). 37918623
  40. [48]Leape, L. L. et al. Systems analysis of adverse drug events. ADE Prev. Study Group. JAMA 274, 33 (1995). 7791256
  41. [49]Lu, Y. et al. A novel algorithm for analyzing drug-drug interactions from MEDLINE literature. Sci. Rep. 5, 1–10 (2015). PMC4661569 26612138
  42. [50]AA, V. et al. Deploying deep learning models on unseen medical imaging using adversarial domain adaptation. PloS one 17, e0273262 (2022). 36240135 PMC9565422
  43. [51]Sreejith Kumar, A. J. et al. Evaluation of generative adversarial networks for high-resolution synthetic image generation of circumpapillary optical coherence Tomography images for Glaucoma. JAMA Ophthalmol. 140, 974–981 (2022). 36048435 PMC9437828
  44. [54]IA, B. et al. Comparison of ophthalmologist and large language model chatbot responses to online patient eye care questions. JAMA Netw. Open 6, e2330320 (2023). 37606922 PMC10445188
  45. [55]Schmidgall, S. et al. Evaluation and mitigation of cognitive biases in medical language models. NPJ Digit. Med.7. 10.1038/s41746-024-01283-6 (2024). PMC11494053 39433945 · DOI · Paper page
  46. [56]Zack, T. et al. Assessing the potential of GPT-4 to perpetuate racial and gender biases in health care: a model evaluation study. Lancet Digit. Health6. 10.1016/S2589-7500(23)00225-X (2024). 38123252 · DOI · Paper page
  47. [57]Yang, Y., Liu, X., Jin, Q. Unmasking and quantifying racial bias of large language models in medical report generation. Commun. Med.4. 10.1038/s43856-024-00601-z (2024). PMC11387737 39256622 · DOI
  48. [59]Maribel, S. et al. The use of artificial intelligence in pharmacovigilance: a systematic review of the literature. Pharm. Med. 36, 295–306 (2022). 35904529
  49. [60]Syrowatka, A. et al. Key use cases for artificial intelligence to reduce the frequency of adverse drug events: a scoping review. Lancet Digit. Health 4, e137–e148 (2022). 34836823
  50. [65]Ning, Y. et al. Generative artificial intelligence in healthcare: ethical considerations and assessment checklist. Lancet Digit. Health 6, e848–e856 (2023). PMC11542614 39294061
  51. [66]Ke, Y. et al. Development and testing of retrieval augmented generation in large language models -- a case study report. Arxiv. Accessed via: https://arxiv.org/abs/2402.01733 (2024). · arXiv
  52. [67]Rau, S. et al. A retrieval-augmented chatbot based on GPT-4 provides appropriate differential diagnosis in gastrointestinal radiology: a proof of concept study. Eur. Radiol. Exp. 8, 60 (2024). 38755410 PMC11098977
  53. [68]Kresevic, S. et al. Optimization of hepatological clinical guidelines interpretation by large language models: a retrieval augmented generation-based framework. NPJ Digit. Med. 7, 102 (2024). 38654102 PMC11039454
  54. [69]Vaid, A. et al. Using fine-tuned large language models to parse clinical notes in musculoskeletal pain disorders. Lancet Digit. Health 5, e855–e858 (2024). 39492289
  55. [70]Wong, Z. S. Y., Waters, N., Liu, J. & Ushiro, S. A large dataset of annotated incident reports on medication errors. Sci. Data 11, 260 (2024). 38424103 PMC10904777
  56. [71]Daniel, et al. Evaluating and reducing cognitive load should be a priority for machine learning in healthcare. Nat. Med.28, 10.1038/s41591-022-01833-z (2022). 35641825 · DOI
  57. [73]Pais, C. et al. Large language models for preventing medication direction errors in online pharmacies. Nat. Med.10.1038/s41591-024-02933-8 (2024). PMC11186789 38664535 · DOI

Authors
Ong, J. C. L., Chen, M. H., Ng, N., Elangovan, K., Tan, N. Y. T., Jin, L., Xie, Q., Ting, D. S. W., Rodriguez-Monguio, R., Bates, D. W., & Liu, N.
Affiliations
  • University of California, San Francisco (US)
  • Duke-NUS Medical School (SG)
  • SingHealth (SG)
  • Singapore National Eye Center (SG)
  • National University of Singapore (SG)
  • Brigham and Women's Hospital (US)
Corresponding author
Liu, Nan
ORCID
Venue
npj Digital Medicine
Publisher
Springer Science and Business Media LLC
Published
2025-03-28
Volume
8
Issue
1
Pages
182-182
ISSN
2398-6352 (ISSN-L)
DOI
10.1038/s41746-025-01565-7
PMC
PMC11953325
OpenAlex
W4408967642
Cited by
64
References
70
Citations by year
2026: 43 · 2025: 21
FWCI
15.30
Type
journal article
Language
en
Open access
Licence
Locations
  • npj Digital Medicine (publishedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
Duke-NUS Medical School
Topics
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Toxicology › Pharmacovigilance and Adverse Drug Reactions
  • Health Sciences › Medicine › Geriatrics and Gerontology › Pharmaceutical Practices and Patient Outcomes
Keywords
generative AI, large language models, medication-related harm, drug-drug interaction prediction, clinical decision support, pharmacovigilance, adverse drug reactions, medication management, patient safety

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review