A systematic mapping review on the capability of large language models in drug-drug interaction analysis.

IF 3 3区医学 Q2 PHARMACOLOGY & PHARMACY

Expert Review of Clinical Pharmacology Pub Date : 2025-09-29 DOI:10.1080/17512433.2025.2568090

Himel Mondal, Ipsita Dash, Shaikat Mondal, Seshadri Reddy Varikasuvu, Rintu Kumar Gayen, Shreya Sharma, Sairavi Kiran Biri

{"title":"A systematic mapping review on the capability of large language models in drug-drug interaction analysis.","authors":"Himel Mondal, Ipsita Dash, Shaikat Mondal, Seshadri Reddy Varikasuvu, Rintu Kumar Gayen, Shreya Sharma, Sairavi Kiran Biri","doi":"10.1080/17512433.2025.2568090","DOIUrl":null,"url":null,"abstract":"Background: Drug-drug interaction (DDI) is a global health concern affecting patient safety and treatment outcomes. Large language models (LLMs), such as ChatGPT, offer accessible alternatives; however, their effectiveness in DDI analysis remains unclear. This review evaluates the current evidence on the performance of LLM-based chatbots in identifying DDIs.Methods: A PRISMA-compliant systematic review (PROSPERO: CRD420251020360) was conducted using PubMed, Scopus, and Web of Science (studies published between 1 January 2015, and 31 March 2025). Eligible studies included those using publicly accessible LLM chatbots for DDI detection.Results: Nine studies (2023-2025) evaluated publicly accessible LLM chatbots, including ChatGPT, Bing AI, and Google Bard, for DDI identification. Methods varied from patient-level polypharmacy screening to single-drug checks and case vignettes. Chatbot performance was inconsistent: ChatGPT identified many potential DDIs, with ChatGPT-4.0 generally identifying more potential DDIs, but with variable accuracy, while Bing AI and Google Bard were less reliable.Conclusion: Publicly accessible LLM chatbots demonstrate variable and partial effectiveness in detecting DDIs. There is a clear need to develop dedicated, freely available chatbots designed specifically for DDI identification. Future research should focus on standardizing evaluation methods and expanding access to improve medication safety in clinical practice.Prospero: CRD420251020360.","PeriodicalId":12207,"journal":{"name":"Expert Review of Clinical Pharmacology","volume":" ","pages":"1-8"},"PeriodicalIF":3.0000,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Expert Review of Clinical Pharmacology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1080/17512433.2025.2568090","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"PHARMACOLOGY & PHARMACY","Score":null,"Total":0}

引用次数: 0

Abstract

Background: Drug-drug interaction (DDI) is a global health concern affecting patient safety and treatment outcomes. Large language models (LLMs), such as ChatGPT, offer accessible alternatives; however, their effectiveness in DDI analysis remains unclear. This review evaluates the current evidence on the performance of LLM-based chatbots in identifying DDIs.

Methods: A PRISMA-compliant systematic review (PROSPERO: CRD420251020360) was conducted using PubMed, Scopus, and Web of Science (studies published between 1 January 2015, and 31 March 2025). Eligible studies included those using publicly accessible LLM chatbots for DDI detection.

Results: Nine studies (2023-2025) evaluated publicly accessible LLM chatbots, including ChatGPT, Bing AI, and Google Bard, for DDI identification. Methods varied from patient-level polypharmacy screening to single-drug checks and case vignettes. Chatbot performance was inconsistent: ChatGPT identified many potential DDIs, with ChatGPT-4.0 generally identifying more potential DDIs, but with variable accuracy, while Bing AI and Google Bard were less reliable.

Conclusion: Publicly accessible LLM chatbots demonstrate variable and partial effectiveness in detecting DDIs. There is a clear need to develop dedicated, freely available chatbots designed specifically for DDI identification. Future research should focus on standardizing evaluation methods and expanding access to improve medication safety in clinical practice.

Prospero: CRD420251020360.

查看原文本刊更多论文

大型语言模型在药物-药物相互作用分析中的能力综述。

背景：药物-药物相互作用（DDI）是影响患者安全和治疗结果的全球健康问题。大型语言模型（llm），如ChatGPT，提供了可访问的替代方案；然而，它们在DDI分析中的有效性尚不清楚。这篇综述评估了目前基于法学硕士的聊天机器人在识别ddi方面的表现。方法：使用PubMed、Scopus和Web of Science（发表于2015年1月1日至2025年3月31日之间的研究）进行符合prisma标准的系统评价（PROSPERO: CRD420251020360）。符合条件的研究包括使用可公开访问的LLM聊天机器人进行DDI检测的研究。结果：9项研究（2023-2025）评估了可公开访问的LLM聊天机器人，包括ChatGPT、Bing AI和b谷歌Bard，用于DDI识别。方法从患者层面的多药筛查到单药检查和病例调查。聊天机器人的表现不一致：ChatGPT识别了许多潜在的ddi， ChatGPT-4.0通常识别出更多潜在的ddi，但准确率不一，而Bing AI和谷歌Bard的可靠性较差。结论：可公开访问的LLM聊天机器人在检测ddi方面表现出可变和部分的有效性。显然有必要开发专门用于DDI识别的专用、免费的聊天机器人。今后的研究应着眼于规范评价方法和扩大可及性，以提高临床用药安全性。普洛斯彼罗:CRD420251020360。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Expert Review of Clinical Pharmacology PHARMACOLOGY & PHARMACY-

CiteScore

7.30

自引率

2.30%

发文量

127

期刊介绍： Advances in drug development technologies are yielding innovative new therapies, from potentially lifesaving medicines to lifestyle products. In recent years, however, the cost of developing new drugs has soared, and concerns over drug resistance and pharmacoeconomics have come to the fore. Adverse reactions experienced at the clinical trial level serve as a constant reminder of the importance of rigorous safety and toxicity testing. Furthermore the advent of pharmacogenomics and ‘individualized’ approaches to therapy will demand a fresh approach to drug evaluation and healthcare delivery. Clinical Pharmacology provides an essential role in integrating the expertise of all of the specialists and players who are active in meeting such challenges in modern biomedical practice.