{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T23:35:13Z","timestamp":1776900913715,"version":"3.51.2"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032167071","type":"print"},{"value":"9783032167088","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-16708-8_19","type":"book-chapter","created":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T22:37:09Z","timestamp":1776897429000},"page":"231-242","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Generating Patient Cohorts from\u00a0Electronic Health Records Using Two-Step Retrieval-Augmented Text-to-SQL Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2978-6305","authenticated-orcid":false,"given":"Angelo","family":"Ziletti","sequence":"first","affiliation":[]},{"given":"Leonardo","family":"D\u2019Ambrosi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,4,1]]},"reference":[{"key":"19_CR1","unstructured":"Anthropic AI: Model card for claude 3 models. https:\/\/docs.anthropic.com\/en\/docs\/resources\/model-card (2024). Accessed Feb 15 2024"},{"key":"19_CR2","first-page":"48","volume":"2017","author":"JM Banda","year":"2017","unstructured":"Banda, J.M., Halpern, Y., Sontag, D., Shah, N.H.: Electronic phenotyping with APHRODITE and the Observational Health Sciences and Informatics (OHDSI) data network. AMIA Joint Summits Transl. Sci. Proc. 2017, 48\u201357 (2017)","journal-title":"AMIA Joint Summits Transl. Sci. Proc."},{"key":"19_CR3","doi-asserted-by":"publisher","unstructured":"Casey, J.A., Schwartz, B.S., Stewart, W.F., Adler, N.E.: Using electronic health records for population health research: a review of methods and applications. Ann. Rev. Public Health 37(Volume 37, 2016), 61\u201381 (2016). https:\/\/doi.org\/10.1146\/annurev-publhealth-032315-021353, https:\/\/www.annualreviews.org\/content\/journals\/10.1146\/annurev-publhealth-032315-021353","DOI":"10.1146\/annurev-publhealth-032315-021353"},{"key":"19_CR4","unstructured":"Chang, S., Fosler-Lussier, E.: How to prompt LLMs for text-to-SQL: a study in zero-shot, single-domain, and cross-domain settings (2023)"},{"key":"19_CR5","doi-asserted-by":"publisher","unstructured":"Chang, S., Fosler-Lussier, E.: Selective demonstrations for cross-domain text-to-SQL. In: Bouamor, H., Pino, J., Bali, K. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2023, pp. 14174\u201314189. Association for Computational Linguistics, Singapore (Dec 2023). https:\/\/doi.org\/10.18653\/v1\/2023.findings-emnlp.944, https:\/\/aclanthology.org\/2023.findings-emnlp.944","DOI":"10.18653\/v1\/2023.findings-emnlp.944"},{"key":"19_CR6","doi-asserted-by":"publisher","unstructured":"Dobbins, N.J., et al.: Leafai: query generator for clinical cohort discovery rivaling a human programmer. J. Am. Med. Inform. Assoc. 30(12), 1954\u20131964 (08 2023). https:\/\/doi.org\/10.1093\/jamia\/ocad149","DOI":"10.1093\/jamia\/ocad149"},{"key":"19_CR7","unstructured":"EMA: HMA-EMA catalogues of real-world data sources and studies (2024). https:\/\/catalogues.ema.europa.eu\/. Accessed 21 Feb 2026 11:56:56"},{"key":"19_CR8","doi-asserted-by":"crossref","unstructured":"Gao, D., Wang, H., Li, Y., Sun, X., Qian, Y., Ding, B., Zhou, J.: Text-to-SQL empowered by large language models: a benchmark evaluation (2023)","DOI":"10.14778\/3641204.3641221"},{"key":"19_CR9","unstructured":"Gao, Y., et al.: A preview of xiyan-SQL: a multi-generator ensemble framework for text-to-SQL (2025). https:\/\/arxiv.org\/abs\/2411.08599"},{"key":"19_CR10","unstructured":"Gemini Team: Gemini: A family of highly capable multimodal models. Tech. rep., Google (12 2023). https:\/\/storage.googleapis.com\/deepmind-media\/gemini_1_report.pdf. Accessed Feb 15 2024"},{"key":"19_CR11","unstructured":"Grattafiori, A., et al.: The llama 3 herd of models (2024). https:\/\/arxiv.org\/abs\/2407.21783"},{"key":"19_CR12","unstructured":"Guo, D., et al.: Deepseek-r1: Incentivizing reasoning capability in LLMs via reinforcement learning (2025). https:\/\/arxiv.org\/abs\/2501.12948"},{"key":"19_CR13","doi-asserted-by":"publisher","unstructured":"Hripcsak, G., et al.: Facilitating phenotype transfer using a common data model. J. Biomed. Inform. 96, 103253 (2019). https:\/\/doi.org\/10.1016\/j.jbi.2019.103253, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1532046419301728","DOI":"10.1016\/j.jbi.2019.103253"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Lee, G., et al.: EHRSQL: A practical text-to-SQL benchmark for electronic health records. In: Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., Oh, A. (eds.) Advances in Neural Information Processing Systems. vol. 35, pp. 15589\u201315601. Curran Associates, Inc. (2022)","DOI":"10.52202\/068431-1134"},{"key":"19_CR15","doi-asserted-by":"publisher","unstructured":"Limsopatham, N., Collier, N.: Normalising medical concepts in social media texts by learning semantic representation. In: Erk, K., Smith, N.A. (eds.) Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1014\u20131023. Association for Computational Linguistics, Berlin, Germany (Aug 2016). https:\/\/doi.org\/10.18653\/v1\/P16-1096, https:\/\/aclanthology.org\/P16-1096","DOI":"10.18653\/v1\/P16-1096"},{"key":"19_CR16","unstructured":"Melnichenko, O.: Designing multi-step cohort creation flow for biomedical datasets. Microsoft Technical Community Blog (2023). https:\/\/techcommunity.microsoft.com\/blog\/healthcareandlifesciencesblog\/designing-multi-step-cohort-creation-flow-for-biomedical-datasets\/3964454"},{"key":"19_CR17","doi-asserted-by":"publisher","unstructured":"Nan, L., et al.: Enhancing text-to-SQL capabilities of large language models: a study on prompt design strategies. In: Bouamor, H., Pino, J., Bali, K. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2023, pp. 14935\u201314956. Association for Computational Linguistics, Singapore (Dec 2023). https:\/\/doi.org\/10.18653\/v1\/2023.findings-emnlp.996, https:\/\/aclanthology.org\/2023.findings-emnlp.996","DOI":"10.18653\/v1\/2023.findings-emnlp.996"},{"key":"19_CR18","unstructured":"OHDSI Collaborative: The book of OHDSI. In: The Book of OHDSI, chap. 10. Observational Health Data Sciences and Informatics (2021). http:\/\/book.ohdsi.org"},{"key":"19_CR19","unstructured":"OMOP-CDM: OMOP CDM common data model. https:\/\/ohdsi.github.io\/CommonDataModel\/ (2023). Accessed Jan 23 2024"},{"key":"19_CR20","unstructured":"OpenAI: Gpt-4 technical report (2023)"},{"key":"19_CR21","unstructured":"OpenAI: Learning to reason with LLMs (September 2024). https:\/\/openai.com\/index\/learning-to-reason-with-llms\/. Accessed Sept 2024"},{"key":"19_CR22","doi-asserted-by":"publisher","unstructured":"Park, J., et al.: Criteria2query 3.0: Leveraging generative large language models for clinical trial eligibility query generation. J. Biomed. Inform. 154, 104649 (2024). https:\/\/doi.org\/10.1016\/j.jbi.2024.104649, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1532046424000674","DOI":"10.1016\/j.jbi.2024.104649"},{"key":"19_CR23","doi-asserted-by":"publisher","unstructured":"Portelli, B., Scaboro, S., Santus, E., Sedghamiz, H., Chersoni, E., Serra, G.: Generalizing over long tail concepts for medical term normalization. In: Goldberg, Y., Kozareva, Z., Zhang, Y. (eds.) Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 8580\u20138591. Association for Computational Linguistics, Abu Dhabi, United Arab Emirates (Dec 2022). https:\/\/doi.org\/10.18653\/v1\/2022.emnlp-main.588, https:\/\/aclanthology.org\/2022.emnlp-main.588","DOI":"10.18653\/v1\/2022.emnlp-main.588"},{"key":"19_CR24","doi-asserted-by":"crossref","unstructured":"Pourreza, M., Rafiei, D.: DIN-SQL: decomposed in-context learning of text-to-SQL with self-correction. In: Thirty-seventh Conference on Neural Information Processing Systems (2023).https:\/\/openreview.net\/forum?id=p53QDxSIc5","DOI":"10.52202\/075280-1577"},{"key":"19_CR25","unstructured":"Privitera, S., Hartenstein, A.: Phenex: Automatic phenotype extractor. https:\/\/github.com\/Bayer-Group\/PhenEx (2024). Accessed 21 Feb 2026 11:56:56"},{"key":"19_CR26","doi-asserted-by":"publisher","unstructured":"Raghavan, P., Liang, J.J., Mahajan, D., Chandra, R., Szolovits, P.: emrKBQA: a clinical knowledge-base question answering dataset. In: Demner-Fushman, D., Cohen, K.B., Ananiadou, S., Tsujii, J. (eds.) Proceedings of the 20th Workshop on Biomedical Language Processing, pp. 64\u201373. Association for Computational Linguistics, Online (Jun 2021). https:\/\/doi.org\/10.18653\/v1\/2021.bionlp-1.7, https:\/\/aclanthology.org\/2021.bionlp-1.7","DOI":"10.18653\/v1\/2021.bionlp-1.7"},{"key":"19_CR27","unstructured":"Rajkumar, N., Li, R., Bahdanau, D.: Evaluating the text-to-SQL capabilities of large language models. ArXiv abs\/2204.00498 (2022). https:\/\/api.semanticscholar.org\/CorpusID:247922681"},{"key":"19_CR28","doi-asserted-by":"publisher","unstructured":"Reich, C., et al.: OHDSI Standardized Vocabularies\u2013a large-scale centralized reference ontology for international data harmonization. J. Am. Med. Inform. Assoc. ocad247 (01 2024). https:\/\/doi.org\/10.1093\/jamia\/ocad247, https:\/\/doi.org\/10.1093\/jamia\/ocad247","DOI":"10.1093\/jamia\/ocad247"},{"key":"19_CR29","doi-asserted-by":"publisher","unstructured":"Sherman, R.E., et al.: Real-world evidence \u2013 what is it and what can it tell us? N. Engl. J. Med. 375(23), 2293\u20132297 (2016). https:\/\/doi.org\/10.1056\/NEJMsb1609216, https:\/\/www.nejm.org\/doi\/full\/10.1056\/NEJMsb1609216","DOI":"10.1056\/NEJMsb1609216"},{"key":"19_CR30","unstructured":"SynPUF: Medicare claims synthetic public use files (synpufs). https:\/\/www.cms.gov\/data-research\/statistics-trends-and-reports\/medicare-claims-synthetic-public-use-files (2010). Accessed 23 Jan 2024"},{"key":"19_CR31","unstructured":"Tarbell, R., Choo, K.K.R., Dietrich, G., Rios, A.: Towards understanding the generalization of medical text-to-SQL models and datasets. AMIA ... Annual Symposium proceedings. AMIA Symposium 2023, 669\u2013678 (2023). https:\/\/api.semanticscholar.org\/CorpusID:257687830"},{"key":"19_CR32","unstructured":"U.S. FDA: Real-world data: Assessing electronic health records and medical claims data to support regulatory decision-making for drug and biological products. Guidance for Industry FDA-2020-D-2307, U.S. Food and Drug Administration (July 2024). https:\/\/www.fda.gov\/regulatory-information\/search-fda-guidance-documents\/real-world-data-assessing-electronic-health-records-and-medical-claims-data-support-regulatory, final Level 1 Guidance"},{"key":"19_CR33","doi-asserted-by":"publisher","unstructured":"Wang, P., Shi, T., Reddy, C.K.: Text-to-SQL generation for question answering on electronic medical records. In: Proceedings of The Web Conference 2020, pp. 350\u2013361. WWW \u201920, Association for Computing Machinery, New York, NY, USA (2020). https:\/\/doi.org\/10.1145\/3366423.3380120","DOI":"10.1145\/3366423.3380120"},{"key":"19_CR34","doi-asserted-by":"publisher","unstructured":"Wang, S.V., et al.: Start-RWE: structured template for planning and reporting on the implementation of real world evidence studies. BMJ 372 (2021). https:\/\/doi.org\/10.1136\/bmj.m4856, https:\/\/www.bmj.com\/content\/372\/bmj.m4856","DOI":"10.1136\/bmj.m4856"},{"key":"19_CR35","unstructured":"Wong, C., et al.: Scaling clinical trial matching using large language models: a case study in oncology. In: Deshpande, K., Fiterau, M., Joshi, S., Lipton, Z., Ranganath, R., Urteaga, I., Yeung, S. (eds.) Proceedings of the 8th Machine Learning for Healthcare Conference. Proceedings of Machine Learning Research, vol. 219, pp. 846\u2013862. PMLR (11\u201312 Aug 2023). https:\/\/proceedings.mlr.press\/v219\/wong23a.html"},{"key":"19_CR36","doi-asserted-by":"publisher","unstructured":"Yan, C., et al.: Large language models facilitate the generation of electronic health record phenotyping algorithms. J. Am. Med. Inform. Assoc. 31(9), 1994\u20132001 (04 2024). https:\/\/doi.org\/10.1093\/jamia\/ocae072, https:\/\/doi.org\/10.1093\/jamia\/ocae072","DOI":"10.1093\/jamia\/ocae072"},{"key":"19_CR37","doi-asserted-by":"publisher","unstructured":"Yuan, C., et al.: Criteria2Query: a natural language interface to clinical databases for cohort definition. J. Am Med. Inform. Assoc. 26(4), 294\u2013305 (02 2019). https:\/\/doi.org\/10.1093\/jamia\/ocy178","DOI":"10.1093\/jamia\/ocy178"},{"key":"19_CR38","doi-asserted-by":"publisher","unstructured":"Zhang, H., Cao, R., Chen, L., Xu, H., Yu, K.: ACT-SQL: In-context learning for text-to-SQL with automatically-generated chain-of-thought. In: Bouamor, H., Pino, J., Bali, K. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2023, pp. 3501\u20133532. Association for Computational Linguistics, Singapore (Dec 2023). https:\/\/doi.org\/10.18653\/v1\/2023.findings-emnlp.227, https:\/\/aclanthology.org\/2023.findings-emnlp.227","DOI":"10.18653\/v1\/2023.findings-emnlp.227"},{"key":"19_CR39","unstructured":"Zhang, P., Xiao, S., Liu, Z., Dou, Z., Nie, J.Y.: Retrieve anything to augment large language models (2023)"},{"key":"19_CR40","doi-asserted-by":"publisher","unstructured":"Zhang, S., et al.: Knowledge-rich self-supervision for biomedical entity linking. In: Goldberg, Y., Kozareva, Z., Zhang, Y. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2022, pp. 868\u2013880. Association for Computational Linguistics, Abu Dhabi, United Arab Emirates (Dec 2022). https:\/\/doi.org\/10.18653\/v1\/2022.findings-emnlp.61, https:\/\/aclanthology.org\/2022.findings-emnlp.61","DOI":"10.18653\/v1\/2022.findings-emnlp.61"},{"key":"19_CR41","doi-asserted-by":"publisher","unstructured":"Ziletti, A., Akbik, A., Berns, C., Herold, T., Legler, M., Viell, M.: Medical coding with biomedical transformer ensembles and zero\/few-shot learning. In: Loukina, A., Gangadharaiah, R., Min, B. (eds.) Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track, pp. 176\u2013187. Association for Computational Linguistics, Hybrid: Seattle, Washington + Online (Jul 2022). https:\/\/doi.org\/10.18653\/v1\/2022.naacl-industry.21, https:\/\/aclanthology.org\/2022.naacl-industry.21","DOI":"10.18653\/v1\/2022.naacl-industry.21"},{"key":"19_CR42","doi-asserted-by":"publisher","unstructured":"Ziletti, A., D\u2019Ambrosi, L.: Retrieval augmented text-to-SQL generation for epidemiological question answering using electronic health records. In: Naumann, T., Ben Abacha, A., Bethard, S., Roberts, K., Bitterman, D. (eds.) Proceedings of the 6th Clinical Natural Language Processing Workshop, pp. 47\u201353. Association for Computational Linguistics, Mexico City, Mexico (Jun 2024). https:\/\/doi.org\/10.18653\/v1\/2024.clinicalnlp-1.4, https:\/\/aclanthology.org\/2024.clinicalnlp-1.4","DOI":"10.18653\/v1\/2024.clinicalnlp-1.4"}],"container-title":["Communications in Computer and Information Science","Artificial Intelligence for Healthcare, and Hybrid Models for Coupling Deductive and Inductive Reasoning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-16708-8_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T22:37:13Z","timestamp":1776897433000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-16708-8_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032167071","9783032167088"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-16708-8_19","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"1 April 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"HC_AIxIA_HYDRA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Joint Workshop on Artificial Intelligence for Healthcare, and Hybrid Models for Coupling Deductive and Inductive Reasoning","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bologna","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"hc_aixia_hydra2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/sites.google.com\/unical.it\/hcaixia-hydra-2025\/home","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}