{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T22:01:17Z","timestamp":1788904877132,"version":"build-2803163510"},"reference-count":77,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T00:00:00Z","timestamp":1778630400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T00:00:00Z","timestamp":1784160000000},"content-version":"vor","delay-in-days":64,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001279","name":"Great Ormond Street Hospital Charity","doi-asserted-by":"publisher","award":["21PP30"],"award-info":[{"award-number":["21PP30"]}],"id":[{"id":"10.13039\/501100001279","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"RCUK | Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/W031892\/1"],"award-info":[{"award-number":["EP\/W031892\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000287","name":"Royal Academy of Engineering","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000287","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000265","name":"RCUK | Medical Research Council","doi-asserted-by":"publisher","award":["UK DRI-7002"],"award-info":[{"award-number":["UK DRI-7002"]}],"id":[{"id":"10.13039\/501100000265","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Commun"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Paediatric cardiology presents challenges due to the rarity and complexity of conditions like congenital heart disease. Using retrospective electronic healthcare records from 1,522 Great Ormond Street Hospital cases, we benchmark machine learning models to predict length of stay and retrieve similar patient cases. BioClinical-BERT is used for embedding-based retrieval, while a Random Forest model achieves the best length of stay prediction accuracy (0.88 \u00a0\u00b1 0.02), outperforming clinicians. The Random Forest model shows mean precision and sensitivity of 0.77 \u00a0\u00b1 0.03 and 0.76 \u00a0\u00b1 0.04 during NHS silent deployment (1,052 admissions). K-means identifies three clinically distinct subgroups. Cosine similarity retrieval reveals diagnosis-driven top matches, while complications dominate broader sets. In a 25-case intensive care unit pilot, clinician-rated utility improves from 4.23 \u00a0\u00b1 2.42 to 4.41 \u00a0\u00b1 2.16 (scale 0-10). Our models surpass clinician performance in length of stay prediction and show promise for case retrieval, supporting data-driven decision-making in paediatric cardiology and beyond.<\/jats:p>","DOI":"10.1038\/s41467-026-73021-3","type":"journal-article","created":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T10:38:22Z","timestamp":1778668702000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Clinically-applicable prediction of hospital stay and patient similarity retrieval in paediatric cardiology using machine learning"],"prefix":"10.1038","volume":"17","author":[{"given":"Louise","family":"Rigny","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5785-4295","authenticated-orcid":false,"given":"Iona","family":"Biggart","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kimberley","family":"Zakka","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingteng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3884-8045","authenticated-orcid":false,"given":"Alexander","family":"Capstick","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sebin","family":"Sabu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pavithra","family":"Rajendran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shankar","family":"Sridharan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sumera","family":"Farooq","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Taylor","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4357-1324","authenticated-orcid":false,"given":"John","family":"Booth","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiren","family":"Patel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Padmanabhan","family":"Ramnarayan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Neil","family":"Sebire","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cho","family":"Ng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8591-9638","authenticated-orcid":false,"given":"Payam","family":"Barnaghi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,13]]},"reference":[{"key":"73021_CR1","doi-asserted-by":"crossref","unstructured":"Speer, E. M. et al. The state and future of pediatric research\u2014an introductory overview. Pediatr. Res. 24, 1\u20135 (2023).","DOI":"10.1038\/s41390-022-02439-4"},{"key":"73021_CR2","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00898-5","volume":"6","author":"V Muralidharan","year":"2023","unstructured":"Muralidharan, V., Burgart, A., Daneshjou, R. & Rose, S. Recommendations for the use of pediatric data in artificial intelligence and machine learning: ACCEPT-AI. npj Digit. Med. 6, 166 (2023).","journal-title":"npj Digit. Med."},{"key":"73021_CR3","doi-asserted-by":"publisher","first-page":"228","DOI":"10.1016\/j.paed.2024.04.005","volume":"34","author":"C Ho","year":"2024","unstructured":"Ho, C. & Sutcliffe, A. The paediatric research environment in the UK: key wins and needs. Paediatr. Child Health 34, 228\u2013233 (2024).","journal-title":"Paediatr. Child Health"},{"key":"73021_CR4","doi-asserted-by":"publisher","first-page":"1236","DOI":"10.1001\/jamapediatrics.2021.3360","volume":"175","author":"C Rees","year":"2021","unstructured":"Rees, C., Monuteaux, M. C. & Herdell, V. Correlation between National Institutes of Health funding for pediatric research and pediatric disease burden in the US. JAMA Pediatr. 175, 1236\u20131243 (2021).","journal-title":"JAMA Pediatr."},{"key":"73021_CR5","doi-asserted-by":"publisher","first-page":"7072","DOI":"10.3390\/jcm11237072","volume":"11","author":"Y Sethi","year":"2022","unstructured":"Sethi, Y. et al. Artificial intelligence in pediatric cardiology: a scoping review. J. Clin. Med. 11, 7072 (2022).","journal-title":"J. Clin. Med."},{"key":"73021_CR6","doi-asserted-by":"publisher","first-page":"e379","DOI":"10.1161\/CIR.0000000000000909","volume":"142","author":"C Fordyce","year":"2020","unstructured":"Fordyce, C. et al. Prevention of complications in the cardiac intensive care unit: A scientific statement from the American Heart Association. Circulation 142, e379\u2013e406 (2020).","journal-title":"Circulation"},{"key":"73021_CR7","first-page":"1","volume":"40","author":"G Huang","year":"2018","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L. & Weinberger, K. Q. Densely connected convolutional networks. IEEE Trans. Pattern Anal. Mach. Intell. 40, 1\u201312 (2018).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"73021_CR8","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521, 436\u2013444 (2015).","journal-title":"Nature"},{"key":"73021_CR9","unstructured":"Office of the National Coordinator for Health Information Technology. National trends in hospital and physician adoption of electronic health records https:\/\/www.healthit.gov\/data\/quickstats\/national-trends-hospital-and-physician-adoption-electronic-health-records (2022)."},{"key":"73021_CR10","unstructured":"Office of the National Coordinator for Health Information Technology. Adoption of electronic health records by hospital service type, 2019\u20132021 https:\/\/www.healthit.gov\/data\/quickstats\/adoption-electronic-health-records-hospital-service-type-2019-2021 (2023)."},{"key":"73021_CR11","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1016\/j.ijcard.2019.01.046","volume":"288","author":"TA Daghistani","year":"2019","unstructured":"Daghistani, T. A. et al. Predictors of in-hospital length of stay among cardiac patients: a machine learning approach. Int. J. Cardiol. 288, 140\u2013147 (2019).","journal-title":"Int. J. Cardiol."},{"key":"73021_CR12","doi-asserted-by":"publisher","first-page":"104073","DOI":"10.1016\/j.ijmedinf.2019.104073","volume":"135","author":"Z Jia","year":"2020","unstructured":"Jia, Z., Zeng, X., Duan, H., Lu, X. & Li, H. A patient-similarity-based model for diagnostic prediction. Int. J. Med. Inform. 135, 104073 (2020).","journal-title":"Int. J. Med. Inform."},{"key":"73021_CR13","doi-asserted-by":"publisher","first-page":"107033","DOI":"10.1016\/j.cmpb.2022.107033","volume":"225","author":"Z Sun","year":"2022","unstructured":"Sun, Z., Lu, X., Duan, H. & Li, H. Deep dynamic patient similarity analysis: Model development and validation in ICU. Comput. Methods Prog. Biomed. 225, 107033 (2022).","journal-title":"Comput. Methods Prog. Biomed."},{"key":"73021_CR14","doi-asserted-by":"publisher","first-page":"209278","DOI":"10.1109\/ACCESS.2020.3037710","volume":"8","author":"V Gupta","year":"2020","unstructured":"Gupta, V. et al. A novel deep similarity learning approach to electronic health records data. IEEE Access 8, 209278\u2013209295 (2020).","journal-title":"IEEE Access"},{"key":"73021_CR15","doi-asserted-by":"publisher","first-page":"699","DOI":"10.3390\/jpm11080699","volume":"11","author":"RW Oei","year":"2021","unstructured":"Oei, R. W. et al. Using domain knowledge and data-driven insights for patient similarity analytics. J. Pers. Med. 11, 699 (2021).","journal-title":"J. Pers. Med."},{"key":"73021_CR16","doi-asserted-by":"publisher","first-page":"e49138","DOI":"10.2196\/49138","volume":"12","author":"H Li","year":"2024","unstructured":"Li, H. et al. A patient similarity network (CHDmap) to predict outcomes after congenital heart surgery: development and validation study. JMIR Med. Inform. 12, e49138 (2024).","journal-title":"JMIR Med. Inform."},{"key":"73021_CR17","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-021-01566-y","volume":"21","author":"HSA Fang","year":"2021","unstructured":"Fang, H. S. A. et al. Patient similarity analytics for explainable clinical risk prediction. BMC Med. Inform. Decis. Mak. 21, 207 (2021).","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"73021_CR18","doi-asserted-by":"publisher","first-page":"1330","DOI":"10.1038\/s41551-022-00898-y","volume":"6","author":"A Zhang","year":"2022","unstructured":"Zhang, A., Xing, L., Zou, J. & Wu, J. Shifting machine learning for healthcare from development to deployment and from models to data. Nat. Biomed. Eng. 6, 1330\u20131345 (2022).","journal-title":"Nat. Biomed. Eng."},{"key":"73021_CR19","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1001\/jama.2017.7797","volume":"318","author":"F Cabitza","year":"2017","unstructured":"Cabitza, F., Rasoini, R. & Gensini, G. F. Unintended consequences of machine learning in medicine. JAMA 318, 517\u2013518 (2017).","journal-title":"JAMA"},{"key":"73021_CR20","doi-asserted-by":"publisher","first-page":"1337","DOI":"10.1038\/s41591-019-0548-6","volume":"25","author":"J Wiens","year":"2019","unstructured":"Wiens, J. et al. Do no harm: a roadmap for responsible machine learning for health care. Nat. Med. 25, 1337\u20131340 (2019).","journal-title":"Nat. Med."},{"key":"73021_CR21","doi-asserted-by":"publisher","first-page":"2613 \u2013 2622","DOI":"10.1038\/s41591-024-03097-1","volume":"30","author":"P Hager","year":"2024","unstructured":"Hager, P. et al. Evaluation and mitigation of the limitations of large language models in clinical decision-making. Nat. Med. 30, 2613 \u2013 2622 (2024).","journal-title":"Nat. Med."},{"key":"73021_CR22","doi-asserted-by":"publisher","first-page":"687","DOI":"10.1038\/s42256-023-00670-0","volume":"5","author":"Z Jia","year":"2023","unstructured":"Jia, Z. et al. The importance of resource awareness in artificial intelligence for healthcare. Nat. Mach. Intell. 5, 687\u2013698 (2023).","journal-title":"Nat. Mach. Intell."},{"key":"73021_CR23","doi-asserted-by":"publisher","first-page":"r240","DOI":"10.1136\/bmj.r240","volume":"388","author":"C Stokel-Walker","year":"2025","unstructured":"Stokel-Walker, C. AI in medicine: UK is pursuing \u201cmiddle path\u201d in adoption and regulation. BMJ 388, r240 (2025).","journal-title":"BMJ"},{"key":"73021_CR24","doi-asserted-by":"publisher","first-page":"330","DOI":"10.1016\/j.sapharm.2012.04.004","volume":"9","author":"N Gisev","year":"2013","unstructured":"Gisev, N., Bell, J. S. & Chen, T. F. Interrater agreement and interrater reliability: Key concepts, approaches, and applications. Res. Soc. Adm. Pharm. 9, 330\u2013338 (2013).","journal-title":"Res. Soc. Adm. Pharm."},{"key":"73021_CR25","doi-asserted-by":"publisher","first-page":"e0245157","DOI":"10.1371\/journal.pone.0245157","volume":"16","author":"W Van Doorn","year":"2021","unstructured":"Van Doorn, W., Stassen, P. & Borggreve, H. F. A comparison of machine learning models versus clinical evaluation for mortality prediction in patients with sepsis. PLoS ONE 16, e0245157 (2021).","journal-title":"PLoS ONE"},{"key":"73021_CR26","doi-asserted-by":"publisher","first-page":"e271","DOI":"10.1016\/S2589-7500(19)30123-2","volume":"1","author":"X Liu","year":"2019","unstructured":"Liu, X., Faes, L. & Wagner, S. A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis. Lancet Digit. Health 1, e271\u2013e297 (2019).","journal-title":"Lancet Digit. Health"},{"key":"73021_CR27","doi-asserted-by":"publisher","first-page":"e2440969","DOI":"10.1001\/jamanetworkopen.2024.40969","volume":"7","author":"E Goh","year":"2024","unstructured":"Goh, E., Gallo, R. & Hom, J. Large language model influence on diagnostic reasoning: A randomized clinical trial. JAMA Network Open 7, e2440969 (2024).","journal-title":"JAMA Network Open"},{"key":"73021_CR28","doi-asserted-by":"publisher","first-page":"e367","DOI":"10.1016\/S2589-7500(24)00047-5","volume":"6","author":"R Han","year":"2024","unstructured":"Han, R., Acosta, J. & Shakeri, Z. Randomised controlled trials evaluating artificial intelligence in clinical practice: a scoping review. Lancet Digit. Health 6, e367\u2013e373 (2024).","journal-title":"Lancet Digit. Health"},{"key":"73021_CR29","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 for electronic health records. NPJ Digit. Med. 1, 18 (2018).","journal-title":"NPJ Digit. Med."},{"key":"73021_CR30","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1007\/s10198-021-01373-2","volume":"23","author":"B Walsh","year":"2022","unstructured":"Walsh, B., Smith, S., Wren, M.-A., Eighan, J. & Lyons, S. The impact of inpatient bed capacity on length of stay.  Eur. J. Health Econ. 23, 499\u2013510 (2022).","journal-title":"Eur. J. Health Econ."},{"key":"73021_CR31","doi-asserted-by":"publisher","DOI":"10.1186\/s12913-021-06912-4","volume":"21","author":"NB Medeiros","year":"2021","unstructured":"Medeiros, N. B., Fogliatto, F. S., Rocha, M. K. & Tortorella, G. L. Forecasting the length-of-stay of pediatric patients in hospitals: a scoping review. BMC Health Serv. Res. 21, 938 (2021).","journal-title":"BMC Health Serv. Res."},{"key":"73021_CR32","doi-asserted-by":"publisher","first-page":"e0000017","DOI":"10.1371\/journal.pdig.0000017","volume":"1","author":"K Stone","year":"2022","unstructured":"Stone, K., Zwiggelaar, R., Jones, P. & Mac Parthal\u00e1in, N. A systematic review of the prediction of hospital length of stay: towards a unified framework. PLOS Digit. Health 1, e0000017 (2022).","journal-title":"PLOS Digit. Health"},{"key":"73021_CR33","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-022-01855-0","volume":"22","author":"Z Xu","year":"2022","unstructured":"Xu, Z., Zhao, C., Scales, C. D., Henao, R. & Goldstein, B. A. Predicting in-hospital length of stay: a two-stage modeling approach to account for highly skewed data. BMC Med. Inform. Decis. Mak. 22, 110 (2022).","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"73021_CR34","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1136\/archdischild-2024-327155","volume":"110","author":"S Dick","year":"2025","unstructured":"Dick, S. et al. Systematic review of interventions to reduce hospital and emergency department stay in paediatric populations. Arch. Dis. Child. 110, 120\u2013126 (2025).","journal-title":"Arch. Dis. Child."},{"key":"73021_CR35","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-25472-z","volume":"12","author":"BP Bednarski","year":"2022","unstructured":"Bednarski, B. P. et al. Temporal convolutional networks and data rebalancing for clinical length of stay and mortality prediction. Sci. Rep. 12, 21247 (2022).","journal-title":"Sci. Rep."},{"key":"73021_CR36","doi-asserted-by":"crossref","unstructured":"Rocheteau, E., Li\u00f2, P. & Hyland, S. Temporal pointwise convolutional networks for length of stay prediction in the intensive care unit. In Proc. Conference on Health, Inference, and Learning 58\u201368 (ACM, 2021).","DOI":"10.1145\/3450439.3451860"},{"key":"73021_CR37","doi-asserted-by":"publisher","first-page":"962","DOI":"10.3390\/bioengineering11100962","volume":"11","author":"H Ganatra","year":"2024","unstructured":"Ganatra, H., Latifi, S. Q. & Baloglu, O. Pediatric intensive care unit length of stay prediction by machine learning. Bioengineering 11, 962 (2024).","journal-title":"Bioengineering"},{"key":"73021_CR38","doi-asserted-by":"publisher","DOI":"10.1186\/s12913-024-11238-y","volume":"24","author":"R Jain","year":"2024","unstructured":"Jain, R., Singh, M., Rao, A. R. & Garg, R. Predicting hospital length of stay using machine learning on a large open health dataset. BMC Health Serv. Res. 24, 860 (2024).","journal-title":"BMC Health Serv. Res."},{"key":"73021_CR39","doi-asserted-by":"publisher","first-page":"e055956","DOI":"10.1136\/bmjopen-2021-055956","volume":"12","author":"IM Niehaus","year":"2022","unstructured":"Niehaus, I. M., Kansy, N., Stock, S., Doetsch, J. & Mueller, D. Applicability of predictive models for 30-day unplanned hospital readmission risk in paediatrics: a systematic review. BMJ Open 12, e055956 (2022).","journal-title":"BMJ Open"},{"key":"73021_CR40","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-20910-4","volume":"12","author":"KH Goh","year":"2021","unstructured":"Goh, K. H. et al. Artificial intelligence in sepsis early prediction and diagnosis using unstructured data in healthcare. Nat. Commun. 12, 711 (2021).","journal-title":"Nat. Commun."},{"key":"73021_CR41","unstructured":"Tonekaboni, S. et al. How to validate machine learning models prior to deployment: a silent trial protocol for evaluation of real-time models at ICU. In Proc. Conference on Health, Inference, and Learning, vol. 174 of Proceedings of Machine Learning Research, 169\u2013182 https:\/\/proceedings.mlr.press\/v174\/tonekaboni22a.html (2022)."},{"key":"73021_CR42","doi-asserted-by":"publisher","first-page":"929508","DOI":"10.3389\/fdgth.2022.929508","volume":"4","author":"JC Kwong","year":"2022","unstructured":"Kwong, J. C. et al. The silent trial-the bridge between bench-to-bedside clinical AI applications. Front. Digit. Health 4, 929508 (2022).","journal-title":"Front. Digit. Health"},{"key":"73021_CR43","doi-asserted-by":"publisher","first-page":"1248","DOI":"10.1016\/j.healun.2022.05.016","volume":"41","author":"D Gupta","year":"2022","unstructured":"Gupta, D., Bansal, N. & Jaegar, B. Prolonged hospital length of stay after pediatric heart transplantation: a machine learning and logistic regression predictive model from the Pediatric Heart Transplant Society. J. Heart Lung Transplant. 41, 1248\u20131257 (2022).","journal-title":"J. Heart Lung Transplant."},{"key":"73021_CR44","doi-asserted-by":"crossref","unstructured":"Holst, K. A., Said, S. M., Nelson, T. J., Cannon, B. C. & Dearani, J. A. Current interventional and surgical management of congenital heart disease: specific focus on valvular disease and cardiac arrhythmias. Circ. Res. 120, 1027\u20131044 (2017).","DOI":"10.1161\/CIRCRESAHA.117.309186"},{"key":"73021_CR45","unstructured":"Chen, D. et al. Early detection of post-surgical complications using time-series electronic health records. In AMIA Jt. Summits Transl. Sci. Proc. 2021, 152\u2013160 (2021)."},{"key":"73021_CR46","doi-asserted-by":"crossref","unstructured":"Hyland, S. L. et al. Early prediction of circulatory failure in the intensive care unit using machine learning. Nat. Med. 26, 364\u2013373 (2020).","DOI":"10.1038\/s41591-020-0789-4"},{"key":"73021_CR47","doi-asserted-by":"publisher","first-page":"2049","DOI":"10.1056\/NEJMsb2005114","volume":"382","author":"EJ Emanuel","year":"2020","unstructured":"Emanuel, E. J. et al. Fair allocation of scarce medical resources in the time of Covid-19. N. Engl. J. Med. 382, 2049\u20132055 (2020).","journal-title":"N. Engl. J. Med."},{"key":"73021_CR48","doi-asserted-by":"publisher","first-page":"2010","DOI":"10.1377\/hlthaff.2020.00980","volume":"39","author":"JD Birkmeyer","year":"2020","unstructured":"Birkmeyer, J. D., Barnato, J. S., Birkmeyer, A., Bessler, J. K. & Skinner, D. J. The impact of the COVID-19 pandemic on hospital admissions in the United States. Health Aff. 39, 2010\u20132017 (2020).","journal-title":"Health Aff."},{"key":"73021_CR49","doi-asserted-by":"publisher","first-page":"e045343","DOI":"10.1136\/bmjopen-2020-045343","volume":"11","author":"R Moynihan","year":"2021","unstructured":"Moynihan, R. et al. Impact of COVID-19 pandemic on utilisation of healthcare services: a systematic review. BMJ Open 11, e045343 (2021).","journal-title":"BMJ Open"},{"key":"73021_CR50","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01899-x","volume":"10","author":"AEW Johnson","year":"2023","unstructured":"Johnson, A. E. W. et al. MIMIC-IV, a freely accessible electronic health record dataset. Sci. Data 10, 1 (2023).","journal-title":"Sci. Data"},{"key":"73021_CR51","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-022-01827-4","volume":"22","author":"P Sabharwal","year":"2022","unstructured":"Sabharwal, P. et al. Combining adult with pediatric patient data to develop a clinical decision support tool intended for children: leveraging machine learning to model heterogeneity. BMC Med. Inform. Decis. Mak. 22, 84 (2022).","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"73021_CR52","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":"73021_CR53","unstructured":"World Health Organisation. The international classification of diseases, tenth revision, clinical modification https:\/\/www.cdc.gov\/nchs\/icd\/icd-10-cm\/index.html (2019)."},{"key":"73021_CR54","unstructured":"NHS Digital. OPCS classification of interventions and procedures (DAPB0084) https:\/\/tinyurl.com\/DAPB0084-OPCS-Classification (2024)."},{"key":"73021_CR55","doi-asserted-by":"publisher","first-page":"929","DOI":"10.1097\/MLR.0000000000001596","volume":"59","author":"V Lequertier","year":"2021","unstructured":"Lequertier, V., Wang, T., Fondrevelle, J., Augusto, V. & Duclos, A. Hospital length of stay prediction methods: a systematic review. Med. Care 59, 929\u2013938 (2021).","journal-title":"Med. Care"},{"key":"73021_CR56","doi-asserted-by":"publisher","first-page":"znac248","DOI":"10.1093\/bjs\/znac248.138","volume":"109","author":"E Howie","year":"2022","unstructured":"Howie, E., Helley, M., Box, E. & Watt, D. WE5.8 length of stay in emergency general surgery\u2014time for a comprehensive look at our elderly population. Br. J. Surg. 109, znac248\u2013138 (2022).","journal-title":"Br. J. Surg."},{"key":"73021_CR57","unstructured":"Alsentzer, E. BioClinicalBERT https:\/\/huggingface.co\/emilyalsentzer\/Bio_ClinicalBERT (2020)."},{"key":"73021_CR58","doi-asserted-by":"crossref","unstructured":"Rasmy, L. et al. Med-BERT: pretrained contextualized embeddings on large-scale structured electronic health records for disease prediction. npj Digit. Med. 4, 86 (2021).","DOI":"10.1038\/s41746-021-00455-y"},{"key":"73021_CR59","doi-asserted-by":"publisher","first-page":"e59260","DOI":"10.2196\/59260","volume":"26","author":"H Lee","year":"2024","unstructured":"Lee, H. et al. Hospital length of stay prediction for planned admissions using observational medical outcomes partnership common data model: Retrospective study. J. Med. Internet Res. 26, e59260 (2024).","journal-title":"J. Med. Internet Res."},{"key":"73021_CR60","doi-asserted-by":"publisher","first-page":"516","DOI":"10.3389\/fphys.2016.00561","volume":"7","author":"S-A Brown","year":"2016","unstructured":"Brown, S.-A. Patient similarity: Emerging concepts in systems and precision medicine. Front. Physiol. 7, 516 (2016).","journal-title":"Front. Physiol."},{"key":"73021_CR61","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1038\/s43588-023-00453-y","volume":"3","author":"G Jia","year":"2023","unstructured":"Jia, G. et al. The high-dimensional space of human diseases built from diagnosis records and mapped to genetic loci. Nat. Comput. Sci. 3, 403\u2013417 (2023).","journal-title":"Nat. Comput. Sci."},{"key":"73021_CR62","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00847-2","volume":"6","author":"M Jacobsen","year":"2023","unstructured":"Jacobsen, M. et al. Wearable based monitoring and self-supervised contrastive learning detect clinical complications during treatment of hematologic malignancies. npj Digit. Med. 6, 105 (2023).","journal-title":"npj Digit. Med."},{"key":"73021_CR63","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-73316-9","volume":"14","author":"W Gao","year":"2024","unstructured":"Gao, W. et al. Enhancing ophthalmology medical record management with multi-modal knowledge graphs. Sci. Rep. 14, 23221 (2024).","journal-title":"Sci. Rep."},{"key":"73021_CR64","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-019-0807-y","volume":"19","author":"Z Jia","year":"2019","unstructured":"Jia, Z., Lu, X., Duan, H. & Li, H. Using the distance between sets of hierarchical taxonomic clinical concepts to measure patient similarity. BMC Med. Inform. Decis. Mak. 19, 91 (2019).","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"73021_CR65","unstructured":"Google. Clustering algorithms - machine learning. Google for Developers https:\/\/tinyurl.com\/4u2e72r6 (2024)."},{"key":"73021_CR66","doi-asserted-by":"crossref","unstructured":"von Luxburg, U. Clustering Stability: An Overview (Now Foundations and Trends, 2010).","DOI":"10.1561\/2200000008"},{"key":"73021_CR67","doi-asserted-by":"publisher","first-page":"e081554","DOI":"10.1136\/bmj-2024-081554","volume":"388","author":"K Lekadir","year":"2025","unstructured":"Lekadir, K. et al. Future-ai: international consensus guideline for trustworthy and deployable artificial intelligence in healthcare. bmj 388, e081554 (2025).","journal-title":"bmj"},{"key":"73021_CR68","unstructured":"Kubeflow Contributors. Kubeflow: machine learning toolkit for Kubernetes https:\/\/www.kubeflow.org\/ (2025)."},{"key":"73021_CR69","unstructured":"Aridhia Informatics. Aridhia: Data science for healthcare and research https:\/\/www.aridhia.com\/ (2025)."},{"key":"73021_CR70","unstructured":"Python Software Foundation. Python 3.9.0 release https:\/\/www.python.org\/downloads\/release\/python-390\/ (2020)."},{"key":"73021_CR71","unstructured":"Pandas. Pandas - Python data analysis library. Pandas PyData https:\/\/pandas.pydata.org\/ (2024)."},{"key":"73021_CR72","unstructured":"NumPy. NumPy documentation https:\/\/numpy.org\/doc\/stable\/ (2024)."},{"key":"73021_CR73","unstructured":"Scikit-learn. Scikit-learn: Machine learning in Python \u2014 scikit-learn 1.3.0 documentation https:\/\/scikit-learn.org\/stable\/index.html (2024)."},{"key":"73021_CR74","unstructured":"Matplotlib. Matplotlib \u2014 visualization with Python https:\/\/matplotlib.org\/ (2024)."},{"key":"73021_CR75","unstructured":"PyTorch Developers. PyTorch documentation: torch https:\/\/pytorch.org\/docs\/stable\/torch.html (2025)."},{"key":"73021_CR76","doi-asserted-by":"publisher","first-page":"1026","DOI":"10.21105\/joss.01026","volume":"3","author":"R Vallat","year":"2018","unstructured":"Vallat, R. Pingouin: statistics in Python. J. Open Source Softw. 3, 1026 (2018).","journal-title":"J. Open Source Softw."},{"key":"73021_CR77","unstructured":"Hugging Face. Transformers documentation (v4.17.0) https:\/\/huggingface.co\/docs\/transformers\/v4.17.0\/en\/index (2022)."}],"container-title":["Nature Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-73021-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-73021-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-73021-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T09:02:43Z","timestamp":1784192563000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-73021-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,13]]},"references-count":77,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["73021"],"URL":"https:\/\/doi.org\/10.1038\/s41467-026-73021-3","relation":{},"ISSN":["2041-1723"],"issn-type":[{"value":"2041-1723","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,13]]},"assertion":[{"value":"13 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 May 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","label":"Competing interests","group":{"name":"EthicsHeading","label":"Ethics"}}],"article-number":"6370"}}