{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T21:39:49Z","timestamp":1778362789290,"version":"3.51.4"},"reference-count":80,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T00:00:00Z","timestamp":1770336000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T00:00:00Z","timestamp":1773360000000},"content-version":"vor","delay-in-days":35,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/100006108","name":"National Center for Advancing Translational Sciences","doi-asserted-by":"publisher","award":["U01TR002623"],"award-info":[{"award-number":["U01TR002623"]}],"id":[{"id":"10.13039\/100006108","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000050","name":"National Heart, Lung, and Blood Institute","doi-asserted-by":"publisher","award":["R01HL170151"],"award-info":[{"award-number":["R01HL170151"]}],"id":[{"id":"10.13039\/100000050","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000092","name":"U.S. National Library of Medicine","doi-asserted-by":"publisher","award":["R01LM013614"],"award-info":[{"award-number":["R01LM013614"]}],"id":[{"id":"10.13039\/100000092","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"DOI":"10.1038\/s41746-026-02406-x","type":"journal-article","created":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T05:05:36Z","timestamp":1770354336000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A weakly supervised transformer for rare disease diagnosis and subphenotyping from EHRs with pulmonary case studies"],"prefix":"10.1038","volume":"9","author":[{"given":"Kimberly F.","family":"Greco","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zongxin","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengyan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Tong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sara","family":"Morini Sweet","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alon","family":"Geva","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kenneth D.","family":"Mandl","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Benjamin A.","family":"Raby","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianxi","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,6]]},"reference":[{"key":"2406_CR1","doi-asserted-by":"crossref","unstructured":"Health, T. L. G. The landscape for rare diseases in 2024. Lancet Glob. Health 12, e341 (2024).","DOI":"10.1016\/S2214-109X(24)00056-1"},{"key":"2406_CR2","doi-asserted-by":"publisher","DOI":"10.1186\/s13023-024-03322-7","volume":"19","author":"CM Wang","year":"2024","unstructured":"Wang, C. M. et al. Operational description of rare diseases: a reference to improve the recognition and visibility of rare diseases. Orphanet J. Rare Dis. 19, 334 (2024).","journal-title":"Orphanet J. Rare Dis."},{"key":"2406_CR3","doi-asserted-by":"publisher","DOI":"10.1186\/s13073-022-01026-w","volume":"14","author":"S Marwaha","year":"2022","unstructured":"Marwaha, S., Knowles, J. W. & Ashley, E. A. A guide for the diagnosis of rare and undiagnosed disease: beyond the exome. Genome Med. 14, 23 (2022).","journal-title":"Genome Med."},{"key":"2406_CR4","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1007\/s40290-020-00332-1","volume":"34","author":"V Boulanger","year":"2020","unstructured":"Boulanger, V., Schlemmer, M., Rossov, S., Seebald, A. & Gavin, P. Establishing patient registries for rare diseases: rationale and challenges. Pharm. Med. 34, 185\u2013190 (2020).","journal-title":"Pharm. Med."},{"key":"2406_CR5","doi-asserted-by":"publisher","first-page":"119811","DOI":"10.1016\/j.cca.2024.119811","volume":"561","author":"CM Mak","year":"2024","unstructured":"Mak, C. M. et al. Computer-assisted patient identification tool in inborn errors of metabolism\u2013potential for rare disease patient registry and big data analysis. Clin. Chim. Acta 561, 119811 (2024).","journal-title":"Clin. Chim. Acta"},{"key":"2406_CR6","doi-asserted-by":"publisher","first-page":"472","DOI":"10.1093\/jamiaopen\/ooaa030","volume":"3","author":"YR Rubinstein","year":"2020","unstructured":"Rubinstein, Y. R. et al. The case for open science: rare diseases. JAMIA Open 3, 472\u2013486 (2020).","journal-title":"JAMIA Open"},{"key":"2406_CR7","doi-asserted-by":"publisher","DOI":"10.1186\/s13023-022-02358-x","volume":"17","author":"A Bauskis","year":"2022","unstructured":"Bauskis, A., Strange, C., Molster, C. & Fisher, C. The diagnostic odyssey: insights from parents of children living with an undiagnosed condition. Orphanet J. Rare Dis. 17, 233 (2022).","journal-title":"Orphanet J. Rare Dis."},{"key":"2406_CR8","doi-asserted-by":"publisher","first-page":"1309","DOI":"10.1016\/j.chest.2017.12.018","volume":"153","author":"JK Stoller","year":"2018","unstructured":"Stoller, J. K. The challenge of rare diseases. Chest 153, 1309\u20131314 (2018).","journal-title":"Chest"},{"key":"2406_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13023-021-01794-5","volume":"16","author":"AG Sreih","year":"2021","unstructured":"Sreih, A. G. et al. Diagnostic delays in vasculitis and factors associated with time to diagnosis. Orphanet J. Rare Dis. 16, 1\u20138 (2021).","journal-title":"Orphanet J. Rare Dis."},{"key":"2406_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13023-020-01574-7","volume":"15","author":"E Gunne","year":"2020","unstructured":"Gunne, E. et al. A retrospective review of the contribution of rare diseases to paediatric mortality in ireland. Orphanet J. Rare Dis. 15, 1\u20138 (2020).","journal-title":"Orphanet J. Rare Dis."},{"key":"2406_CR11","doi-asserted-by":"publisher","DOI":"10.1186\/s13023-023-02944-7","volume":"18","author":"M Mazzucato","year":"2023","unstructured":"Mazzucato, M. et al. Estimating mortality in rare diseases using a population-based registry, 2002 through 2019. Orphanet J. Rare Dis. 18, 362 (2023).","journal-title":"Orphanet J. Rare Dis."},{"key":"2406_CR12","doi-asserted-by":"crossref","unstructured":"eClinicalMedicine. Raising the voice for rare diseases: under the spotlight for equity. EClinicalMedicine 57, 101941 (2023).","DOI":"10.1016\/j.eclinm.2023.101941"},{"key":"2406_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40413-018-0207-2","volume":"11","author":"A Gherasim","year":"2018","unstructured":"Gherasim, A., Dao, A. & Bernstein, J. A. Confounders of severe asthma: diagnoses to consider when asthma symptoms persist despite optimal therapy. World Allergy Organ. J. 11, 1\u201311 (2018).","journal-title":"World Allergy Organ. J."},{"key":"2406_CR14","doi-asserted-by":"publisher","first-page":"e20","DOI":"10.1183\/20734735.0362-2018","volume":"15","author":"J Kavanagh","year":"2019","unstructured":"Kavanagh, J., Jackson, D. J. & Kent, B. D. Over-and under-diagnosis in asthma. Breathe 15, e20\u2013e27 (2019).","journal-title":"Breathe"},{"key":"2406_CR15","doi-asserted-by":"publisher","first-page":"1379","DOI":"10.1001\/jama.2022.4402","volume":"327","author":"NF Ruopp","year":"2022","unstructured":"Ruopp, N. F. & Cockrill, B. A. Diagnosis and treatment of pulmonary arterial hypertension: a review. JAMA 327, 1379\u20131391 (2022).","journal-title":"JAMA"},{"key":"2406_CR16","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1093\/eurheartj\/ehv317","volume":"37","author":"N Gali\u00e8","year":"2016","unstructured":"Gali\u00e8, N. et al. 2015 ESC\/ERS guidelines for the diagnosis and treatment of pulmonary hypertension: the Joint Task Force for the Diagnosis and Treatment of Pulmonary Hypertension of the European Society of Cardiology (ESC) and the European Respiratory Society (ERS): endorsed by: Association for European Paediatric and Congenital Cardiology (AEPC), International Society for Heart and Lung Transplantation (ISHLT). Eur. Heart J. 37, 67\u2013119 (2016).","journal-title":"Eur. Heart J."},{"key":"2406_CR17","doi-asserted-by":"publisher","first-page":"3618","DOI":"10.1093\/eurheartj\/ehac237","volume":"43","author":"M Humbert","year":"2022","unstructured":"Humbert, M. et al. 2022 ESC\/ERS guidelines for the diagnosis and treatment of pulmonary hypertension: developed by the Task Force for the Diagnosis and Treatment of Pulmonary Hypertension of the European Society of Cardiology (ESC) and The European Respiratory Society (ERS). Endorsed by the International Society for Heart and Lung Transplantation (ISHLT) and the European Reference Network on Rare Respiratory Diseases (ERN-LUNG). Eur. Heart J. 43, 3618\u20133731 (2022).","journal-title":"Eur. Heart J."},{"key":"2406_CR18","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1378\/chest.10-1166","volume":"140","author":"LM Brown","year":"2011","unstructured":"Brown, L. M. et al. Delay in recognition of pulmonary arterial hypertension: factors identified from the reveal registry. Chest 140, 19\u201326 (2011).","journal-title":"Chest"},{"key":"2406_CR19","doi-asserted-by":"crossref","unstructured":"Chung, K. F. Diagnosis and management of severe asthma. In Seminars in Respiratory and Critical Care Medicine (ed. O\u2019Byrne, P. M.), Vol. 39, 091\u2013099 (Thieme Medical Publishers, 2018).","DOI":"10.1055\/s-0037-1607391"},{"key":"2406_CR20","unstructured":"Sheikh, A. et al. Difficult-to-treat and severe asthma in adolescents and adult patients: diagnosis and management. Global Initiative for Asthma (GINA) (2018)."},{"key":"2406_CR21","unstructured":"Levy, M. L. et al. Why asthma still kills: the National Review of Asthma Deaths (NRAD) confidential enquiry report. Royal College of Physicians, (London, 2014)."},{"key":"2406_CR22","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1177\/2050640615618042","volume":"4","author":"HM D\u2019Agnolo","year":"2016","unstructured":"D\u2019Agnolo, H. M. et al. Creating an effective clinical registry for rare diseases. United European Gastroenterol. J. 4, 333\u2013338 (2016).","journal-title":"United European Gastroenterol. J."},{"key":"2406_CR23","unstructured":"Gliklich, R., Dreyer, N. & Leavy, M. Registries for Evaluating Patient Outcomes: A User\u2019s Guide 3rd edn (Agency for Healthcare Research and Quality (US), 2014)."},{"key":"2406_CR24","doi-asserted-by":"publisher","DOI":"10.1186\/s13023-023-02719-0","volume":"18","author":"IC Hageman","year":"2023","unstructured":"Hageman, I. C., van Rooij, I. A., de Blaauw, I., Trajanovska, M. & King, S. K. A systematic overview of rare disease patient registries: challenges in design, quality management, and maintenance. Orphanet J. Rare Dis. 18, 106 (2023).","journal-title":"Orphanet J. Rare Dis."},{"key":"2406_CR25","doi-asserted-by":"publisher","first-page":"676","DOI":"10.1016\/j.kint.2019.11.037","volume":"97","author":"N Garcelon","year":"2020","unstructured":"Garcelon, N., Burgun, A., Salomon, R. & Neuraz, A. Electronic health records for the diagnosis of rare diseases. Kidney Int. 97, 676\u2013686 (2020).","journal-title":"Kidney Int."},{"key":"2406_CR26","doi-asserted-by":"crossref","unstructured":"Ahmad, S. G. et al. IoT based smart wearable belt for tracking fetal kicks and movements in expectant mothers. IEEE Sensors J. 25, 27322\u201327333 (2025).","DOI":"10.1109\/JSEN.2025.3571818"},{"key":"2406_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s44196-025-00760-4","volume":"18","author":"A Hassan","year":"2025","unstructured":"Hassan, A. et al. Enhanced model for gestational diabetes mellitus prediction using a fusion technique of multiple algorithms with explainability. Int. J. Comput. Intell. Syst. 18, 1\u201333 (2025).","journal-title":"Int. J. Comput. Intell. Syst."},{"key":"2406_CR28","doi-asserted-by":"crossref","unstructured":"Hassan, A., Nawaz, S., Tahira, S. & Ahmed, A. Preterm birth prediction using an explainable machine learning approach. Artif. Intell. Appl. 0, 1\u201314 (2025).","DOI":"10.47852\/bonviewAIA52024517"},{"key":"2406_CR29","first-page":"66","volume":"8","author":"A Hassan","year":"2023","unstructured":"Hassan, A. & Ahmed, A. Predicting Parkinson\u2019s disease progression: a non-invasive method leveraging voice inputs. Comput. Sci. 8, 66\u201382 (2023).","journal-title":"Comput. Sci."},{"key":"2406_CR30","doi-asserted-by":"publisher","first-page":"837","DOI":"10.1016\/S2213-2600(18)30286-8","volume":"6","author":"SL Walsh","year":"2018","unstructured":"Walsh, S. L., Calandriello, L., Silva, M. & Sverzellati, N. Deep learning for classifying fibrotic lung disease on high-resolution computed tomography: a case-cohort study. Lancet Respir. Med. 6, 837\u2013845 (2018).","journal-title":"Lancet Respir. Med."},{"key":"2406_CR31","doi-asserted-by":"crossref","unstructured":"Huang, P. et al. Deep machine learning predicts cancer risk in follow-up lung screening. Lancet Digit. Health 1, e353\u2013e362 (2019).","DOI":"10.1016\/S2589-7500(19)30159-1"},{"key":"2406_CR32","doi-asserted-by":"publisher","first-page":"2255","DOI":"10.1016\/j.jaip.2021.02.014","volume":"9","author":"A Kaplan","year":"2021","unstructured":"Kaplan, A. et al. Artificial intelligence\/machine learning in respiratory medicine and potential role in asthma and copd diagnosis. J. Allergy Clin. Immunol. Pract. 9, 2255\u20132261 (2021).","journal-title":"J. Allergy Clin. Immunol. Pract."},{"key":"2406_CR33","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1016\/j.jpeds.2017.05.037","volume":"188","author":"A Geva","year":"2017","unstructured":"Geva, A. et al. A computable phenotype improves cohort ascertainment in a pediatric pulmonary hypertension registry. J. Pediatr. 188, 224\u2013231 (2017).","journal-title":"J. Pediatr."},{"key":"2406_CR34","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1136\/amiajnl-2013-001935","volume":"21","author":"C Shivade","year":"2014","unstructured":"Shivade, C. et al. A review of approaches to identifying patient phenotype cohorts using electronic health records. J. Am. Med. Inform. Assoc. 21, 221\u2013230 (2014).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"2406_CR35","doi-asserted-by":"publisher","first-page":"1235","DOI":"10.3390\/electronics8111235","volume":"8","author":"H Alzoubi","year":"2019","unstructured":"Alzoubi, H. et al. A review of automatic phenotyping approaches using electronic health records. Electronics 8, 1235 (2019).","journal-title":"Electronics"},{"key":"2406_CR36","doi-asserted-by":"publisher","unstructured":"Xiong, X. et al. Knowledge-driven online multimodal automated phenotyping system. medRxiv https:\/\/doi.org\/10.1101\/2023.09.29.23296239 (2023).","DOI":"10.1101\/2023.09.29.23296239"},{"key":"2406_CR37","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1093\/jamia\/ocx111","volume":"25","author":"S Yu","year":"2018","unstructured":"Yu, S. et al. Enabling phenotypic big data with phenorm. J. Am. Med. Inform. Assoc. 25, 54\u201360 (2018).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"2406_CR38","first-page":"48","volume":"2017","author":"JM Banda","year":"2017","unstructured":"Banda, J. M., Halpern, Y., Sontag, D. & Shah, N. H. Electronic phenotyping with aphrodite and the Observational Health Sciences and Informatics (OHDSI) data network. AMIA Summits Transl. Sci. Proc. 2017, 48 (2017).","journal-title":"AMIA Summits Transl. Sci. Proc."},{"key":"2406_CR39","doi-asserted-by":"publisher","first-page":"104175","DOI":"10.1016\/j.jbi.2022.104175","volume":"134","author":"I-E Nogues","year":"2022","unstructured":"Nogues, I.-E. et al. Weakly semi-supervised phenotyping using electronic health records. J. Biomed. Inform. 134, 104175 (2022).","journal-title":"J. Biomed. Inform."},{"key":"2406_CR40","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1093\/jamia\/ocac216","volume":"30","author":"S Yang","year":"2023","unstructured":"Yang, S., Varghese, P., Stephenson, E., Tu, K. & Gronsbell, J. Machine learning approaches for electronic health records phenotyping: a methodical review. J. Am. Med. Inform. Assoc. 30, 367\u2013381 (2023).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"2406_CR41","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1146\/annurev-biodatasci-080917-013315","volume":"1","author":"JM Banda","year":"2018","unstructured":"Banda, J. M., Seneviratne, M., Hernandez-Boussard, T. & Shah, N. H. Advances in electronic phenotyping: from rule-based definitions to machine learning models. Annu. Rev. Biomed. Data Sci. 1, 53\u201368 (2018).","journal-title":"Annu. Rev. Biomed. Data Sci."},{"key":"2406_CR42","unstructured":"Callahan, T. J. et al. Characterizing patient representations for computational phenotyping. In AMIA Annual Symposium Proceedings, Vol. 2022, 319-328 (American Medical Informatics Association, Washington, DC USA, 2023)."},{"key":"2406_CR43","doi-asserted-by":"crossref","unstructured":"Choi, E. et al. Multi-layer representation learning for medical concepts. In Proc. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 1495\u20131504 (Association for Computing Machinery, New York, NY USA, 2016).","DOI":"10.1145\/2939672.2939823"},{"key":"2406_CR44","doi-asserted-by":"publisher","unstructured":"Weng, W.-H. & Szolovits, P. Representation learning for electronic health records. Preprint at arXiv https:\/\/doi.org\/10.48550\/arXiv.1909.09248 (2019).","DOI":"10.48550\/arXiv.1909.09248"},{"key":"2406_CR45","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-018-0029-1","volume":"1","author":"A Rajkomar","year":"2018","unstructured":"Rajkomar, A. et al. Scalable and accurate deep learning with electronic health records. NPJ Digital Med. 1, 18 (2018).","journal-title":"NPJ Digital Med."},{"key":"2406_CR46","doi-asserted-by":"publisher","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","volume":"35","author":"Y Bengio","year":"2013","unstructured":"Bengio, Y., Courville, A. & Vincent, P. Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35, 1798\u20131828 (2013).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2406_CR47","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-023-02112-2","volume":"23","author":"EA Fridgeirsson","year":"2023","unstructured":"Fridgeirsson, E. A., Sontag, D. & Rijnbeek, P. Attention-based neural networks for clinical prediction modelling on electronic health records. BMC Med. Res. Methodol. 23, 285 (2023).","journal-title":"BMC Med. Res. Methodol."},{"key":"2406_CR48","doi-asserted-by":"publisher","first-page":"803","DOI":"10.1038\/s41592-023-01886-z","volume":"20","author":"J Banerjee","year":"2023","unstructured":"Banerjee, J. et al. Machine learning in rare disease. Nat. Methods 20, 803\u2013814 (2023).","journal-title":"Nat. Methods"},{"key":"2406_CR49","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13023-020-01424-6","volume":"15","author":"J Schaefer","year":"2020","unstructured":"Schaefer, J., Lehne, M., Schepers, J., Prasser, F. & Thun, S. The use of machine learning in rare diseases: a scoping review. Orphanet J. Rare Dis. 15, 1\u201310 (2020).","journal-title":"Orphanet J. Rare Dis."},{"key":"2406_CR50","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-024-02581-5","volume":"24","author":"J Yang","year":"2024","unstructured":"Yang, J., Triendl, H., Soltan, A. A., Prakash, M. & Clifton, D. A. Addressing label noise for electronic health records: insights from computer vision for tabular data. BMC Med. Inform. Decis. Mak. 24, 183 (2024).","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"2406_CR51","doi-asserted-by":"crossref","unstructured":"Wu, H., Yamal, J. M., Yaseen, A. & Maroufy, V. Statistics and Machine Learning Methods for EHR Data: From Data Extraction to Data Analytics (CRC Press, 2020).","DOI":"10.1201\/9781003030003"},{"key":"2406_CR52","doi-asserted-by":"publisher","first-page":"e201965","DOI":"10.1001\/jamanetworkopen.2020.1965","volume":"3","author":"AA Mitani","year":"2020","unstructured":"Mitani, A. A. & Haneuse, S. Small data challenges of studying rare diseases. JAMA Netw. Open 3, e201965\u2013e201965 (2020).","journal-title":"JAMA Netw. Open"},{"key":"2406_CR53","unstructured":"Vaswani, A. et al. Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)."},{"key":"2406_CR54","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-43715-z","volume":"14","author":"Z Yang","year":"2023","unstructured":"Yang, Z., Mitra, A., Liu, W., Berlowitz, D. & Yu, H. Transformehr: transformer-based encoder-decoder generative model to enhance prediction of disease outcomes using electronic health records. Nat. Commun. 14, 7857 (2023).","journal-title":"Nat. Commun."},{"key":"2406_CR55","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-62922-y","volume":"10","author":"Y Li","year":"2020","unstructured":"Li, Y. et al. Behrt: transformer for electronic health records. Sci. Rep. 10, 7155 (2020).","journal-title":"Sci. Rep."},{"key":"2406_CR56","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-021-00455-y","volume":"4","author":"L Rasmy","year":"2021","unstructured":"Rasmy, L., Xiang, Y., Xie, Z., Tao, C. & Zhi, D. Med-bert: pretrained contextualized embeddings on large-scale structured electronic health records for disease prediction. NPJ Digital Med. 4, 86 (2021).","journal-title":"NPJ Digital Med."},{"key":"2406_CR57","doi-asserted-by":"crossref","unstructured":"Hirszowicz, O. & Aran, D. ICU bloodstream infection prediction: a transformer-based approach for EHR analysis. In International Conference on Artificial Intelligence in Medicine, 279\u2013292 (Springer, 2024).","DOI":"10.1007\/978-3-031-66538-7_28"},{"key":"2406_CR58","doi-asserted-by":"publisher","first-page":"e281","DOI":"10.1016\/S2589-7500(24)00025-6","volume":"6","author":"Z Kraljevic","year":"2024","unstructured":"Kraljevic, Z. et al. Foresight\u2014a generative pretrained transformer for modelling of patient timelines using electronic health records: a retrospective modelling study. Lancet Digital Health 6, e281\u2013e290 (2024).","journal-title":"Lancet Digital Health"},{"key":"2406_CR59","doi-asserted-by":"publisher","unstructured":"Yu, S., Cai, T. & Cai, T. NILE: fast natural language processing for electronic health records. Preprint at arXiv https:\/\/doi.org\/10.48550\/arXiv.1311.6063 (2013).","DOI":"10.48550\/arXiv.1311.6063"},{"key":"2406_CR60","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01320-4","volume":"7","author":"M Li","year":"2024","unstructured":"Li, M. et al. Multisource representation learning for pediatric knowledge extraction from electronic health records. NPJ Digital Med. 7, 319 (2024).","journal-title":"NPJ Digital Med."},{"key":"2406_CR61","doi-asserted-by":"crossref","unstructured":"Chen, T. & Guestrin, C. Xgboost: a scalable tree boosting system. In Proc. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785\u2013794 (Association for Computing Machinery, New York, NY USA, 2016).","DOI":"10.1145\/2939672.2939785"},{"key":"2406_CR62","first-page":"2579","volume":"9","author":"Lvd Maaten","year":"2008","unstructured":"Maaten, L. vd & Hinton, G. Visualizing data using t-sne. J. Mach. Learn. Res. 9, 2579\u20132605 (2008).","journal-title":"J. Mach. Learn. Res."},{"key":"2406_CR63","unstructured":"Ramos, J. et al. Using tf-idf to determine word relevance in document queries. In Proc. First Instructional Conference on Machine Learning, Vol. 242, 29\u201348 (Citeseer, 2003)."},{"key":"2406_CR64","unstructured":"Van der Maaten, L. & Hinton, G. Visualizing data using t-sne. J. Mach. Learn. Res. 9, 2579\u20132605 (2008)."},{"key":"2406_CR65","doi-asserted-by":"publisher","first-page":"324","DOI":"10.1093\/ije\/dyu222","volume":"44","author":"LD Amorim","year":"2015","unstructured":"Amorim, L. D. & Cai, J. Modelling recurrent events: a tutorial for analysis in epidemiology. Int. J. Epidemiol. 44, 324\u2013333 (2015).","journal-title":"Int. J. Epidemiol."},{"key":"2406_CR66","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1007\/s00778-019-00552-1","volume":"29","author":"A Ratner","year":"2020","unstructured":"Ratner, A. et al. Snorkel: rapid training data creation with weak supervision. VLDB J. 29, 709\u2013730 (2020).","journal-title":"VLDB J."},{"key":"2406_CR67","first-page":"596","volume":"33","author":"K Sohn","year":"2020","unstructured":"Sohn, K. et al. Fixmatch: simplifying semi-supervised learning with consistency and confidence. Adv. Neural Inf. Process. Syst. 33, 596\u2013608 (2020).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2406_CR68","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1049\/cit2.12216","volume":"8","author":"Z Ren","year":"2023","unstructured":"Ren, Z., Wang, S. & Zhang, Y. Weakly supervised machine learning. CAAI Trans. Intell. Technol. 8, 549\u2013580 (2023).","journal-title":"CAAI Trans. Intell. Technol."},{"key":"2406_CR69","doi-asserted-by":"publisher","first-page":"1255","DOI":"10.1093\/jamia\/ocz066","volume":"26","author":"KP Liao","year":"2019","unstructured":"Liao, K. P. et al. High-throughput multimodal automated phenotyping (MAP) with application to phewas. J. Am. Med. Inform. Assoc. 26, 1255\u20131262 (2019).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"2406_CR70","doi-asserted-by":"publisher","first-page":"103746","DOI":"10.1016\/j.jbi.2021.103746","volume":"117","author":"T Fert\u00e9","year":"2021","unstructured":"Fert\u00e9, T. et al. Automatic phenotyping of electronical health record: Phevis algorithm. J. Biomed. Inform. 117, 103746 (2021).","journal-title":"J. Biomed. Inform."},{"key":"2406_CR71","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1016\/j.chest.2019.02.004","volume":"156","author":"RL Benza","year":"2019","unstructured":"Benza, R. L. et al. Predicting survival in patients with pulmonary arterial hypertension: the reveal risk score calculator 2.0 and comparison with ESC\/ERS-based risk assessment strategies. Chest 156, 323\u2013337 (2019).","journal-title":"Chest"},{"key":"2406_CR72","doi-asserted-by":"publisher","first-page":"1457","DOI":"10.1016\/j.jaci.2014.08.015","volume":"135","author":"ED Bateman","year":"2015","unstructured":"Bateman, E. D. et al. Development and validation of a novel risk score for asthma exacerbations: the risk score for exacerbations. J. Allergy Clin. Immunol. 135, 1457\u20131464 (2015).","journal-title":"J. Allergy Clin. Immunol."},{"key":"2406_CR73","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/j.acap.2021.07.005","volume":"22","author":"J Hatoun","year":"2022","unstructured":"Hatoun, J., Correa, E. T., MacGinnitie, A. J., Gaffin, J. M. & Vernacchio, L. Development and validation of the asthma exacerbation risk score using claims data. Acad. Pediatr. 22, 47\u201354 (2022).","journal-title":"Acad. Pediatr."},{"key":"2406_CR74","unstructured":"Teshima, T., Sato, I. & Sugiyama, M. Few-shot domain adaptation by causal mechanism transfer. In International Conference on Machine Learning, 9458\u20139469 (PMLR, 2020)."},{"key":"2406_CR75","doi-asserted-by":"crossref","unstructured":"Guan, J., Zhang, M. & Lu, Z. Large-scale cross-domain few-shot learning. In Proc. Asian Conference on Computer Vision (Springer, 2020).","DOI":"10.1007\/978-3-030-69535-4_29"},{"key":"2406_CR76","doi-asserted-by":"publisher","first-page":"12459","DOI":"10.1109\/TNNLS.2023.3263176","volume":"35","author":"T Jing","year":"2023","unstructured":"Jing, T., Xia, H., Hamm, J. & Ding, Z. Marginalized augmented few-shot domain adaptation. IEEE Trans. Neural Netw. Learn. Syst. 35, 12459\u201312469 (2023).","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"2406_CR77","doi-asserted-by":"publisher","unstructured":"Liu, F., Shareghi, E., Meng, Z., Basaldella, M. & Collier, N. Self-alignment pretraining for biomedical entity representations. Preprint at arXiv https:\/\/doi.org\/10.48550\/arXiv.2010.11784 (2020).","DOI":"10.48550\/arXiv.2010.11784"},{"key":"2406_CR78","doi-asserted-by":"publisher","first-page":"103983","DOI":"10.1016\/j.jbi.2021.103983","volume":"126","author":"Z Yuan","year":"2022","unstructured":"Yuan, Z. et al. Coder: knowledge-infused cross-lingual medical term embedding for term normalization. J. Biomed. Inform. 126, 103983 (2022).","journal-title":"J. Biomed. Inform."},{"key":"2406_CR79","doi-asserted-by":"publisher","unstructured":"Wu, Z. et al. Token statistics transformer: linear-time attention via variational rate reduction. Preprint at arXiv https:\/\/doi.org\/10.48550\/arXiv.2412.17810 (2024).","DOI":"10.48550\/arXiv.2412.17810"},{"key":"2406_CR80","doi-asserted-by":"publisher","unstructured":"Shazeer, N. Glu variants improve transformer. Preprint at arXiv https:\/\/doi.org\/10.48550\/arXiv.2002.05202 (2020).","DOI":"10.48550\/arXiv.2002.05202"}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02406-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02406-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02406-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T13:04:07Z","timestamp":1773407047000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02406-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,6]]},"references-count":80,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2406"],"URL":"https:\/\/doi.org\/10.1038\/s41746-026-02406-x","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,6]]},"assertion":[{"value":"2 November 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"211"}}