{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T07:58:37Z","timestamp":1786089517150,"version":"3.56.0"},"reference-count":29,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T00:00:00Z","timestamp":1727049600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172028"],"award-info":[{"award-number":["62172028"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772197"],"award-info":[{"award-number":["61772197"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,9,23]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Medication recommendation is a crucial application of artificial intelligence in healthcare. Current methodologies mostly depend on patient-level longitudinal representation, which utilizes the entirety of historical electronic health records for making predictions. However, they tend to overlook a few key elements: (1) The need to analyze the impact of past medications on previous conditions. (2) Similarity in patient visits is more common than similarity in the complete medical histories of patients. (3) It is difficult to accurately represent patient-level longitudinal data due to the varying numbers of visits. To our knowledge, current models face difficulties in dealing with initial patient visits (i.e. in cold-start scenarios) which are common in clinical practice. This paper introduces DrugDoctor, an innovative drug recommendation model crafted to emulate the decision-making mechanics of human doctors. Unlike previous methods, DrugDoctor explores the visit-level relationship between prescriptions and diseases while considering the impact of past prescriptions on the patient\u2019s condition to provide more accurate recommendations. We design a plug-and-play block to effectively capture drug substructure-aware disease information and effectiveness-aware medication information, employing cross-attention and multi-head self-attention mechanisms. Furthermore, DrugDoctor adopts a fundamentally new visit-level training strategy, aligning more closely with the practices of doctors. Extensive experiments conducted on the MIMIC-III and MIMIC-IV datasets demonstrate that DrugDoctor outperforms 10 other state-of-the-art methods in terms of Jaccard, F1-score, and PRAUC. Moreover, DrugDoctor exhibits strong robustness in handling patients with varying numbers of visits and effectively tackles \u201ccold-start\u201d issues in medication combination recommendations.<\/jats:p>","DOI":"10.1093\/bib\/bbae464","type":"journal-article","created":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T13:24:47Z","timestamp":1727097887000},"source":"Crossref","is-referenced-by-count":18,"title":["DrugDoctor: enhancing drug recommendation in cold-start scenario via visit-level representation learning and training"],"prefix":"10.1093","volume":"25","author":[{"given":"Yabin","family":"Kuang","sequence":"first","affiliation":[{"name":"College of Information Science and Engineering, Hunan Normal University , 36 Lushan Road, Yuelu District, Changsha 410081, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minzhu","family":"Xie","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Hunan Normal University , 36 Lushan Road, Yuelu District, Changsha 410081, China"},{"name":"Key Laboratory of Computing and Stochastic Mathematics (Ministry of Education) , Changsha 410081, China"},{"name":"College of Mathematics and Statistics, Hunan Normal University , 36 Lushan Road, Yuelu District, Changsha 410081, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,9,23]]},"reference":[{"key":"2024092313243655300_ref1","doi-asserted-by":"publisher","first-page":"812","DOI":"10.1093\/bib\/bbaa418","article-title":"Health informatics and EHR to support clinical research in the COVID-19 pandemic: An overview","volume":"22","author":"Dagliati","year":"2021","journal-title":"Brief Bioinform"},{"key":"2024092313243655300_ref2","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1038\/s41390-022-02343-x","article-title":"Utilizing big data from electronic health records in pediatric clinical care","volume":"93","author":"Macias","year":"2023","journal-title":"Pediatr Res"},{"key":"2024092313243655300_ref3","doi-asserted-by":"publisher","first-page":"1240","DOI":"10.1038\/s41591-022-01811-5","article-title":"Machine learning model to predict mental health crises from electronic health records","volume":"28","author":"Garriga","year":"2022","journal-title":"Nat Med"},{"key":"2024092313243655300_ref4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3488668","article-title":"Personalizing medication recommendation with a graph-based approach","volume":"40","author":"Bhoi","year":"2021","journal-title":"ACM Trans Inf Syst"},{"key":"2024092313243655300_ref5","article-title":"Self-supervised adversarial distribution regularization for medication recommendation","author":"Wang","journal-title":"proceedings of the thirtieth international joint conference on artificial intelligence, IJCAI-21"},{"key":"2024092313243655300_ref6","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1145\/3394486.3403055","article-title":"Attention and memory-augmented networks for dual-view sequential learning","volume-title":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","author":"He","year":"2020"},{"key":"2024092313243655300_ref7","doi-asserted-by":"crossref","first-page":"3970","DOI":"10.1145\/3534678.3539089","article-title":"4sdrug: Symptom-based set-to-set small and safe drug recommendation","volume-title":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","author":"Tan","year":"2022"},{"key":"2024092313243655300_ref8","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.ymeth.2023.06.005","article-title":"A patient information mining network for drug recommendation","volume":"216","author":"Li","year":"2023","journal-title":"Methods"},{"key":"2024092313243655300_ref9","doi-asserted-by":"crossref","first-page":"101939","DOI":"10.1016\/j.inffus.2023.101939","article-title":"Megacare: Knowledge-guided multi-view hypergraph predictive framework for healthcare","volume":"100","author":"Jialun","year":"2023","journal-title":"Inf Fusion"},{"key":"2024092313243655300_ref10","doi-asserted-by":"publisher","first-page":"480","DOI":"10.1080\/15374416.2015.1015133","article-title":"A pilot smart for developing an adaptive treatment strategy for adolescent depression","volume":"45","author":"Gunlicks-Stoessel","year":"2016","journal-title":"J Clin Child Adolesc Psychol"},{"key":"2024092313243655300_ref11","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1017\/S1471068416000429","article-title":"A physician advisory system for chronic heart failure management based on knowledge patterns","volume":"16","author":"Chen","year":"2016","journal-title":"Theory Pract Log Program"},{"key":"2024092313243655300_ref12","doi-asserted-by":"crossref","first-page":"1315","DOI":"10.1145\/3097983.3098109","article-title":"LEAP: Learning to prescribe effective and safe treatment combinations for multimorbidity","volume-title":"Proceedings of the 23rd ACM SIGKDD international conference on knowledge Discovery and data Mining","author":"Zhang","year":"2017"},{"key":"2024092313243655300_ref13","doi-asserted-by":"publisher","first-page":"1126","DOI":"10.1609\/aaai.v33i01.33011126","article-title":"GAMENet: Graph augmented memory networks for recommending medication combination","volume":"33","author":"Shang","year":"2019","journal-title":"In proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2024092313243655300_ref14","first-page":"3735","article-title":"SafeDrug: Dual molecular graph encoders for recommending effective and safe drug combinations","volume-title":"Proceedings of the thirtieth international joint conference on artificial intelligence, IJCAI-21","author":"Yang"},{"key":"2024092313243655300_ref15","doi-asserted-by":"crossref","first-page":"4075","DOI":"10.1145\/3543507.3583872","article-title":"MoleRec: Combinatorial drug recommendation with substructure-aware molecular representation learning","volume-title":"Proceedings of the ACM Web Conference 2023, WWW \u201823","author":"Yang","year":"2023"},{"key":"2024092313243655300_ref16","first-page":"935","article-title":"Conditional generation net for medication recommendation","volume":"2022","author":"Rui","year":"2022","journal-title":"In Proceedings of the ACM Web Conference"},{"key":"2024092313243655300_ref17","doi-asserted-by":"publisher","first-page":"6018","DOI":"10.1109\/JBHI.2023.3320139","article-title":"SHAPE: A sample-adaptive hierarchical prediction network for medication recommendation","volume":"27","author":"Liu","year":"2023","journal-title":"IEEE J Biomed Health Inform"},{"key":"2024092313243655300_ref18","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"key":"2024092313243655300_ref19","doi-asserted-by":"crossref","first-page":"2518","DOI":"10.1093\/bioinformatics\/btn479","article-title":"Chemical substructures that enrich for biological activity","volume":"24","author":"Klekota","year":"2008","journal-title":"Bioinformatics"},{"key":"2024092313243655300_ref20","doi-asserted-by":"publisher","first-page":"1503","DOI":"10.1002\/cmdc.200800178","article-title":"On the art of compiling and using\u2019drug-like\u2019chemical fragment spaces. ChemMedChem: Chemistry enabling","volume":"3","author":"Degen","year":"2008","journal-title":"Drug Discovery"},{"key":"2024092313243655300_ref21","article-title":"RDKit documentation","volume-title":"Release","author":"Landrum"},{"key":"2024092313243655300_ref22","article-title":"How powerful are graph neural networks?","volume-title":"Proceedings of the Seventh International Conference on Learning Representations, ICLR","author":"Xu"},{"key":"2024092313243655300_ref23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2016.35","article-title":"MIMIC-III, a freely accessible critical care database","volume":"3","author":"Johnson","year":"2016","journal-title":"Sci data"},{"key":"2024092313243655300_ref24","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01899-x","article-title":"MIMIC-IV, a freely accessible electronic health record dataset","volume":"10","author":"Johnson","year":"2023","journal-title":"Scientific data"},{"key":"2024092313243655300_ref25","article-title":"Classifier chains for multi-label classification","volume-title":"Machine Learning","author":"Read"},{"key":"2024092313243655300_ref26","doi-asserted-by":"crossref","first-page":"1637","DOI":"10.1145\/3219819.3219981","article-title":"Dual memory neural computer for asynchronous two-view sequential learning","volume-title":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","author":"Le","year":"2018"},{"key":"2024092313243655300_ref27","first-page":"3728","article-title":"Change matters: Medication change prediction with recurrent residual networks","volume-title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21","author":"Yang"},{"key":"2024092313243655300_ref28","doi-asserted-by":"publisher","first-page":"1668","DOI":"10.1109\/JBHI.2023.3346210","article-title":"EHR-HGCN: An enhanced hybrid approach for text classification using heterogeneous graph convolutional networks in electronic health records","volume":"28","author":"Wang","year":"2023","journal-title":"IEEE J Biomed Health Inform"},{"key":"2024092313243655300_ref29","first-page":"303","article-title":"Deep learning for medication recommendation: A systematic survey. Data","volume":"5","author":"Ali","year":"2023","journal-title":"Dermatol Int"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/25\/6\/bbae464\/59242513\/bbae464.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/25\/6\/bbae464\/59242513\/bbae464.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T13:24:55Z","timestamp":1727097895000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbae464\/7765457"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,23]]},"references-count":29,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,9,23]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbae464","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,11]]},"published":{"date-parts":[[2024,9,23]]},"article-number":"bbae464"}}