{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T15:26:47Z","timestamp":1789658807587,"version":"4.0.1"},"reference-count":30,"publisher":"Oxford University Press (OUP)","issue":"9","license":[{"start":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T00:00:00Z","timestamp":1784073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"CIFRE doctoral fellowship funded by the French National Association of Research and Technology"},{"name":"Agence Nationale de la Recherche under the France 2030 program, reference","award":["22-PESN-0013"],"award-info":[{"award-number":["22-PESN-0013"]}],"id":[{"id":"https:\/\/ror.org\/00rbzpz17","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>The analysis of care trajectories derived from electronic health records and claims data has become increasingly common in biomedical informatics. This has enabled large-scale studies of care processes, yet widely used binary code representations result in high-dimensional, sparse data that fail to capture semantic relationships between medical concepts. Learning dense vector representations (embeddings) has emerged as a promising approach to address these limitations. We aimed to construct and share joint embeddings for the International Classification of Diseases (ICD-10) and the Anatomical Therapeutic Chemical (ATC) classification system, providing reusable semantic representations of diagnoses and treatments from real-world claims data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and Methods<\/jats:title>\n                    <jats:p>Using claims records from 1.5 million patients, we defined code co-occurrences within temporal windows and constructed a Positive Pointwise Mutual Information (PPMI) matrix spanning ICD-10 and ATC codes. Singular Value Decomposition (SVD) was applied to derive a low-dimensional embedding space. Evaluation combined UMAP visualization, nearest-neighbor retrieval, and a code-level classification task based on ICD chapters and ATC classes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The embeddings reflected the hierarchical organization of ICD-10 and ATC and revealed associations across coding systems, including clinically relevant diagnosis-treatment relationships. The classification task achieved mean AUCs of 0.93 for ICD-10 and 0.90 for ATC, indicating strong grouping of semantically related codes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>The embeddings provide a reusable, code-level semantic representation that can support code retrieval, reduce manual code grouping, and be aggregated into patient-level features without training a task-specific model.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>We release the first openly available joint ICD-10\u2013ATC embedding space derived from real-world claims data, providing a reusable resource for biomedical informatics research.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/jamia\/ocag113","type":"journal-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T13:41:33Z","timestamp":1784122893000},"page":"1571-1581","source":"Crossref","is-referenced-by-count":0,"title":["Medical code embeddings from claims-based co-occurrences: a unified semantic space for ICD-10 diagnoses and ATC medications"],"prefix":"10.1093","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5264-5592","authenticated-orcid":false,"given":"Corentin","family":"Faujour","sequence":"first","affiliation":[{"name":"CEMKA , 92340 Bourg-la-Reine,","place":["France"]},{"name":"Universit\u00e9 Paris Cit\u00e9, Inria, Inserm, HeKA , 75015 Paris,","place":["France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"St\u00e9phane","family":"Bou\u00e9e","sequence":"additional","affiliation":[{"name":"CEMKA , 92340 Bourg-la-Reine,","place":["France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Corinne","family":"Emery","sequence":"additional","affiliation":[{"name":"CEMKA , 92340 Bourg-la-Reine,","place":["France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8001-8539","authenticated-orcid":false,"given":"Anne-Sophie","family":"Jannot","sequence":"additional","affiliation":[{"name":"Universit\u00e9 Paris Cit\u00e9, Inria, Inserm, HeKA , 75015 Paris,","place":["France"]},{"name":"French National Rare Disease Registry (BNDMR), Greater Paris University Hospitals (AP-HP) , 75012 Paris,","place":["France"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,7,15]]},"reference":[{"key":"2026091614320665500_ocag113-B1","doi-asserted-by":"publisher","first-page":"136947","DOI":"10.1109\/ACCESS.2020.3011099","article-title":"Secondary use of electronic health record: opportunities and challenges","volume":"8","author":"Shah","year":"2020","journal-title":"IEEE Access"},{"key":"2026091614320665500_ocag113-B2","doi-asserted-by":"publisher","first-page":"103980","DOI":"10.1016\/j.jbi.2021.103980","article-title":"Deep learning for temporal data representation in electronic health records: a systematic review of challenges and methodologies","volume":"126","author":"Xie","year":"2022","journal-title":"J Biomed Inform"},{"key":"2026091614320665500_ocag113-B3","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1186\/s12874-023-02019-y","article-title":"Analytical methods for identifying sequences of utilization in health data: a scoping review","volume":"23","author":"Flothow","year":"2023","journal-title":"BMC Med Res Methodol"},{"key":"2026091614320665500_ocag113-B4","doi-asserted-by":"publisher","first-page":"e00687","DOI":"10.1002\/prp2.687","article-title":"Classification of drug use patterns","volume":"8","author":"Righolt","year":"2020","journal-title":"Pharmacol. Res. Perspect"},{"key":"2026091614320665500_ocag113-B5","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1186\/s12913-020-5030-0","article-title":"Healthcare utilization after a first hospitalization for COPD: a new approach of state sequence analysis based on the \u201c6W\u201d multidimensional model of care trajectories","volume":"20","author":"Vanasse","year":"2020","journal-title":"BMC Health Serv Res"},{"key":"2026091614320665500_ocag113-B6","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1177\/0272989X17731753","article-title":"Uncovering longitudinal healthcare behaviors for millions of Medicaid enrollees: a multistate comparison of pediatric asthma utilization","volume":"38","author":"Hilton","year":"2018","journal-title":"Med Decis Making."},{"key":"2026091614320665500_ocag113-B7","doi-asserted-by":"publisher","first-page":"362","DOI":"10.1007\/s42979-022-01252-4","article-title":"Encoding high-dimensional procedure codes for healthcare fraud detection","volume":"3","author":"Johnson","year":"2022","journal-title":"SN Comput Sci"},{"key":"2026091614320665500_ocag113-B8","doi-asserted-by":"publisher","first-page":"2020:11-17","author":"Lu","DOI":"10.25080\/Majora-342d178e-002"},{"key":"2026091614320665500_ocag113-B9","doi-asserted-by":"publisher","DOI":"10.1142\/9789811215636_0027","article-title":"Clinical concept embeddings learned from massive sources of multimodal medical data","author":"Beam","year":"2019"},{"key":"2026091614320665500_ocag113-B10","first-page":"2493","article-title":"Natural language processing (almost) from scratch","volume":"12","author":"Collobert","year":"2011","journal-title":"J Mach Learn Res"},{"key":"2026091614320665500_ocag113-B11","doi-asserted-by":"publisher","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","article-title":"Representation learning: a review and new perspectives","volume":"35","author":"Bengio","year":"2013","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2026091614320665500_ocag113-B12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00537","article-title":"How well do self-supervised models transfer?","author":"Ericsson","year":"2021"},{"key":"2026091614320665500_ocag113-B13","first-page":"22243","article-title":"Big self-supervised models are strong semi-supervised learners","author":"Chen","year":"2020"},{"key":"2026091614320665500_ocag113-B14","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1186\/s12880-024-01253-0","article-title":"A survey of the impact of self-supervised pretraining for diagnostic tasks in medical X-ray, CT, MRI, and ultrasound","volume":"24","author":"VanBerlo","year":"2024","journal-title":"BMC Med Imaging."},{"key":"2026091614320665500_ocag113-B15","first-page":"386","article-title":"Code2Vec: embedding and clustering medical diagnosis data","author":"Kartchner","year":"2017"},{"key":"2026091614320665500_ocag113-B16","first-page":"1532","article-title":"GloVe: global vectors for word representation","author":"Pennington","year":"2014"},{"key":"2026091614320665500_ocag113-B17","first-page":"1495","article-title":"Multi-layer representation learning for medical concepts","author":"Choi","year":"2016"},{"key":"2026091614320665500_ocag113-B18","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"Mikolov","year":"2013"},{"key":"2026091614320665500_ocag113-B19","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1038\/s41746-021-00519-z","article-title":"Clinical knowledge extraction via sparse embedding regression (KESER) with multi-center large scale electronic health record data","volume":"4","author":"Hong","year":"2021","journal-title":"Npj Digit Med"},{"key":"2026091614320665500_ocag113-B20","doi-asserted-by":"publisher","first-page":"861","DOI":"10.21105\/joss.00861","article-title":"UMAP: uniform manifold approximation and projection","volume":"3","author":"McInnes","year":"2018","journal-title":"JOSS"},{"key":"2026091614320665500_ocag113-B21","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1016\/j.revmed.2014.11.009","article-title":"French health insurance databases: what interest for medical research?","volume":"36","author":"Moulis","year":"2015","journal-title":"Rev Med Interne."},{"key":"2026091614320665500_ocag113-B22","first-page":"2177","article-title":"Neural word embedding as implicit matrix factorization","volume":"27","author":"Levy","year":"2014","journal-title":"Adv Neur Info Proc Syst"},{"key":"2026091614320665500_ocag113-B23","doi-asserted-by":"publisher","first-page":"4282","DOI":"10.1609\/aaai.v30i1.9959","article-title":"Intrinsic and extrinsic evaluations of word embeddings","volume":"30","author":"Zhai","year":"2016","journal-title":"Aaai."},{"key":"2026091614320665500_ocag113-B24","doi-asserted-by":"publisher","author":"Zeng","DOI":"10.1145\/3459930.3469519"},{"key":"2026091614320665500_ocag113-B25","first-page":"6000","article-title":"Attention is all you need","volume":"31","author":"Vaswani","year":"2017","journal-title":"Adv Neur Info Proc Syst"},{"key":"2026091614320665500_ocag113-B26","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput"},{"key":"2026091614320665500_ocag113-B27","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1038\/s41586-025-09529-3","article-title":"Learning the natural history of human disease with generative transformers","volume":"647","author":"Shmatko","year":"2025","journal-title":"Nature."},{"key":"2026091614320665500_ocag113-B28","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1207\/s15516709cog1402_1","article-title":"Finding structure in time","volume":"14","author":"Elman","year":"1990","journal-title":"Cogn Sci"},{"key":"2026091614320665500_ocag113-B29","doi-asserted-by":"publisher","first-page":"3846","DOI":"10.3390\/app12083846","article-title":"Attention map-guided visual explanations for deep neural networks","volume":"12","author":"An","year":"2022","journal-title":"Appl Sci"},{"key":"2026091614320665500_ocag113-B30","first-page":"3319","volume-title":"Proceedings of the 34th International Conference on Machine Learning","author":"Sundararajan","year":"2017"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/advance-article-pdf\/doi\/10.1093\/jamia\/ocag113\/68886413\/ocag113.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/33\/9\/1571\/68886413\/ocag113.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/33\/9\/1571\/68886413\/ocag113.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T18:32:15Z","timestamp":1789583535000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/33\/9\/1571\/8734822"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,15]]},"references-count":30,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,7,15]]},"published-print":{"date-parts":[[2026,9,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocag113","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,9]]},"published":{"date-parts":[[2026,7,15]]}}}