
浏览全部资源
扫码关注微信
1.西安交通大学第一附属医院药学部,西安 710061
2.西北妇女儿童医院药剂科,西安 710061
主管药师。研究方向:医院药学、药学信息化。电话:029-85324174。E-mail:wangfeng7927@126.com
主任药师,博士。研究方向:医院药学、临床药学。电话:029-85323508。E-mail:donghy@mail.xjtu.edu.cn
收稿:2026-05-19,
修回:2026-09-20,
录用:2026-09-24,
纸质出版:2026-10-15
移动端阅览
王丰,王琦,范园园,等.基于多模态相似度模型的中文药品名称潜在混淆风险筛查与显示名优化 [J].中国药房,2026,37(19):2570-2576.
WANG Feng,WANG Qi,FAN Yuanyuan,et al.Potential confusion risk screening and display-name optimization for Chinese drug names based on a multimodal similarity model[J].ZHONGGUO YAOFANG,2026,37(19):2570-2576.
王丰,王琦,范园园,等.基于多模态相似度模型的中文药品名称潜在混淆风险筛查与显示名优化 [J].中国药房,2026,37(19):2570-2576. DOI: 10.6039/j.issn.1001-0408.2026.19.15.
WANG Feng,WANG Qi,FAN Yuanyuan,et al.Potential confusion risk screening and display-name optimization for Chinese drug names based on a multimodal similarity model[J].ZHONGGUO YAOFANG,2026,37(19):2570-2576. DOI: 10.6039/j.issn.1001-0408.2026.19.15.
目的
2
构建中文药品名称多模态相似度模型并设计优化显示名,比较同一药品目录在不同场景中显示名的潜在混淆风险,为药品显示名的管理提供量化依据。
方法
2
从某三级甲等医院药品字典提取1 221个药品条目,组成744 810对药对;基于院内现用显示名(场景一)与标准显示名(场景二)候选混淆药对的混淆特征归纳出“五项规则”,生成优化显示名(场景三)。构建融合拼音、字形、字符序列与渲染视觉特征的多模态相似度模型,以同一阈值(总相似度
S
total
≥0.70)筛选候选混淆药对,开展混淆风险分级与转移、混淆特征标注、混淆网络聚类及残余簇分析,并通过显示形态指标与规则消融考察优化显示名的命名机制,通过相似度阈值与模型融合权重敏感性分析评价3种场景比较结果的稳健性。
结果
2
3种场景候选混淆药对分别为156、269、83对(高风险及以上者分别为109、215、64对);与场景一相比,场景三候选混淆药对减少46.8%,高风险及以上者减少41.3%;显示形态分析显示,场景三的平均墨量密度最低(0.057 3)、平均结构槽位数量最多(2.99个);规则消融分析显示,禁用厂家特征缩写提示规则后,候选混淆药对数量增幅最大(增加74对),而单独禁用结构化命名则净减少9对。残余簇主要涉及同成分不同规格或亚型药品,以及同厂家、名称主干相似的系列品种。在0.60~0.80、步长0.025的阈值设置及11种不同权重配置(含基准值)下,候选混淆药对数量均保持“场景三<场景一<场景二”的排序。
结论
2
多模态相似度模型可用于中文药品显示名潜在混淆的量化筛查,场景间的候选混淆药对数量排序在所设置参数范围内能保持稳定。基于“五项规则”的优化显示名能减少该院目录中的候选混淆药对、高风险及以上候选混淆药对的数量,但其对实际辨识行为和临床用药安全的影响仍需进一步验证。
OBJECTIVE
2
To construct a multimodal similarity model for Chinese drug names and design optimized display names,compare the potential confusion risk of display names of the same drug catalogue in different scenarios,so as to provide a quantitative basis for the management of drug display names.
METHODS
2
A total of 1 221 drug entries were extracted from the drug dictionary of a tertiary grade A hospital,forming 744 810 drug pairs. “Five rules” were summarized based on the confusion characteristics of candidate confusable drug pairs under the currently used in-hospital display names (Scenario 1) and standard display names (Scenario 2),to generate optimized display names (Scenario 3). A multimodal similarity model integrating Pinyin,glyph,character sequence and rendered visual features was constructed. The same threshold (total similarity
S
total
≥0.70) was adopted to screen candidate confusable drug pairs. Confusion risk grading and transition,confusion characteristic labeling,confusion network clustering and residual cluster analysis were carried out. The naming mechanism of optimized display names was investigated through display morphology indicators and rule ablation,and the robustness of the comparison results among the three scenarios was evaluated through similarity threshold and fusion weight sensitivity analysis.
RESULTS
2
The numbers of candidate confusable drug pairs in the three scenarios were 156,269 and 83 respectively,among which the number of pairs at high risk and above was 109, 215 and 64 respectively. Compared with Scenario 1,Scenario 3 reduced the number of candidate confusable drug pairs by 46.8%,and the number of those at high risk or above decreased by 41.3%. Display morphology analysis showed that Scenario 3 had the lowest average ink density (0.057 3) and the largest average number of structural slots (2.99). Rule ablation analysis showed that after disabling the rule of manufacturer characteristic abbreviation prompts,the number of candidate confusable drug pairs increased the most (+74 pairs),while disabling structured naming alone resulted in a net decrease of 9 pairs. The residual clusters mainly involved drugs with the same active ingredient but different specifications or subtypes,as well as series products from the same manufacturer with similar main name stems. Under the threshold setting of 0.60 to 0.80 with a step size of 0.025 and 11 different weight configurations (including the baseline value),the number of candidate confusable drug pairs always maintained the ranking of Scenario 3<Scenario 1<Scenario 2.
CONCLUSIONS
2
The multimodal similarity model can be used for quantitative screening of potential confusion of Chinese drug display names,and the ranking of the number of candidate confusable drug pairs among scenarios remains stable within the set parameter range. The optimized display names based on the “five rules” can reduce the number of candidate confusable drug pairs, and the number of those at high risk or above in the hospital’s drug catalogue,but their impact on actual identification behavior and clinical medication safety still needs further verification.
Donaldson L J , Kelley E T , Dhingra-Kumar N , et al . Medication without harm:WHO’s third global patient safety challenge [J ] . Lancet , 2017 , 389 ( 10080 ): 1680 - 1681 .
陈杨 , 淡重辉 , 何瑶 , 等 . 基于莱文斯坦距离的易混淆药品目录自动生成算法及软件实现 [J ] . 中国药房 , 2024 , 35 ( 15 ): 1899 - 1904 .
Simas da Rocha B , Garcia Moraes C , Miyake Okumura L , et al . Interventions to reduce problems related to the readability and comprehensibility of drug packages and labels:a systematic review [J ] . J Patient Saf , 2021 , 17 ( 8 ): e1494 - e1506 .
Bryan R , Aronson J K , Williams A J , et al . A systematic literature review of LASA error interventions [J ] . Br J Clin Pharmacol , 2021 , 87 ( 2 ): 336 - 351 .
Chen C Y , Chen Y L , Scholl J , et al . Ability of machine-learning based clinical decision support system to reduce alert fatigue,wrong-drug errors,and alert users about look alike,sound alike medication [J ] . Comput Methods Programs Biomed , 2024 , 243 : 107869 .
Larmené-Beld K H M , Alting E K , Taxis K . A systematic literature review on strategies to avoid look-alike errors of labels [J ] . Eur J Clin Pharmacol , 2018 , 74 ( 8 ): 985 - 993 .
周怡 , 尤启冬 . 中国化学药品通用名称的构建及监管 [J ] . 药学与临床研究 , 2025 , 33 ( 1 ): 1 - 3 .
陈家润 , 沈波 , 沈小莉 , 等 . 广东省医疗机构制剂化学药品通用名称命名存在问题及对策 [J ] . 中国药事 , 2022 , 36 ( 10 ): 1117 - 1121 .
Neelakantan M , Sharma P , Kulkarni A . Look-alike,sound-alike (LASA) drugs in India [J ] . Lancet Reg Health Southeast Asia , 2024 , 26 : 100425 .
Lv L S , Yao Y , Zhang M W , et al . Impact of implementing the lean management on internal errors at an outpatient hospital pharmacy in China [J ] . Patient Prefer Adherence , 2025 , 19 : 139 - 147 .
Ting H W , Chung S L , Chen C F , et al . A drug identification model developed using deep learning technologies:experience of a medical center in Taiwan [J ] . BMC Health Serv Res , 2020 , 20 ( 1 ): 312 .
Rash-Foanio C , Galanter W , Bryson M , et al . Automated detection of look-alike/sound-alike medication errors [J ] . Am J Health Syst Pharm , 2017 , 74 ( 7 ): 521 - 527 .
Lambert B L , Lin S J , Chang K Y , et al . Similarity as a risk factor in drug-name confusion errors:the look-alike(orthographic)and sound-alike(phonetic)model [J ] . Med Care , 1999 , 37 ( 12 ): 1214 - 1225 .
Kondrak G , Dorr B . Automatic identification of confusable drug names [J ] . Artif Intell Med , 2006 , 36 ( 1 ): 29 - 42 .
Emmerton L , Curtain C , Swaminathan G , et al . Development and exploratory analysis of software to detect look-alike,sound-alike medicine names [J ] . Int J Med Inform , 2020 , 137 : 104119 .
Levenshtein V I . Binary codes capable of correcting deletions,insertions,and reversals [J ] . Sov Phys Dokl , 1966 , 10 ( 8 ): 707 - 710 .
Jaccard P . Étude comparative de la distribution florale dans une portion des Alpes et du Jura [J ] . Bull Soc Vau- doise Sci Nat , 1901 , 37 : 547 - 579 .
Zobel J , Dart P . Phonetic string matching:lessons from information retrieval [C ] //Frei H P,Harman D,Schäuble P,et al. Proceedings of the 19th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval . New York : ACM , 1996 : 166 - 172 .
Qiao Z H , Zhou H Q , Liu Y M , et al . DISC:plug-and-play decoding intervention with similarity of characters for Chinese spelling check [C ] //Che W X,Nabende J,Shutova E,et al. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics : Volume 1 :Long Papers.Vienna: Association for Computational Linguistics ,2025: 28312 - 28324 .
Murdock B B . The serial position effect of free recall [J ] . J Exp Psychol , 1962 , 64 ( 5 ): 482 - 488 .
Rezatofighi H , Tsoi N , Gwak J Y , et al . Generalized intersection over union:a metric and a loss for bounding box regression [C ] // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR) . Piscataway : IEEE , 2019 : 658 - 666 .
US Food and Drug Administration . Best practices in developing proprietary names for human prescription drug products:guidance for industry [R ] . Silver Spring(MD):US Department of Health and Human Services,Food and Drug Administration , 2020 .
王琦 , 曾攀科 , 宋昊昕 , 等 . 基于数智驱动的中药房调剂取药流程优化研究 [J ] . 中国药房 , 2026 , 37 ( 5 ): 660 - 664 .
王琦 , 曾攀科 , 冯靖婷 , 等 . 基于数智追溯技术重构门诊药房药品库间转移验收流程 [J ] . 医药导报 , 2026 , 45 ( 2 ): 325 - 330 .
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621