{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T16:37:22Z","timestamp":1785602242864,"version":"3.56.0"},"reference-count":98,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,6,14]],"date-time":"2025-06-14T00:00:00Z","timestamp":1749859200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,6,14]],"date-time":"2025-06-14T00:00:00Z","timestamp":1749859200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Mr Nicolas Pictet"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The widespread adoption of Electronic Health Records (EHRs) and deep learning, particularly through Self-Supervised Representation Learning (SSRL) for categorical data, has transformed clinical decision-making. This scoping review, following PRISMA-ScR guidelines, examines 46 studies published from January 2019 to April 2024, sourced from PubMed, MEDLINE, Embase, ACM, and Web of Science, focusing on SSRL for unlabeled categorical EHR data. The review systematically assesses research trends in building computationally and data-efficient representations for medical tasks, identifying major trends in model families: Transformer-based (43%), Autoencoder-based (28%), and Graph Neural Network-based (17%) models. The analysis highlights scenarios where healthcare institutions can leverage or develop SSRL technologies. It also addresses current limitations in assessing the impact of these technologies and identifies research opportunities to enhance their influence on clinical practice.<\/jats:p>","DOI":"10.1038\/s41746-025-01692-1","type":"journal-article","created":{"date-parts":[[2025,6,14]],"date-time":"2025-06-14T07:19:45Z","timestamp":1749885585000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["A scoping review of self-supervised representation learning for clinical decision making using EHR categorical data"],"prefix":"10.1038","volume":"8","author":[{"given":"Yuanyuan","family":"Zheng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adel","family":"Bensahla","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mina","family":"Bjelogrlic","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jamil","family":"Zaghir","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hugues","family":"Turbe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lydie","family":"Bednarczyk","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christophe","family":"Gaudet-Blavignac","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julien","family":"Ehrsam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"St\u00e9phane","family":"Marchand-Maillet","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Lovis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,6,14]]},"reference":[{"key":"1692_CR1","doi-asserted-by":"publisher","first-page":"e3","DOI":"10.2196\/jmir.7.1.e3","volume":"7","author":"TD Gunter","year":"2005","unstructured":"Gunter, T. D. & Terry, N. P. The emergence of national electronic health record architectures in the United States and Australia: models, costs, and questions. J. Med. Internet Res. 7, e3 (2005).","journal-title":"J. Med. Internet Res."},{"key":"1692_CR2","doi-asserted-by":"publisher","first-page":"327","DOI":"10.3390\/life10120327","volume":"10","author":"CH Tsai","year":"2020","unstructured":"Tsai, C. H. et al. Effects of electronic health record implementation and barriers to adoption and use: a scoping review and qualitative analysis of the content. Life 10, 327 (2020).","journal-title":"Life"},{"key":"1692_CR3","doi-asserted-by":"crossref","unstructured":"Deep learning techniques for electronic health record (EHR) analysis. IEEE J. Biomed. Health Inf. 22, 1589\u20131604 (2017).","DOI":"10.1109\/JBHI.2017.2767063"},{"key":"1692_CR4","unstructured":"FDA. Artificial intelligence and machine learning (AI\/ML)-enabled medical devices (FDA, 2024)."},{"key":"1692_CR5","doi-asserted-by":"crossref","unstructured":"Wornow, M. et al. The shaky foundations of large language models and foundation models for electronic health records. npj Digit. Med. 6, 1\u201310 (2023).","DOI":"10.1038\/s41746-023-00879-8"},{"key":"1692_CR6","unstructured":"Oquab, M. et al. DINOv2: Learning Robust Visual Features without Supervision. Transactions on Machine Learning Research (2024)."},{"key":"1692_CR7","doi-asserted-by":"publisher","unstructured":"Cherti, M. et al. Reproducible scaling laws for contrastive language-image learning. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2818\u20132829. https:\/\/doi.org\/10.1109\/CVPR52729.2023.00276. (2023)","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"1692_CR8","unstructured":"OpenAI et al. GPT-4 Technical Report. Preprint at http:\/\/arxiv.org\/abs\/2303.08774 (2024)."},{"key":"1692_CR9","doi-asserted-by":"publisher","unstructured":"Wang, Z., Wu, Z., Agarwal, D. & Sun, J. MedCLIP: Contrastive Learning from Unpaired Medical Images and Text. in Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (eds. Goldberg, Y., Kozareva, Z. & Zhang, Y.) 3876\u20133887 https:\/\/doi.org\/10.18653\/v1\/2022.emnlp-main.256 (Association for Computational Linguistics, Abu Dhabi, United Arab Emirates, 2022).","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"1692_CR10","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-44824-z","volume":"15","author":"J Ma","year":"2024","unstructured":"Ma, J. et al. Segment anything in medical images. Nat. Commun. 15, 654 (2024).","journal-title":"Nat. Commun."},{"key":"1692_CR11","doi-asserted-by":"publisher","unstructured":"Bommasani, R. et al. On the opportunities and risks of foundation models. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2108.07258 (2022).","DOI":"10.48550\/arXiv.2108.07258"},{"key":"1692_CR12","doi-asserted-by":"crossref","unstructured":"He, Y. et al. Foundation Model for Advancing Healthcare: Challenges, Opportunities and Future Directions. IEEE Rev. Biomed. Eng. 18, 172\u2013191 (2025).","DOI":"10.1109\/RBME.2024.3496744"},{"key":"1692_CR13","doi-asserted-by":"publisher","first-page":"4548","DOI":"10.1109\/JBHI.2023.3288768","volume":"27","author":"M Lentzen","year":"2023","unstructured":"Lentzen, M. et al. A Transformer-Based Model Trained on Large Scale Claims Data for Prediction of Severe COVID-19 Disease Progression. IEEE J. Biomed. Health Inform. 27, 4548\u20134558 (2023).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"1692_CR14","doi-asserted-by":"crossref","unstructured":"Steinberg, E. et al. Language models are an effective representation learning technique for electronic health record data. J. Biomed. Inform 113, 103637 (2021).","DOI":"10.1016\/j.jbi.2020.103637"},{"key":"1692_CR15","unstructured":"The HIPAA privacy rule. https:\/\/www.hhs.gov\/hipaa\/for-professionals\/privacy\/index.html (2008)."},{"key":"1692_CR16","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1136\/medethics-2019-105472","volume":"46","author":"E Ford","year":"2020","unstructured":"Ford, E. et al. Should free-text data in electronic medical records be shared for research? A citizens\u2019 jury study in the UK. J. Med. Ethics 46, 367\u2013377 (2020).","journal-title":"J. Med. Ethics"},{"key":"1692_CR17","first-page":"857","volume":"35","author":"X Liu","year":"2023","unstructured":"Liu, X. et al. Self-supervised learning: generative or contrastive. IEEE Trans. Knowl. Data Eng. 35, 857\u2013876 (2023).","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"1692_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2020.103671","volume":"115","author":"Y Si","year":"2021","unstructured":"Si, Y. et al. Deep representation learning of patient data from Electronic Health Records (EHR): a systematic review. J. Biomed. Inform. 115, 103671 (2021).","journal-title":"J. Biomed. Inform."},{"key":"1692_CR19","doi-asserted-by":"publisher","first-page":"104430","DOI":"10.1016\/j.jbi.2023.104430","volume":"144","author":"A Amirahmadi","year":"2023","unstructured":"Amirahmadi, A., Ohlsson, M. & Etminani, K. Deep learning prediction models based on EHR trajectories: a systematic review. J. Biomed. Inform. 144, 104430 (2023).","journal-title":"J. Biomed. Inform."},{"key":"1692_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2024.104616","volume":"151","author":"H Oss Boll","year":"2024","unstructured":"Oss Boll, H. et al. Graph neural networks for clinical risk prediction based on electronic health records: A survey. J. Biomed. Inform. 151, 104616 (2024).","journal-title":"J. Biomed. Inform."},{"key":"1692_CR21","doi-asserted-by":"crossref","unstructured":"Hama, T. et al. Enhancing Patient Outcome Prediction Through Deep Learning With Sequential Diagnosis Codes From Structured Electronic Health Record Data: Systematic Review. J. Med. Internet Res 27, e57358 (2025).","DOI":"10.2196\/57358"},{"key":"1692_CR22","doi-asserted-by":"crossref","unstructured":"Shang, J., Ma, T., Xiao, C. & Sun, J. Pre-training of Graph Augmented Transformers for Medication Recommendation. 5953\u20135959 (2019).","DOI":"10.24963\/ijcai.2019\/825"},{"key":"1692_CR23","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-07545-1","volume":"12","author":"X Zeng","year":"2022","unstructured":"Zeng, X., Linwood, S. L. & Liu, C. Pretrained transformer framework on pediatric claims data for population specific tasks. Sci. Rep. 12, 3651 (2022).","journal-title":"Sci. Rep."},{"key":"1692_CR24","doi-asserted-by":"publisher","first-page":"2124","DOI":"10.1109\/TCYB.2021.3109881","volume":"53","author":"C Lu","year":"2023","unstructured":"Lu, C., Reddy, C. K. & Ning, Y. Self-supervised graph learning with hyperbolic embedding for temporal health event prediction. IEEE Trans. Cybern. 53, 2124\u20132136 (2023).","journal-title":"IEEE Trans. Cybern."},{"key":"1692_CR25","doi-asserted-by":"publisher","unstructured":"Xu, Y. et al. SeqCare: sequential training with external medical knowledge graph for diagnosis prediction in healthcare data. In: Proceedings of the ACM Web Conference 2023 2819\u20132830 (ACM, 2023). https:\/\/doi.org\/10.1145\/3543507.3583543.","DOI":"10.1145\/3543507.3583543"},{"key":"1692_CR26","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1109\/JBHI.2022.3217810","volume":"27","author":"S Liu","year":"2023","unstructured":"Liu, S. et al. Multimodal data matters: language model pre-training over structured and unstructured electronic health records. IEEE J. Biomed. Health Inform. 27, 504\u2013514 (2023).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"1692_CR27","doi-asserted-by":"publisher","first-page":"2329","DOI":"10.1109\/TBME.2023.3243311","volume":"70","author":"Z Liu","year":"2023","unstructured":"Liu, Z. et al. Patient clustering for vital organ failure using ICD code with graph attention. IEEE Trans. Biomed. Eng. 70, 2329\u20132337 (2023).","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"1692_CR28","doi-asserted-by":"publisher","unstructured":"Cao, Y., Wang, Q., Wang, X., Peng, D. & Li, P. Multi-gate mixture of multi-view graph contrastive learning on electronic health record. IEEE J. Biomed. Health Inf. 1\u201313, https:\/\/doi.org\/10.1109\/JBHI.2023.3325221 (2023)","DOI":"10.1109\/JBHI.2023.3325221"},{"key":"1692_CR29","doi-asserted-by":"publisher","first-page":"e28842","DOI":"10.2196\/28842","volume":"10","author":"S Kumar","year":"2022","unstructured":"Kumar, S., Nanelia, A., Mariappan, R., Rajagopal, A. & Rajan, V. Patient representation learning from heterogeneous data sources and knowledge graphs using deep collective matrix factorization: evaluation study. JMIR Med. Inf. 10, e28842 (2022).","journal-title":"JMIR Med. Inf."},{"key":"1692_CR30","doi-asserted-by":"publisher","first-page":"e25113","DOI":"10.2196\/25113","volume":"23","author":"Y-P Chen","year":"2021","unstructured":"Chen, Y.-P., Lo, Y.-H., Lai, F. & Huang, C.-H. Disease concept-embedding based on the self-supervised method for medical information extraction from electronic health records and disease retrieval: algorithm development and validation study. J. Med. Internet Res. 23, e25113 (2021).","journal-title":"J. Med. Internet Res."},{"key":"1692_CR31","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-019-0985-7","volume":"19","author":"T Ruan","year":"2019","unstructured":"Ruan, T. et al. Representation learning for clinical time series prediction tasks in electronic health records. BMC Med. Inf. Decis. Mak. 19, 259 (2019).","journal-title":"BMC Med. Inf. Decis. Mak."},{"key":"1692_CR32","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-020-00923-1","volume":"20","author":"L Wang","year":"2020","unstructured":"Wang, L., Tong, L., Davis, D., Arnold, T. & Esposito, T. The application of unsupervised deep learning in predictive models using electronic health records. BMC Med. Res. Methodol. 20, 37 (2020).","journal-title":"BMC Med. Res. Methodol."},{"key":"1692_CR33","doi-asserted-by":"publisher","first-page":"e19905","DOI":"10.2196\/19905","volume":"9","author":"Y Huang","year":"2021","unstructured":"Huang, Y. et al. Patient representation from structured electronic medical records based on embedding technique: development and validation study. JMIR Med. Inf. 9, e19905 (2021).","journal-title":"JMIR Med. Inf."},{"key":"1692_CR34","doi-asserted-by":"publisher","unstructured":"Poulain, R., Gupta, M., Foraker, R. & Beheshti, R. Transformer-based multi-target regression on electronic health records for primordial prevention of cardiovascular disease. In: 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) 726\u2013731 (IEEE, 2021). https:\/\/doi.org\/10.1109\/BIBM52615.2021.9669441.","DOI":"10.1109\/BIBM52615.2021.9669441"},{"key":"1692_CR35","doi-asserted-by":"publisher","first-page":"1106","DOI":"10.1109\/JBHI.2022.3224727","volume":"27","author":"Y Li","year":"2023","unstructured":"Li, Y. et al. Hi-BEHRT: hierarchical transformer-based model for accurate prediction of clinical events using multimodal longitudinal electronic health records. IEEE J. Biomed. Health Inform. 27, 1106\u20131117 (2023).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"1692_CR36","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-30820-8","volume":"13","author":"LL Guo","year":"2023","unstructured":"Guo, L. L. et al. EHR foundation models improve robustness in the presence of temporal distribution shift. Sci. Rep. 13, 3767 (2023).","journal-title":"Sci. Rep."},{"key":"1692_CR37","doi-asserted-by":"publisher","first-page":"2004","DOI":"10.1093\/jamia\/ocad175","volume":"30","author":"J Lemmon","year":"2023","unstructured":"Lemmon, J. et al. Self-supervised machine learning using adult inpatient data produces effective models for pediatric clinical prediction tasks. J. Am. Med. Inform. Assoc. 30, 2004\u20132011 (2023).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"1692_CR38","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2022.104218","volume":"135","author":"E Manzini","year":"2022","unstructured":"Manzini, E. et al. Longitudinal deep learning clustering of Type 2 Diabetes Mellitus trajectories using routinely collected health records. J. Biomed. Inform. 135, 104218 (2022).","journal-title":"J. Biomed. Inform."},{"key":"1692_CR39","doi-asserted-by":"publisher","first-page":"102895","DOI":"10.1016\/j.media.2023.102895","volume":"89","author":"C Pellegrini","year":"2023","unstructured":"Pellegrini, C., Navab, N. & Kazi, A. Unsupervised pre-training of graph transformers on patient population graphs. Med. Image Anal. 89, 102895 (2023).","journal-title":"Med. Image Anal."},{"key":"1692_CR40","doi-asserted-by":"publisher","first-page":"1723","DOI":"10.1109\/TNNLS.2020.2989364","volume":"32","author":"J Song","year":"2021","unstructured":"Song, J. et al. Local\u2013global memory neural network for medication prediction. IEEE Trans. Neural Netw. Learn. Syst. 32, 1723\u20131736 (2021).","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"1692_CR41","doi-asserted-by":"publisher","first-page":"2641","DOI":"10.1093\/jamia\/ocab203","volume":"28","author":"Y Huang","year":"2021","unstructured":"Huang, Y. et al. Deep significance clustering: a novel approach for identifying risk-stratified and predictive patient subgroups. J. Am. Med. Inform. Assoc. 28, 2641\u20132653 (2021).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"1692_CR42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41746-020-0301-z","volume":"3","author":"I Landi","year":"2020","unstructured":"Landi, I. et al. Deep representation learning of electronic health records to unlock patient stratification at scale. npj Digit. Med. 3, 1\u201311 (2020).","journal-title":"npj Digit. Med."},{"key":"1692_CR43","doi-asserted-by":"publisher","first-page":"104168","DOI":"10.1016\/j.jbi.2022.104168","volume":"134","author":"T Zhang","year":"2022","unstructured":"Zhang, T., Chen, M. & Bui, A. A. T. AdaDiag: adversarial domain adaptation of diagnostic prediction with clinical event sequences. J. Biomed. Inform. 134, 104168 (2022).","journal-title":"J. Biomed. Inform."},{"key":"1692_CR44","doi-asserted-by":"publisher","first-page":"450","DOI":"10.1109\/JBHI.2023.3321132","volume":"28","author":"P Blinov","year":"2024","unstructured":"Blinov, P. & Kokh, V. Medical profile model: scientific and practical applications in healthcare. IEEE J. Biomed. Health Inform. 28, 450\u2013458 (2024).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"1692_CR45","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":"1692_CR46","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2021.100337","volume":"2","author":"JK De Freitas","year":"2021","unstructured":"De Freitas, J. K. et al. Phe2vec: Automated disease phenotyping based on unsupervised embeddings from electronic health records. Patterns 2, 100337 (2021).","journal-title":"Patterns"},{"key":"1692_CR47","doi-asserted-by":"publisher","first-page":"256","DOI":"10.1093\/jamia\/ocac208","volume":"30","author":"CN Ta","year":"2023","unstructured":"Ta, C. N. et al. Clinical and temporal characterization of COVID-19 subgroups using patient vector embeddings of electronic health records. J. Am. Med. Inform. Assoc. 30, 256\u2013272 (2023).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"1692_CR48","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1038\/s41586-023-06221-2","volume":"620","author":"H Wang","year":"2023","unstructured":"Wang, H. et al. Scientific discovery in the age of artificial intelligence. Nature 620, 47\u201360 (2023).","journal-title":"Nature"},{"key":"1692_CR49","doi-asserted-by":"publisher","first-page":"551","DOI":"10.3390\/e24040551","volume":"24","author":"S Albelwi","year":"2022","unstructured":"Albelwi, S. Survey on Self-Supervised Learning: Auxiliary Pretext Tasks and Contrastive Learning Methods in Imaging. Entropy 24, 551 (2022).","journal-title":"Entropy"},{"key":"1692_CR50","unstructured":"Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv, http:\/\/arxiv.org\/abs\/1810.04805 (2018)."},{"key":"1692_CR51","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":"1692_CR52","doi-asserted-by":"publisher","first-page":"3121","DOI":"10.1109\/JBHI.2021.3063721","volume":"25","author":"Y Meng","year":"2021","unstructured":"Meng, Y., Speier, W., Ong, M. K. & Arnold, C. W. Bidirectional representation learning from transformers using multimodal electronic health record data to predict depression. IEEE J. Biomed. Health Inform. 25, 3121\u20133129 (2021).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"1692_CR53","doi-asserted-by":"publisher","first-page":"e41775","DOI":"10.2196\/41775","volume":"7","author":"B Ru","year":"2023","unstructured":"Ru, B. et al. Comparison of machine learning algorithms for predicting hospital readmissions and worsening heart failure events in patients with heart failure with reduced ejection fraction: modeling study. JMIR Form. Res. 7, e41775 (2023).","journal-title":"JMIR Form. Res."},{"key":"1692_CR54","doi-asserted-by":"publisher","first-page":"1","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 Digit. Med. 4, 1\u201313 (2021).","journal-title":"npj Digit. Med."},{"key":"1692_CR55","unstructured":"Pang, C. et al. CEHR-BERT: Incorporating temporal information from structured EHR data to improve prediction tasks. in Proceedings of Machine Learning for Health 239\u2013260 (PMLR, 2021)."},{"key":"1692_CR56","first-page":"853","volume":"182","author":"R Poulain","year":"2022","unstructured":"Poulain, R., Gupta, M. & Beheshti, R. Few-shot learning with semi-supervised transformers for electronic health records. Proc. Mach. Learn Res. 182, 853\u2013873 (2022).","journal-title":"Proc. Mach. Learn Res."},{"key":"1692_CR57","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":"1692_CR58","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-39543-2","volume":"13","author":"B Dong","year":"2023","unstructured":"Dong, B. et al. Toward a stable and low-resource PLM-based medical diagnostic system via prompt tuning and MoE structure. Sci. Rep. 13, 12595 (2023).","journal-title":"Sci. Rep."},{"key":"1692_CR59","first-page":"249","volume":"258","author":"S de Lusignan","year":"2019","unstructured":"de Lusignan, S. et al. Analysis of primary care computerised medical records with deep learning. Stud. Health Technol. Inf. 258, 249\u2013250 (2019).","journal-title":"Stud. Health Technol. Inf."},{"key":"1692_CR60","doi-asserted-by":"publisher","first-page":"102211","DOI":"10.1016\/j.artmed.2021.102211","volume":"122","author":"D Chushig-Muzo","year":"2021","unstructured":"Chushig-Muzo, D., Soguero-Ruiz, C., de Miguel-Bohoyo, P. & Mora-Jim\u00e9nez, I. Interpreting clinical latent representations using autoencoders and probabilistic models. Artif. Intell. Med. 122, 102211 (2021).","journal-title":"Artif. Intell. Med."},{"key":"1692_CR61","doi-asserted-by":"publisher","first-page":"768","DOI":"10.3390\/jpm12050768","volume":"12","author":"AN Navaz","year":"2022","unstructured":"Navaz, A. N., El-Kassabi H, T., Serhani, M. A., Oulhaj, A. & Khalil, K. A novel patient similarity network (PSN) framework based on multi-model deep learning for precision medicine. JPM 12, 768 (2022).","journal-title":"JPM"},{"key":"1692_CR62","doi-asserted-by":"publisher","first-page":"50295","DOI":"10.1109\/ACCESS.2023.3272745","volume":"11","author":"J Herp","year":"2023","unstructured":"Herp, J. et al. Modeling of electronic health records for time-variant event learning beyond bio-markers\u2014a case study in prostate cancer. IEEE Access 11, 50295\u201350309 (2023).","journal-title":"IEEE Access"},{"key":"1692_CR63","doi-asserted-by":"publisher","first-page":"ooad086","DOI":"10.1093\/jamiaopen\/ooad086","volume":"6","author":"BW Jones","year":"2023","unstructured":"Jones, B. W., Taylor, W. D. & Walsh, C. G. Sequential autoencoders for feature engineering and pretraining in major depressive disorder risk prediction. JAMIA Open 6, ooad086 (2023).","journal-title":"JAMIA Open"},{"key":"1692_CR64","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-022-04680-4","volume":"23","author":"W Shao","year":"2022","unstructured":"Shao, W. et al. Application of unsupervised deep learning algorithms for identification of specific clusters of chronic cough patients from EMR data. BMC Bioinforma. 23, 140 (2022).","journal-title":"BMC Bioinforma."},{"key":"1692_CR65","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-85255-w","volume":"11","author":"T Wu","year":"2021","unstructured":"Wu, T., Wang, Y., Wang, Y., Zhao, E. & Yuan, Y. Leveraging graph-based hierarchical medical entity embedding for healthcare applications. Sci. Rep. 11, 5858 (2021).","journal-title":"Sci. Rep."},{"key":"1692_CR66","doi-asserted-by":"crossref","unstructured":"Nurmaini, S. et al. Deep Learning-Based Stacked Denoising and Autoencoder for ECG Heartbeat Classification. Electronics 9, 135 (2020).","DOI":"10.3390\/electronics9010135"},{"key":"1692_CR67","doi-asserted-by":"publisher","unstructured":"Steck, H. Embarrassingly shallow autoencoders for sparse data. In: The World Wide Web Conference 3251\u20133257, https:\/\/doi.org\/10.1145\/3308558.3313710 (2019).","DOI":"10.1145\/3308558.3313710"},{"key":"1692_CR68","doi-asserted-by":"publisher","unstructured":"Almeida, F. & Xex\u00e9o, G. Word embeddings: a survey. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1901.09069 (2023).","DOI":"10.48550\/arXiv.1901.09069"},{"key":"1692_CR69","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1146\/annurev-biodatasci-110723-024625","volume":"7","author":"R Johnson","year":"2024","unstructured":"Johnson, R., Li, M. M., Noori, A., Queen, O. & Zitnik, M. Graph artificial intelligence in medicine. Annu. Rev. Biomed. Data Sci. 7, 345\u2013368 (2024).","journal-title":"Annu. Rev. Biomed. Data Sci."},{"key":"1692_CR70","doi-asserted-by":"publisher","DOI":"10.1016\/j.physd.2019.132306","volume":"404","author":"A Sherstinsky","year":"2020","unstructured":"Sherstinsky, A. Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. Phys. D Nonlinear Phenom. 404, 132306 (2020).","journal-title":"Phys. D Nonlinear Phenom."},{"key":"1692_CR71","unstructured":"RWKV-TS: beyond traditional recurrent neural network for time series tasks. Preprint at https:\/\/arxiv.org\/html\/2401.09093v1 (2024)."},{"key":"1692_CR72","unstructured":"Vaswani, A. et al. Attention is all you need. arXiv, http:\/\/arxiv.org\/abs\/1706.03762 (2017)."},{"key":"1692_CR73","doi-asserted-by":"publisher","unstructured":"Izsak, P., Berchansky, M. & Levy, O. How to train BERT with an academic budget. In: Proceedings of the 2021 conference on empirical methods in natural language processing (eds. Moens, M.-F., Huang, X., Specia, L. & Yih, S. W.) 10644\u201310652 (Association for Computational Linguistics, Online and Punta Cana, Dominican Republic, 2021). https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.831.","DOI":"10.18653\/v1\/2021.emnlp-main.831"},{"key":"1692_CR74","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/j.cmpb.2018.05.008","volume":"174","author":"Z Liang","year":"2019","unstructured":"Liang, Z. et al. Deep generative learning for automated EHR diagnosis of traditional Chinese medicine. Comput Methods Prog. Biomed. 174, 17\u201323 (2019).","journal-title":"Comput Methods Prog. Biomed."},{"key":"1692_CR75","unstructured":"Definitions, methods, and applications in interpretable machine learning. https:\/\/www.pnas.org\/doi\/epdf\/10.1073\/pnas.1900654116"},{"key":"1692_CR76","doi-asserted-by":"publisher","unstructured":"Seki, T., Kawazoe, Y. & Ohe, K. Graph representation learning-based fixed-length clinical feature vector generation from heterogeneous medical records. In: Studies in health technology and informatics (eds. Bichel-Findlay, J., Otero, P., Scott, P. & Huesing, E.) (IOS Press, 2024). https:\/\/doi.org\/10.3233\/SHTI231058.","DOI":"10.3233\/SHTI231058"},{"key":"1692_CR77","unstructured":"Understanding the ICD-10 code structure. https:\/\/www.healthnetworksolutions.net\/index.php\/understanding-the-icd-10-code-structure."},{"key":"1692_CR78","doi-asserted-by":"publisher","DOI":"10.23915\/distill.00002","volume":"1","author":"M Wattenberg","year":"2016","unstructured":"Wattenberg, M., Vi\u00e9gas, F. & Johnson, I. How to use t-SNE effectively. Distill 1, e2 (2016).","journal-title":"Distill"},{"key":"1692_CR79","doi-asserted-by":"publisher","unstructured":"Serrano, S. & Smith, N. A. Is attention interpretable? In: Proceedings of the 57th annual meeting of the association for computational linguistics (eds. Korhonen, A., Traum, D. & M\u00e0rquez, L.) 2931\u20132951 (Association for Computational Linguistics, Florence, 2019). https:\/\/doi.org\/10.18653\/v1\/P19-1282.","DOI":"10.18653\/v1\/P19-1282"},{"key":"1692_CR80","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41746-024-01166-w","volume":"7","author":"LL Guo","year":"2024","unstructured":"Guo, L. L. et al. A multi-center study on the adaptability of a shared foundation model for electronic health records. npj Digit. Med. 7, 1\u20139 (2024).","journal-title":"npj Digit. Med."},{"key":"1692_CR81","doi-asserted-by":"publisher","unstructured":"Thieme, A. et al. Challenges for Responsible AI Design and Workflow Integration in Healthcare: A Case Study of Automatic Feeding Tube Qualification in Radiology. ACM Trans. Comput.-Hum. Interact. https:\/\/doi.org\/10.1145\/3716500 (2025).","DOI":"10.1145\/3716500"},{"key":"1692_CR82","doi-asserted-by":"publisher","first-page":"1584","DOI":"10.1093\/jamia\/ocac086","volume":"29","author":"Z Zhang","year":"2022","unstructured":"Zhang, Z., Yan, C., Zhang, X., Nyemba, S. L. & Malin, B. A. Forecasting the future clinical events of a patient through contrastive learning. J. Am. Med. Inform. Assoc. 29, 1584\u20131592 (2022).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"1692_CR83","doi-asserted-by":"publisher","unstructured":"Raj, J. A., Qian, L. & Ibrahim, Z. Fine-tuning\u2013a Transfer Learning approach. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2411.03941 (2024).","DOI":"10.48550\/arXiv.2411.03941"},{"key":"1692_CR84","doi-asserted-by":"crossref","unstructured":"Zaghir, J. et al. Prompt Engineering Paradigms for Medical Applications: Scoping Review. J. Med. Internet Res 26, e60501 (2024).","DOI":"10.2196\/60501"},{"key":"1692_CR85","unstructured":"Wornow, M., Thapa, R., Steinberg, E., Fries, J. & Shah, N. EHRSHOT: An EHR Benchmark for Few-Shot Evaluation of Foundation Models. Advances in Neural Information Processing Systems 36, 67125\u201367137 (2023)."},{"key":"1692_CR86","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41746-020-00323-1","volume":"3","author":"N Rieke","year":"2020","unstructured":"Rieke, N. et al. The future of digital health with federated learning. npj Digit. Med. 3, 1\u20137 (2020).","journal-title":"npj Digit. Med."},{"key":"1692_CR87","doi-asserted-by":"publisher","unstructured":"Johnson, R. et al. Unified clinical vocabulary embeddings for advancing precision. Preprint at https:\/\/doi.org\/10.1101\/2024.12.03.24318322 (2024).","DOI":"10.1101\/2024.12.03.24318322"},{"key":"1692_CR88","unstructured":"SNOMED International. Systematized nomenclature of medicine - clinical terms (SNOMED-CT). https:\/\/www.snomed.org\/ (1999)."},{"key":"1692_CR89","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1007\/s10676-024-09769-3","volume":"26","author":"T Speith","year":"2024","unstructured":"Speith, T., Crook, B., Mann, S., Schom\u00e4cker, A. & Langer, M. Conceptualizing understanding in explainable artificial intelligence (XAI): an abilities-based approach. Ethics Inf. Technol. 26, 40 (2024).","journal-title":"Ethics Inf. Technol."},{"key":"1692_CR90","doi-asserted-by":"publisher","unstructured":"Nauta, M. et al. Interpreting and Correcting Medical Image Classification with PIP-Net. in Artificial Intelligence. ECAI 2023 International Workshops (eds. Nowaczyk, S. et al.) 198\u2013215 https:\/\/doi.org\/10.1007\/978-3-031-50396-2_11 (Springer Nature Switzerland, Cham, 2024).","DOI":"10.1007\/978-3-031-50396-2_11"},{"key":"1692_CR91","unstructured":"Hu, E. J. et al. LoRA: Low-Rank Adaptation of Large Language Models. in (2021)."},{"key":"1692_CR92","unstructured":"Gao, Y. et al. Retrieval-Augmented Generation for Large Language Models: A Survey. CoRR (2023)."},{"key":"1692_CR93","doi-asserted-by":"publisher","unstructured":"Placido, D. et al. A deep learning algorithm to predict risk of pancreatic cancer from disease trajectories. Nat. Med. 1\u201310, https:\/\/doi.org\/10.1038\/s41591-023-02332-5 (2023).","DOI":"10.1038\/s41591-023-02332-5"},{"key":"1692_CR94","doi-asserted-by":"publisher","first-page":"1045","DOI":"10.1038\/ng2127","volume":"39","author":"TA Manolio","year":"2007","unstructured":"Manolio, T. A. et al. New models of collaboration in genome-wide association studies: the Genetic Association Information Network. Nat. Genet 39, 1045\u20131051 (2007).","journal-title":"Nat. Genet"},{"key":"1692_CR95","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1515\/dx-2018-0036","volume":"6","author":"M Quinn","year":"2019","unstructured":"Quinn, M. et al. Electronic health records, communication, and data sharing: challenges and opportunities for improving the diagnostic process. Diagnosis 6, 241\u2013248 (2019).","journal-title":"Diagnosis"},{"key":"1692_CR96","doi-asserted-by":"publisher","unstructured":"Kim, J., Kim, J., Hur, K. & Choi, E. EHRFL: federated learning framework for heterogeneous EHRs and precision-guided selection of participating clients. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2404.13318 (2024).","DOI":"10.48550\/arXiv.2404.13318"},{"key":"1692_CR97","doi-asserted-by":"crossref","unstructured":"Benson, T. Principles of Health Interoperability HL7 and SNOMED (Springer Science & Business Media, 2012).","DOI":"10.1007\/978-1-4471-2801-4"},{"key":"1692_CR98","doi-asserted-by":"publisher","first-page":"467","DOI":"10.7326\/M18-0850","volume":"169","author":"AC Tricco","year":"2018","unstructured":"Tricco, A. C. et al. PRISMA Extension for Scoping Reviews (PRISMA-ScR): Checklist and Explanation. Ann. Intern. Med. 169, 467\u2013473 (2018).","journal-title":"Ann. Intern. Med."}],"updated-by":[{"DOI":"10.1038\/s41746-025-01919-1","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T00:00:00Z","timestamp":1755475200000}}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01692-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01692-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01692-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T21:10:32Z","timestamp":1757193032000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01692-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,14]]},"references-count":98,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1692"],"URL":"https:\/\/doi.org\/10.1038\/s41746-025-01692-1","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-5058251\/v1","asserted-by":"object"}]},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,14]]},"assertion":[{"value":"9 September 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 April 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 June 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 August 2025","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1038\/s41746-025-01919-1","URL":"https:\/\/doi.org\/10.1038\/s41746-025-01919-1","order":7,"name":"change_details","label":"Change Details","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":"362"}}