{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T06:00:41Z","timestamp":1790834441318,"version":"4.1.0"},"reference-count":38,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Large language models (LLMs) have emerged as a novel technical solution for intelligent prescription review. Nevertheless, comparative analyses of their performance remain limited. This study comprehensively evaluates five mainstream LLMs (ChatGPT, DeepSeek, Kimi, Qwen and Doubao) in prescription review, aiming to furnish data-based references for model selection, optimization and clinical deployment of intelligent prescription review systems.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      This study employed a cross-sectional comparative design. The evaluation dataset was derived from the prescription review question bank of the Chinese Pharmacist Skills Competition. In total, 100 prescriptions from 10 clinical specialties were randomly sampled, encompassing 270 standardized medication assessment items. Official standard answers served as the gold standard. Quantitative comparisons were performed on overall detection rate, question type identification and adaptability across clinical specialties. Prescription-level repeated-measures analysis of variance (ANOVA) and Holm-adjusted pairwise paired\n                      <jats:italic>t<\/jats:italic>\n                      -tests were used to examine inter-model statistical differences.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The five models yielded item-level prescription detection rate ranging from 45.19% to 70.37% across 270 standardized medication assessment items. Their performance ranked from highest to lowest as follows: Kimi, DeepSeek, Qwen, Doubao and ChatGPT. Overall, the four Chinese domestic models included in this study outperformed the single tested international model (ChatGPT) in this China-focused prescription review task. Repeated-measures ANOVA confirmed statistically significant within-prescription differences in overall performance (F\u2009=\u200922.46,\n                      <jats:italic>P<\/jats:italic>\n                      \u2009&amp;lt;\u20090.001). While all models performed well at identifying inappropriate dosage forms and administration routes, they were less effective in detecting issues involving absent allergy test documentation and flawed result interpretation. Prescription reviews for the respiratory department yielded the best results, whereas detection rate was substantially lower for specialized clinical specialties such as oncology, pediatrics and pain management. Even the best-performing model presented a high false-negative rate and cannot yet satisfy the strict reliability criteria for clinical application in prescription review.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Performance varied markedly across the five LLMs in prescription review. Although these models can effectively identify routine and straightforward medication issues, they demonstrate prominent deficiencies in assessing complex prescriptions from specialist clinical specialties and detecting hidden medication risks. Currently, LLMs are only suitable for preliminary auxiliary screening and cannot substitute dedicated prescription review software or manual pharmacist evaluation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1939786","type":"journal-article","created":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T05:41:09Z","timestamp":1790833269000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Performance of large language models in prescription review: a comparative study"],"prefix":"10.3389","volume":"13","author":[{"given":"Can","family":"Huang","sequence":"first","affiliation":[{"name":"Beijing Youan Hospital, Capital Medical University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanfang","family":"Sun","sequence":"additional","affiliation":[{"name":"Beijing Youan Hospital, Capital Medical University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing Youan Hospital, Capital Medical University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,10,1]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"849","DOI":"10.1093\/heapol\/czt067","article-title":"The impact of clinical pharmacy services in China on the quality use of medicines: a systematic review in context of China\u2019s current healthcare reform","volume":"29","author":"Penm","year":"2014","journal-title":"Health Policy Plan"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1383","DOI":"10.1016\/j.sapharm.2019.01.009","article-title":"A systematic review of pharmacist-led medicines review services in New Zealand \u2013 is there equity for M\u0101ori older adults?","volume":"15","author":"Hikaka","year":"2019","journal-title":"Res Soc Adm Pharm"},{"key":"B3","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1186\/s12875-016-0577-x","article-title":"Effectiveness of medication review: a systematic review and meta-analysis of randomized controlled trials","volume":"18","author":"Huiskes","year":"2017","journal-title":"BMC Fam Pract"},{"key":"B4","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1186\/s40545-022-00461-9","article-title":"Assessment of prescribing errors reported by community pharmacy professionals","volume":"15","author":"Simegn","year":"2022","journal-title":"J of Pharm Policy and Pract"},{"key":"B5","doi-asserted-by":"publisher","first-page":"439","DOI":"10.3389\/fphar.2019.00439","article-title":"How to prevent or reduce prescribing errors: an evidence brief for policy","volume":"10","author":"de Ara\u00fajo","year":"2019","journal-title":"Front Pharmacol"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1579","DOI":"10.1016\/j.sapharm.2020.12.008","article-title":"Evaluating the impact of a pharmacist-led prescribing feedback intervention on prescribing errors in a hospital setting","volume":"17","author":"Lloyd","year":"2021","journal-title":"Res Soc Adm Pharm"},{"key":"B7","doi-asserted-by":"publisher","first-page":"768","DOI":"10.1177\/0091270003254794","article-title":"Reducing medication errors and increasing patient safety: case studies in clinical pharmacology","volume":"43","author":"Benjamin","year":"2003","journal-title":"J Clin Pharma"},{"key":"B8","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1186\/s12913-025-12901-8","article-title":"Establishment, maintenance and application effect analysis of the prescription pre-review system in a tertiary hospital in China","volume":"25","author":"Zhou","year":"2025","journal-title":"BMC Health Serv Res"},{"key":"B9","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1016\/j.sapharm.2025.11.009","article-title":"Identifying outcomes for evaluating the impact of pharmacist prescribing: a rapid overview of reviews","volume":"22","author":"Ali","year":"2026","journal-title":"Res Soc Adm Pharm"},{"key":"B10","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1001\/jama.2024.21700","article-title":"Testing and evaluation of health care applications of large language models: a systematic review","volume":"333","author":"Bedi","year":"2025","journal-title":"JAMA"},{"key":"B11","doi-asserted-by":"publisher","first-page":"943","DOI":"10.1038\/s41591-024-03423-7","article-title":"Toward expert-level medical question answering with large language models","volume":"31","author":"Singhal","year":"2025","journal-title":"Nat Med"},{"key":"B12","doi-asserted-by":"publisher","first-page":"616","DOI":"10.1002\/jrsm.1715","article-title":"Can large language models replace humans in systematic reviews? Evaluating GPT -4\u2019s efficacy in screening and extracting data from peer-reviewed and grey literature in multiple languages","volume":"15","author":"Khraisha","year":"2024","journal-title":"Res Synth Methods"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1134","DOI":"10.1038\/s41591-024-02855-5","article-title":"Adapted large language models can outperform medical experts in clinical text summarization","volume":"30","author":"Van Veen","year":"2024","journal-title":"Nat Med"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1233","DOI":"10.1038\/s41591-024-03456-y","article-title":"GPT-4 assistance for improvement of physician performance on patient care tasks: a randomized controlled trial","volume":"31","author":"Goh","year":"2025","journal-title":"Nat Med"},{"key":"B15","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1038\/s41746-025-01650-x","article-title":"Synthetic medical education in dermatology leveraging generative artificial intelligence","volume":"8","author":"Rao","year":"2025","journal-title":"npj Digit Med"},{"key":"B16","doi-asserted-by":"publisher","first-page":"973","DOI":"10.1142\/S0192415X25500375","article-title":"Application of large language models in traditional Chinese medicine: a state-of-the-art review","volume":"53","author":"Shataer","year":"2025","journal-title":"Am J Chin Med"},{"key":"B17","doi-asserted-by":"publisher","first-page":"e69929","DOI":"10.2196\/69929","article-title":"Performance of ChatGPT-4o and four open-source large language models in generating diagnoses based on China\u2019s rare disease catalog: comparative study","volume":"27","author":"Zhong","year":"2025","journal-title":"J Med Internet Res"},{"key":"B18","doi-asserted-by":"publisher","first-page":"2550","DOI":"10.1038\/s41591-025-03726-3","article-title":"Comparative benchmarking of the DeepSeek large language model on medical tasks and clinical reasoning","volume":"31","author":"Tordjman","year":"2025","journal-title":"Nat Med"},{"key":"B19","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1038\/s41591-024-03328-5","article-title":"An evaluation framework for clinical use of large language models in patient interaction tasks","volume":"31","author":"Johri","year":"2025","journal-title":"Nat Med"},{"key":"B20","doi-asserted-by":"publisher","first-page":"e0345098","DOI":"10.1371\/journal.pone.0345098","article-title":"Evaluation of the effect of refined management of prospective prescription review rules for antimicrobial agents in an outpatient setting of a county-level hospital in China","volume":"21","author":"Pan","year":"2026","journal-title":"PLoS One"},{"key":"B21","doi-asserted-by":"publisher","first-page":"106092","DOI":"10.1016\/j.ijmedinf.2025.106092","article-title":"Clinical effectiveness of a cloud-based dual-layer prescription review system: provincial integration across internet and outpatient care","volume":"205","author":"Shi","year":"2026","journal-title":"Int J Med Inf"},{"key":"B22","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1016\/j.puhe.2018.06.009","article-title":"Toward safer prescribing: evaluation of a prospective drug utilization review system on inappropriate prescriptions, prescribing patterns, and adverse drug events and related health expenditure in South Korea","volume":"163","author":"Kim","year":"2018","journal-title":"Public Health"},{"key":"B23","doi-asserted-by":"publisher","first-page":"e100683","DOI":"10.1136\/bmjhci-2022-100683","article-title":"Clinical decision support systems to improve drug prescription and therapy optimisation in clinical practice: a scoping review","volume":"30","author":"Armando","year":"2023","journal-title":"BMJ Health Care Inform"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1276","DOI":"10.1186\/s12913-025-13377-2","article-title":"Information pharmacists assist in the construction of GLP-1RA prescription review rules in a tertiary hospital in China","volume":"25","author":"Zhou","year":"2025","journal-title":"BMC Health Serv Res"},{"key":"B25","doi-asserted-by":"publisher","first-page":"106042","DOI":"10.1016\/j.puhe.2025.106042","article-title":"Evaluation of large language models in the clinical management of multiple chronic conditions: a comparative study of DeepSeek-R1 and ChatGPT-o1","volume":"249","author":"Zeng","year":"2025","journal-title":"Public Health"},{"key":"B26","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1038\/s41746-023-00896-7","article-title":"Evaluating large language models on medical evidence summarization","volume":"6","author":"Tang","year":"2023","journal-title":"npj Digit Med"},{"key":"B27","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1192\/bjp.2023.136","article-title":"Artificial intelligence and increasing misinformation","volume":"224","author":"Monteith","year":"2024","journal-title":"Br J Psychiatry"},{"key":"B28","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1186\/s12875-018-0808-4","article-title":"The impact of a prescription review and prescriber feedback system on prescribing practices in primary care clinics: a cluster randomised trial","volume":"19","author":"Lim","year":"2018","journal-title":"BMC Fam Pract"},{"key":"B29","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1093\/jamia\/ocaf174","article-title":"Compliance and factuality of large language models for clinical research document generation","volume":"33","author":"Wang","year":"2026","journal-title":"J Am Med Inform Assoc"},{"key":"B30","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1038\/s41746-026-02382-2","article-title":"Human\u2013large language model collaboration in clinical medicine: a systematic review and meta-analysis","volume":"9","author":"Wang","year":"2026","journal-title":"npj Digit Med"},{"key":"B31","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1186\/s12911-023-02124-4","article-title":"Factors influencing the implementation of decision support systems for antibiotic prescription in hospitals: a systematic review","volume":"23","author":"Tokg\u00f6z","year":"2023","journal-title":"BMC Med Inform Decis Mak"},{"key":"B32","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.ijmedinf.2018.11.004","article-title":"Effects of chemotherapy prescription clinical decision-support systems on the chemotherapy process: a systematic review","volume":"122","author":"Rahimi","year":"2019","journal-title":"Int J Med Inf"},{"key":"B33","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1186\/s12929-025-01131-z","article-title":"Impact of large language model (ChatGPT) in healthcare: an umbrella review and evidence synthesis","volume":"32","author":"Iqbal","year":"2025","journal-title":"J Biomed Sci"},{"key":"B34","doi-asserted-by":"publisher","first-page":"860","DOI":"10.1093\/cid\/ciad633","article-title":"Black box warning: large language models and the future of infectious diseases consultation","volume":"78","author":"Schwartz","year":"2024","journal-title":"Clin Infect Dis"},{"key":"B35","doi-asserted-by":"publisher","first-page":"101176","DOI":"10.1016\/j.patter.2025.101176","article-title":"Attention heads of large language models","volume":"6","author":"Zheng","year":"2025","journal-title":"Patterns"},{"key":"B36","doi-asserted-by":"publisher","first-page":"e2440969","DOI":"10.1001\/jamanetworkopen.2024.40969","article-title":"Large language model influence on diagnostic reasoning: a randomized clinical trial","volume":"7","author":"Goh","year":"2024","journal-title":"JAMA Netw Open"},{"key":"B37","doi-asserted-by":"publisher","first-page":"1706056","DOI":"10.3389\/fphar.2025.1706056","article-title":"Implementation and impact analysis of a clinical pharmacy ambulatory: a two-year experience","volume":"16","author":"Mengato","year":"2025","journal-title":"Front Pharmacol"},{"key":"B38","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1093\/ijpp\/riaf115","article-title":"Implementation of clinical pharmacy services in an adult medical intensive care unit at a French university hospital and the ICU team's perception of the pharmacist's role","volume":"34","author":"Plesa","year":"2026","journal-title":"Int J Pharm Pract"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1939786\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T05:41:10Z","timestamp":1790833270000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1939786\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,1]]},"references-count":38,"alternative-id":["10.3389\/fmed.2026.1939786"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1939786","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,1]]},"article-number":"1939786"}}