{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T23:18:25Z","timestamp":1787699905940,"version":"build-2784847793"},"reference-count":69,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T00:00:00Z","timestamp":1781136000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T00:00:00Z","timestamp":1787702400000},"content-version":"vor","delay-in-days":76,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100021856","name":"Ministero dell\u2019Universit\u00e0 e della Ricerca","doi-asserted-by":"publisher","award":["Department of Excellence 2023-2027 awarded to Department of Mathematics, Politecnico di Milano"],"award-info":[{"award-number":["Department of Excellence 2023-2027 awarded to Department of Mathematics, Politecnico di Milano"]}],"id":[{"id":"10.13039\/501100021856","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Identifying patient diagnoses from hospital discharge letters is essential for large-scale cohort selection and epidemiological research, but traditional supervised approaches require extensive manual annotation, which is often impractical for large textual datasets. We present a weakly supervised Natural Language Processing (NLP) pipeline for classifying Italian discharge letters without document-level manual annotation. The method extracts diagnosis-related sentences, generates semantic embeddings using a transformer model further pre-trained on Italian medical documents, and applies a two-level clustering procedure to derive weak labels that are then used to train a document-level classifier. The approach was evaluated in a case study on bronchiolitis using 33,176 discharge letters of children admitted to 44 emergency rooms or hospitals in the Veneto Region, Italy, between 2017 and 2020. The best weakly supervised model achieved an AUROC of 77.68% (\n                    <jats:inline-formula>\n                      <jats:tex-math>$$\\pm 4.30\\%$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    ), an AUPRC of 73.13% (\n                    <jats:inline-formula>\n                      <jats:tex-math>$$\\pm 4.93\\%$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    ), and an F1-score of 78.14% (\n                    <jats:inline-formula>\n                      <jats:tex-math>$$\\pm 4.89\\%$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    ) against manually annotated data. Performance surpassed unsupervised baselines and approached fully supervised models, while reducing the need for manual annotation by more than 1,500 hours for a dataset of this size. Similar model rankings were observed in a secondary validation on a smaller bronchitis dataset (3,188 discharge letters, 2020-2025), where the best weakly supervised model achieved an AUPRC of 76.72% (\n                    <jats:inline-formula>\n                      <jats:tex-math>$$\\pm 5.02\\%$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    ). These results suggest the potential of weakly supervised NLP methods for scalable disease identification from clinical discharge letters.\n                  <\/jats:p>","DOI":"10.1038\/s41598-026-56721-0","type":"journal-article","created":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T15:44:56Z","timestamp":1781192696000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Automatic identification of diagnosis from hospital discharge letters via weakly supervised Natural Language Processing"],"prefix":"10.1038","volume":"16","author":[{"given":"Vittorio","family":"Torri","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elisa","family":"Barbieri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anna","family":"Cantarutti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carlo","family":"Giaquinto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francesca","family":"Ieva","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,11]]},"reference":[{"key":"56721_CR1","doi-asserted-by":"publisher","DOI":"10.1002\/wics.1549","volume":"13","author":"M Tayefi","year":"2021","unstructured":"Tayefi, M. et al. Challenges and opportunities beyond structured data in analysis of electronic health records. WIREs Comput. Stat. 13, e1549 (2021).","journal-title":"WIREs Comput. Stat."},{"key":"56721_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00392-016-1025-6","volume":"106","author":"MR Cowie","year":"2017","unstructured":"Cowie, M. R. et al. Electronic health records to facilitate clinical research. Clin. Res. Cardiol. 106, 1\u20139 (2017).","journal-title":"Clin. Res. Cardiol."},{"key":"56721_CR3","doi-asserted-by":"publisher","first-page":"544","DOI":"10.1136\/amiajnl-2011-000464","volume":"18","author":"PM Nadkarni","year":"2011","unstructured":"Nadkarni, P. M., Ohno-Machado, L. & Chapman, W. W. Natural Language Processing: an introduction. J. Am. Med. Inform. Assoc. 18, 544\u2013551 (2011).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"56721_CR4","doi-asserted-by":"publisher","first-page":"3713","DOI":"10.1007\/s11042-022-13428-4","volume":"82","author":"D Khurana","year":"2023","unstructured":"Khurana, D., Koli, A., Khatter, K. & Singh, S. Natural Language Processing: state of the art, current trends and challenges. Multimed. Tools Appl. 82, 3713\u20133744 (2023).","journal-title":"Multimed. Tools Appl."},{"key":"56721_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.106649","volume":"155","author":"E Hossain","year":"2023","unstructured":"Hossain, E. et al. Natural Language Processing in electronic health records in relation to healthcare decision-making: a systematic review. Comput. Biol. Med. 155, 106649 (2023).","journal-title":"Comput. Biol. Med."},{"key":"56721_CR6","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1007\/978-1-4471-4474-8_8","volume-title":"Biomedical Informatics Computer Applications in Health Care and Biomedicine","author":"C Friedman","year":"2014","unstructured":"Friedman, C. & Elhadad, N. Natural Language Processing in health care and biomedicine. In Biomedical Informatics Computer Applications in Health Care and Biomedicine 255\u2013284 (Springer, 2014)."},{"key":"56721_CR7","first-page":"44","volume":"8","author":"OG Iroju","year":"2015","unstructured":"Iroju, O. G. & Olaleke, J. O. A systematic review of Natural Language Processing in healthcare. Int. J. Inf. Technol. Comput. Sci. 8, 44\u201350 (2015).","journal-title":"Int. J. Inf. Technol. Comput. Sci."},{"key":"56721_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13326-018-0179-8","volume":"9","author":"A N\u00e9v\u00e9ol","year":"2018","unstructured":"N\u00e9v\u00e9ol, A., Dalianis, H., Velupillai, S., Savova, G. & Zweigenbaum, P. Clinical Natural Language Processing in languages other than English: opportunities and challenges. J. Biomed. Semant. 9, 1\u201313 (2018).","journal-title":"J. Biomed. Semant."},{"key":"56721_CR9","unstructured":"World Health Organization. International Statistical Classification of Diseases and Related Health Problems, 10th Revision, 5th Edition Vol. 3 (World Health Organization, 2016)."},{"key":"56721_CR10","doi-asserted-by":"publisher","first-page":"1184","DOI":"10.1136\/bmj.328.7449.1184","volume":"328","author":"SH Walsh","year":"2004","unstructured":"Walsh, S. H. The clinician\u2019s perspective on electronic health records and how they can affect patient care. BMJ 328, 1184\u20131187 (2004).","journal-title":"BMJ"},{"key":"56721_CR11","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1007\/s12553-020-00517-3","volume":"11","author":"P Millares Martin","year":"2021","unstructured":"Millares Martin, P. Consultation analysis: use of free text versus coded text. Health Technol. 11, 349\u2013357 (2021).","journal-title":"Health Technol."},{"key":"56721_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12874-018-0589-4","volume":"18","author":"P Walsh","year":"2018","unstructured":"Walsh, P. & Rothenberg, S. J. Which ICD-9-CM codes should be used for bronchiolitis research?. BMC Med. Res. Methodol. 18, 1\u201311 (2018).","journal-title":"BMC Med. Res. Methodol."},{"key":"56721_CR13","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2017-020630","volume":"8","author":"F Cozzolino","year":"2018","unstructured":"Cozzolino, F. et al. Accuracy of colorectal cancer ICD-9-CM codes in Italian administrative healthcare databases: a cross-sectional diagnostic study. BMJ Open 8, e020630 (2018).","journal-title":"BMJ Open"},{"key":"56721_CR14","doi-asserted-by":"publisher","first-page":"678","DOI":"10.3122\/jabfm.2015.05.140136","volume":"28","author":"CW Cipparone","year":"2015","unstructured":"Cipparone, C. W. et al. Inaccuracy of ICD-9 codes for chronic kidney disease: a study from two practice-based research networks (PBRNs). J. Am. Board Family Med. 28, 678\u2013682 (2015).","journal-title":"J. Am. Board Family Med."},{"issue":"1","key":"56721_CR15","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1038\/s41746-022-00705-7","volume":"5","author":"H Dong","year":"2022","unstructured":"Dong, H. Automated clinical coding: what, why, and where we are?. npj Digit. Med. 5(1), 159 (2022).","journal-title":"npj Digit. Med."},{"key":"56721_CR16","doi-asserted-by":"crossref","unstructured":"Mehrafarin, H., Rajaee, S. & Pilehvar, M. T. On the importance of data size in probing fine-tuned models. In Findings of the Association for Computational Linguistics: ACL2022, 228\u2013238 (2022).","DOI":"10.18653\/v1\/2022.findings-acl.20"},{"key":"56721_CR17","doi-asserted-by":"publisher","DOI":"10.2196\/14330","volume":"8","author":"C Lanera","year":"2020","unstructured":"Lanera, C. et al. Use of machine learning techniques for case-detection of varicella zoster using routinely collected textual ambulatory records: pilot observational study. JMIR Med. Inform. 8, e14330 (2020).","journal-title":"JMIR Med. Inform."},{"key":"56721_CR18","doi-asserted-by":"publisher","first-page":"5959","DOI":"10.3390\/ijerph19105959","volume":"19","author":"C Lanera","year":"2022","unstructured":"Lanera, C. et al. A deep learning approach to estimate the incidence of infectious disease cases for routinely collected ambulatory records: the example of varicella-zoster. Int. J. Environ. Res. Public Health 19, 5959 (2022).","journal-title":"Int. J. Environ. Res. Public Health"},{"key":"56721_CR19","unstructured":"Sciannameo, V. Deep learning for predicting urgent hospitalizations in elderly population using healthcare administrative databases 4022016 (2022) (SSRN pre-print)."},{"key":"56721_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2021.103712","volume":"116","author":"L Hammami","year":"2021","unstructured":"Hammami, L. et al. Automated classification of cancer morphology from Italian pathology reports using Natural Language Processing techniques: a rule-based approach. J. Biomed. Inform. 116, 103712 (2021).","journal-title":"J. Biomed. Inform."},{"key":"56721_CR21","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1016\/j.ijmedinf.2017.12.013","volume":"111","author":"N Viani","year":"2018","unstructured":"Viani, N. et al. Information extraction from Italian medical reports: an ontology-driven approach. Int. J. Med. Inform. 111, 140\u2013148 (2018).","journal-title":"Int. J. Med. Inform."},{"key":"56721_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2019.103219","volume":"95","author":"N Viani","year":"2019","unstructured":"Viani, N. et al. Supervised methods to extract clinical events from cardiology reports in Italian. J. Biomed. Inform. 95, 103219 (2019).","journal-title":"J. Biomed. Inform."},{"key":"56721_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2016.35","volume":"3","author":"AE Johnson","year":"2016","unstructured":"Johnson, A. E. et al. MIMIC-III, a freely accessible critical care database. Sci. Data 3, 1\u20139 (2016).","journal-title":"Sci. Data"},{"key":"56721_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41597-022-01899-x","volume":"10","author":"AE Johnson","year":"2023","unstructured":"Johnson, A. E. et al. MIMIC-IV, a freely accessible electronic health record dataset. Sci. Data 10, 1 (2023).","journal-title":"Sci. Data"},{"key":"56721_CR25","doi-asserted-by":"crossref","unstructured":"Edin, J. Automated medical coding on MIMIC-III and MIMIC-IV: a critical review and replicability study. In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2572\u20132582 (2023).","DOI":"10.1145\/3539618.3591918"},{"key":"56721_CR26","doi-asserted-by":"crossref","unstructured":"Li, F. & Yu, H. ICD coding from clinical text using multi-filter residual convolutional neural network. In Proceedings of the AAAI Conference on Artificial Intelligence34, 8180\u20138187 (2020).","DOI":"10.1609\/aaai.v34i05.6331"},{"key":"56721_CR27","doi-asserted-by":"publisher","first-page":"1193","DOI":"10.1109\/TCBB.2018.2817488","volume":"16","author":"M Li","year":"2018","unstructured":"Li, M. et al. Automated ICD-9 coding via a deep learning approach. IEEE\/ACM Trans. Comput. Biol. Bioinform. 16, 1193\u20131202 (2018).","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinform."},{"key":"56721_CR28","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1093\/ehjdh\/ztae008","volume":"5","author":"M Falter","year":"2024","unstructured":"Falter, M. et al. Using Natural Language Processing for automated classification of disease and to identify misclassified ICD codes in cardiac disease. Eur. Heart J.-Digit. Health 5, 229\u2013234 (2024).","journal-title":"Eur. Heart J.-Digit. Health"},{"key":"56721_CR29","unstructured":"Boytcheva, S. Automatic matching of ICD-10 codes to diagnoses in discharge letters. In Proceedings of the Second Workshop on Biomedical Natural Language Processing, 11\u201318 (2011)."},{"key":"56721_CR30","doi-asserted-by":"crossref","unstructured":"Velichkov, B. Automatic ICD-10 codes association to diagnosis: Bulgarian case. In CSBio\u201920: Proceedings of the Eleventh International Conference on Computational Systems-Biology and Bioinformatics, 46\u201353 (2020).","DOI":"10.1145\/3429210.3429224"},{"key":"56721_CR31","doi-asserted-by":"crossref","unstructured":"Bagheri, A. Automatic ICD-10 classification of diseases from Dutch discharge letters. In Conjunction with the 13th International Joint Conference on Biomedical Engineering Systems and Technologies-BIOSTEC 2020 (2020).","DOI":"10.5220\/0009372600002513"},{"key":"56721_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.107757","volume":"168","author":"JR van Leeuwen","year":"2024","unstructured":"van Leeuwen, J. R., Penne, E. L., Rabelink, T., Knevel, R. & Teng, Y. O. Using an artificial intelligence tool incorporating Natural Language Processing to identify patients with a diagnosis of ANCA-associated vasculitis in electronic health records. Comput. Biol. Med. 168, 107757 (2024).","journal-title":"Comput. Biol. Med."},{"key":"56721_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108672","volume":"178","author":"L Lenc","year":"2024","unstructured":"Lenc, L. Czech medical coding assistant based on transformer networks. Comput. Biol. Med. 178, 108672 (2024).","journal-title":"Comput. Biol. Med."},{"key":"56721_CR34","doi-asserted-by":"crossref","unstructured":"Remmer, S., Lamproudis, A. & Dalianis, H. Multi-label diagnosis classification of swedish discharge summaries\u2013ICD-10 code assignment using KB-BERT. In International Conference Recent Advances in Natural Language Processing (RANLP\u201921), online, September 1\u20133, 2021, 1158\u20131166 (INCOMA Ltd., 2021).","DOI":"10.26615\/978-954-452-072-4_130"},{"key":"56721_CR35","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2021.103969","volume":"126","author":"J Sanyal","year":"2022","unstructured":"Sanyal, J., Rubin, D. & Banerjee, I. A weakly supervised model for the automated detection of adverse events using clinical notes. J. Biomed. Inform. 126, 103969 (2022).","journal-title":"J. Biomed. Inform."},{"key":"56721_CR36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12911-018-0723-6","volume":"19","author":"Y Wang","year":"2019","unstructured":"Wang, Y. et al. A clinical text classification paradigm using weak supervision and deep representation. BMC Med. Inform. Decis. Mak 19, 1 (2019).","journal-title":"BMC Med. Inform. Decis. Mak"},{"key":"56721_CR37","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1016\/j.jpsychires.2021.01.052","volume":"136","author":"M Cusick","year":"2021","unstructured":"Cusick, M. et al. Using weak supervision and deep learning to classify clinical notes for identification of current suicidal ideation. J. Psychiatr. Res. 136, 95\u2013102 (2021).","journal-title":"J. Psychiatr. Res."},{"key":"56721_CR38","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2022.104864","volume":"167","author":"SY Wang","year":"2022","unstructured":"Wang, S. Y. et al. Leveraging weak supervision to perform named entity recognition in electronic health records progress notes to identify the ophthalmology exam. Int. J. Med. Inform. 167, 104864 (2022).","journal-title":"Int. J. Med. Inform."},{"key":"56721_CR39","doi-asserted-by":"publisher","DOI":"10.2196\/32903","volume":"10","author":"M Humbert-Droz","year":"2022","unstructured":"Humbert-Droz, M. et al. Strategies to address the lack of labeled data for supervised machine learning training with electronic health records: case study for the extraction of symptoms from clinical notes. JMIR Med. Inform. 10, e32903 (2022).","journal-title":"JMIR Med. Inform."},{"key":"56721_CR40","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1038\/s41746-026-02406-x","volume":"9","author":"KF Greco","year":"2026","unstructured":"Greco, K. F. A weakly supervised transformer for rare disease diagnosis and subphenotyping from EHRs with pulmonary case studies. npj Digit. Med. 9, 211 (2026).","journal-title":"npj Digit. Med."},{"key":"56721_CR41","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":"56721_CR42","doi-asserted-by":"publisher","first-page":"1235","DOI":"10.1093\/jamia\/ocaa079","volume":"27","author":"Y Ahuja","year":"2020","unstructured":"Ahuja, Y. et al. sureLDA: a multidisease automated phenotyping method for the electronic health record. J. Am. Med. Inform. Assoc. 27, 1235\u20131243 (2020).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"56721_CR43","doi-asserted-by":"publisher","first-page":"731","DOI":"10.1093\/jamia\/ocw011","volume":"23","author":"Y Halpern","year":"2016","unstructured":"Halpern, Y., Horng, S., Choi, Y. & Sontag, D. Electronic medical record phenotyping using the anchor and learn framework. J. Am. Med. Inform. Assoc. 23, 731\u2013740 (2016).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"56721_CR44","doi-asserted-by":"publisher","first-page":"3200","DOI":"10.1093\/bioinformatics\/btaa088","volume":"36","author":"KB Wagholikar","year":"2020","unstructured":"Wagholikar, K. B., Estiri, H., Murphy, M. & Murphy, S. N. Polar labeling: silver standard algorithm for training disease classifiers. Bioinformatics 36, 3200\u20133206 (2020).","journal-title":"Bioinformatics"},{"key":"56721_CR45","doi-asserted-by":"publisher","first-page":"1166","DOI":"10.1093\/jamia\/ocw028","volume":"23","author":"V Agarwal","year":"2016","unstructured":"Agarwal, V. et al. Learning statistical models of phenotypes using noisy labeled training data. J. Am. Med. Inform. Assoc. 23, 1166\u20131173 (2016).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"56721_CR46","first-page":"1","volume":"1","author":"R Smith","year":"2024","unstructured":"Smith, R., Fries, J. A., Hancock, B. & Bach, S. H. Language models in the loop: incorporating prompting into weak supervision. ACM\/JMS J. Data Sci. 1, 1\u201330 (2024).","journal-title":"ACM\/JMS J. Data Sci."},{"issue":"1","key":"56721_CR47","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1038\/s41746-025-01522-4","volume":"8","author":"A Das","year":"2025","unstructured":"Das, A., Talati, I. A., Chaves, J. M. Z., Rubin, D. & Banerjee, I. Weakly supervised language models for automated extraction of critical findings from radiology reports. npj Digit. Med. 8(1), 257 (2025).","journal-title":"npj Digit. Med."},{"key":"56721_CR48","doi-asserted-by":"crossref","unstructured":"De Ferrari, J., \u00d1anculef, R., Benoit, D., Araya, M. & Solar, M. Assessing GPT as a weak oracle for annotating radiological studies. In International Conference on Artificial Intelligence in Medicine, 98\u2013109 (Springer, 2025).","DOI":"10.1007\/978-3-031-95838-0_10"},{"key":"56721_CR49","doi-asserted-by":"publisher","first-page":"588","DOI":"10.1056\/NEJMoa0804877","volume":"360","author":"CB Hall","year":"2009","unstructured":"Hall, C. B. et al. The burden of respiratory syncytial virus infection in young children. N. Engl. J. Med. 360, 588\u2013598 (2009).","journal-title":"N. Engl. J. Med."},{"key":"56721_CR50","doi-asserted-by":"crossref","unstructured":"Cantarutti, A. & Giaquinto, C. Pedianet database. In Databases for Pharmacoepidemiological Research, 159\u2013164 (Springer, 2021).","DOI":"10.1007\/978-3-030-51455-6_13"},{"key":"56721_CR51","doi-asserted-by":"publisher","first-page":"352","DOI":"10.1111\/j.1442-200X.2008.02589.x","volume":"50","author":"Y Durani","year":"2008","unstructured":"Durani, Y., Friedman, M. J. & Attia, M. W. Clinical predictors of respiratory syncytial virus infection in children. Pediatr. Int. 50, 352\u2013355 (2008).","journal-title":"Pediatr. Int."},{"key":"56721_CR52","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1038\/s41598-021-04080-3","volume":"12","author":"AT Gebremedhin","year":"2022","unstructured":"Gebremedhin, A. T., Hogan, A. B., Blyth, C. C., Glass, K. & Moore, H. C. Developing a prediction model to estimate the true burden of respiratory syncytial virus (RSV) in hospitalised children in western australia. Sci. Rep. 12, 332 (2022).","journal-title":"Sci. Rep."},{"key":"56721_CR53","doi-asserted-by":"publisher","first-page":"e821","DOI":"10.1016\/S2589-7500(23)00175-9","volume":"5","author":"P Vartiainen","year":"2023","unstructured":"Vartiainen, P. et al. Risk factors for severe respiratory syncytial virus infection during the first year of life: development and validation of a clinical prediction model. Lancet Digit. Health 5, e821\u2013e830 (2023).","journal-title":"Lancet Digit. Health"},{"key":"56721_CR54","unstructured":"Mikolov, T., Chen, K., Corrado, G. & Dean, J. Efficient estimation of word representations in vector space. In ICLR Workshop, 1\u201312 (2013)."},{"key":"56721_CR55","first-page":"I","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A. Attention is all you need. Advances in Neural Information Processing Systems 30, I (2017).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"56721_CR56","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. BERT: pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), 4171\u20134186 (2019).","DOI":"10.18653\/v1\/N19-1423"},{"key":"56721_CR57","unstructured":"Liu, Y. et al. RoBERTa: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"56721_CR58","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","volume":"36","author":"J Lee","year":"2020","unstructured":"Lee, J. et al. BioBERT: a pre-trained biomedical language representation model for biomedical text mining. Bioinformatics 36, 1234\u20131240 (2020).","journal-title":"Bioinformatics"},{"key":"56721_CR59","doi-asserted-by":"crossref","unstructured":"Alsentzer, E. Publicly available clinical BERT embeddings. In Proceedings of the 2nd Clinical Natural Language Processing Workshop, 72\u201378 (2019).","DOI":"10.18653\/v1\/W19-1909"},{"key":"56721_CR60","first-page":"415","volume":"2020","author":"F Tamburini","year":"2020","unstructured":"Tamburini, F. How, \u201cBERTology\u2019\u2019 changed the state-of-the-art also for Italian NLP. Comput. Linguist. CLiC-it 2020, 415 (2020).","journal-title":"Comput. Linguist. CLiC-it"},{"key":"56721_CR61","doi-asserted-by":"crossref","unstructured":"Magnini, B., Altuna, B., Lavelli, A., Speranza, M. & Zanoli, R. The E3C project: collection and annotation of a multilingual corpus of clinical cases. In Proceedings of the Seventh Italian Conference on Computational Linguistics (2020).","DOI":"10.4000\/books.aaccademia.8663"},{"key":"56721_CR62","doi-asserted-by":"crossref","unstructured":"Campello, R.\u00a0J., Moulavi, D. & Sander, J. Density-based clustering based on hierarchical density estimates. In Pacific-Asia Conference on Knowledge Discovery and Data Mining, 160\u2013172 (Springer, 2013).","DOI":"10.1007\/978-3-642-37456-2_14"},{"key":"56721_CR63","doi-asserted-by":"crossref","unstructured":"Asyaky, M.\u00a0S. & Mandala, R. Improving the performance of HDBSCAN on short text clustering by using word embedding and UMAP. In 2021 8th International Conference on Advanced Informatics: Concepts, Theory and Applications (ICAICTA), 1\u20136 (IEEE, 2021).","DOI":"10.1109\/ICAICTA53211.2021.9640285"},{"key":"56721_CR64","doi-asserted-by":"crossref","unstructured":"Yeasmin, S., Afrin, N. & Huq, M.\u00a0R. Transformer-based text clustering for newspaper articles. In International Conference on Machine Intelligence and Emerging Technologies, 443\u2013457 (Springer, 2022).","DOI":"10.1007\/978-3-031-34619-4_35"},{"key":"56721_CR65","doi-asserted-by":"crossref","unstructured":"Limsopatham, N. Effectively leveraging BERT for legal document classification. In Proceedings of the Natural Legal Language Processing Workshop 2021, 210\u2013216 (2021).","DOI":"10.18653\/v1\/2021.nllp-1.22"},{"key":"56721_CR66","unstructured":"Polignano, M., Basile, P. & Semeraro, G. Advanced natural-based interaction for the italian language: LLaMAntino-3-ANITA. arXiv preprint arXiv:2405.07101 (2024)."},{"key":"56721_CR67","doi-asserted-by":"crossref","unstructured":"Conneau, A. et al. Unsupervised cross-lingual representation learning at scale. In Jurafsky, D., Chai, J., Schluter, N. & Tetreault, J. (eds.) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 8440\u20138451 (Association for Computational Linguistics, Online, 2020).","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"56721_CR68","unstructured":"Chung, H.\u00a0W., Fevry, T., Tsai, H., Johnson, M. & Ruder, S. Rethinking embedding coupling in pre-trained language models. arXiv preprint arXiv:2010.12821 (2020)."},{"key":"56721_CR69","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1002\/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3","volume":"3","author":"WJ Youden","year":"1950","unstructured":"Youden, W. J. Index for rating diagnostic tests. Cancer 3, 32\u201335 (1950).","journal-title":"Cancer"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-56721-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-56721-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-56721-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T23:04:06Z","timestamp":1787699046000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-56721-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,11]]},"references-count":69,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["56721"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-56721-0","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,11]]},"assertion":[{"value":"23 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 June 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":"Declarations"}}],"article-number":"26727"}}