{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T21:55:30Z","timestamp":1781646930177,"version":"3.54.5"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"FH Joanneum - University of Applied Sciences"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Med Syst"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>In the European Union, all medications must include a paper-based medication leaflet providing essential information. However, challenges with paper leaflets have driven efforts toward digitization and standardization. This paper presents an automated extraction, digitization, and standardization pipeline for medication leaflet information, integrated into a mobile medication management application. The automated extraction is using an LLM-based question-answer pipeline. Extracted information was standardized through template-based mapping to FHIR resources, where LLM-structured content was integrated into profile-aligned templates and validated using the $validate operation. To assess pipeline performance, ten randomly selected medication leaflets were evaluated, with 36 extracted fields per leaflet scored binary for correctness, completeness, and format adherence. Errors were categorized into four types: assignment errors (separating coherent information), missing information, interpretation errors (handling ambiguous content), and false information (hallucination). Mean scores were calculated per question set to identify extraction patterns. Fields with clearly delimited information\u2014such as indications, excipient ingredients, and dose form\u2014achieved mean scores of 0.9 or higher, with 20 of 36 fields demonstrating perfect accuracy. However, complex nested sections showed substantially lower performance: precautions scored 0.20 (predominantly assignment errors), interactions 0.30 (assignment errors), and undesirable effects 0.40 (primarily missing information). These recurring errors indicate the pipeline requires refinement for heterogeneous structural patterns in nested information. Structural inconsistencies in information hierarchies most significantly impacted extraction accuracy for these clinical use cases. By addressing these challenges, this approach opens new pathways in healthcare information management for mobile health developers and healthcare IT professionals. The mobile application could potentially be used by patients taking different medications and aims to improve medication literacy and accessibility. This work combines information extraction and standardization processes, laying potential groundwork for extending the approach to other healthcare areas. Practical benefits include enhanced searchability, multi-system interoperability, and improved patient access to structured medication information through mobile applications.<\/jats:p>","DOI":"10.1007\/s10916-026-02370-9","type":"journal-article","created":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T01:31:26Z","timestamp":1775007086000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Integrating Medication Leaflets Utilizing FHIR and an LLM-Based Question-Answer Pipeline in a Mobile Application"],"prefix":"10.1007","volume":"50","author":[{"given":"Katharina","family":"Kirchsteiger","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lisa","family":"Heiler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Markus","family":"B\u00f6denler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sten","family":"Hanke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,1]]},"reference":[{"key":"2370_CR1","doi-asserted-by":"crossref","unstructured":"N. Lopes, C. Rodrigues, and E. Pegado, \u2018Medication literacy and its social contextuality\u2019, Health (London), vol. 28, no. 6, pp. 858\u2013876, Nov. 2024.","DOI":"10.1177\/13634593231211520"},{"key":"2370_CR2","doi-asserted-by":"crossref","unstructured":"A. Pouliot, R. Vaillancourt, D. Stacey, and P. Suter, \u2018Defining and identifying concepts of medication literacy: An international perspective\u2019, Research in Social and Administrative Pharmacy, vol. 14, no. 9, pp. 797\u2013804, Sep. 2018.","DOI":"10.1016\/j.sapharm.2017.11.005"},{"key":"2370_CR3","doi-asserted-by":"crossref","unstructured":"C. Pires, M. Vig\u00e1rio, and A. Cavaco, \u2018Readability of medicinal package leaflets: A systematic review\u2019, Revista de Saude Publica, vol. 49, 2015.","DOI":"10.1590\/S0034-8910.2015049005559"},{"key":"2370_CR4","doi-asserted-by":"crossref","unstructured":"H. P. Maat and L. Lentz, \u2018Improving the usability of patient information leaflets\u2019, Patient Education and Counseling, vol. 80, no. 1, pp. 113\u2013119, Jul. 2010.","DOI":"10.1016\/j.pec.2009.09.030"},{"key":"2370_CR5","doi-asserted-by":"crossref","unstructured":"C. Skogman-Lindqvist, O. Lapatto-Reiniluoto, M. Sirvi\u00f6, and M. Siv\u00e9n, \u2018Benefits and challenges of electronic package leaflet (ePL) - review of ePL pilots in hospital settings in Europe\u2019, European Journal of Pharmaceutical Sciences, vol. 191, p. 106605, Dec. 2023.","DOI":"10.1016\/j.ejps.2023.106605"},{"key":"2370_CR6","unstructured":"EMA, \u2018Electronic product information (ePI)\u2019. n.d. [Online]. Available: https:\/\/www.ema.europa.eu\/en\/human-regulatory-overview\/marketing-authorisation\/product-information-requirements\/electronic-product-information-epi#eu-epi-common-standard-14451"},{"key":"2370_CR7","doi-asserted-by":"publisher","unstructured":"D. Bender and K. Sartipi, \u2018HL7 FHIR: An Agile and RESTful approach to healthcare information exchange\u2019, in Proceedings of the 26th IEEE International Symposium on Computer-Based Medical Systems, Porto, Portugal: IEEE, Jun. 2013, pp. 326\u2013331. doi: https:\/\/doi.org\/10.1109\/CBMS.2013.6627810.","DOI":"10.1109\/CBMS.2013.6627810"},{"key":"2370_CR8","unstructured":"M. D. Wilkinson et al., \u2018Comment: The FAIR Guiding Principles for scientific data management and stewardship\u2019, Scientific Data, vol. 3, p. 160018, Mar. 2016."},{"key":"2370_CR9","doi-asserted-by":"publisher","DOI":"10.3233\/SHTI240668","volume-title":"Studies in Health Technology and Informatics","author":"A Ni\u0163ulescu","year":"2024","unstructured":"A. Ni\u0163ulescu and L. Stoicu-Tivadar, \u2018Data Standardization in the Medical Field Through FHIR and FAIR Implementation: A Systematic Review\u2019, in Studies in Health Technology and Informatics, J. Mantas, A. Hasman, G. Demiris, K. Saranto, M. Marschollek, T. N. Arvanitis, I. Ognjanovi\u0107, A. Benis, P. Gallos, E. Zoulias, and E. Andrikopoulou, Eds, IOS Press, 2024. doi: https:\/\/doi.org\/10.3233\/SHTI240668."},{"key":"2370_CR10","doi-asserted-by":"crossref","unstructured":"N. Pimenta, A. Chaves, R. Sousa, A. Abelha, and H. Peixoto, \u2018Interoperability of Clinical Data through FHIR: A review\u2019, Procedia Computer Science, vol. 220, pp. 856\u2013861, Jan. 2023.","DOI":"10.1016\/j.procs.2023.03.115"},{"key":"2370_CR11","doi-asserted-by":"crossref","unstructured":"C. N. Vorisek et al., \u2018Fast Healthcare Interoperability Resources (FHIR) for Interoperability in Health Research: Systematic Review.\u2019, JMIR Medical Informatics, vol. 10, no. 7, p. e35724, Jul. 2022.","DOI":"10.2196\/35724"},{"key":"2370_CR12","doi-asserted-by":"publisher","first-page":"100511","DOI":"10.1016\/j.cosrev.2022.100511","volume":"46","author":"I Li","year":"2022","unstructured":"I. Li et al., \u2018Neural Natural Language Processing for unstructured data in electronic health records: A review\u2019, Computer Science Review, vol. 46, p. 100511, 2022.","journal-title":"Computer Science Review"},{"key":"2370_CR13","doi-asserted-by":"crossref","unstructured":"B. Adamson et al., \u2018Approach to machine learning for extraction of real-world data variables from electronic health records\u2019, Frontiers in Pharmacology, vol. 14, 2023.","DOI":"10.3389\/fphar.2023.1180962"},{"key":"2370_CR14","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1016\/j.ijmedinf.2017.12.024","volume":"111","author":"N Afzal","year":"2018","unstructured":"N. Afzal et al., \u2018Natural language processing of clinical notes for identification of critical limb ischemia\u2019, International Journal of Medical Informatics, vol. 111, pp. 83\u201389, 2018.","journal-title":"International Journal of Medical Informatics"},{"key":"2370_CR15","doi-asserted-by":"crossref","unstructured":"E. Hossain et al., \u2018Natural Language Processing in Electronic Health Records in relation to healthcare decision-making: A systematic review\u2019, vol. 155. p. 106649, 2023.","DOI":"10.1016\/j.compbiomed.2023.106649"},{"key":"2370_CR16","doi-asserted-by":"crossref","unstructured":"K. Singhal et al., \u2018Large language models encode clinical knowledge\u2019, Nature, vol. 620, pp. 172\u2013180, Aug. 2023.","DOI":"10.1038\/s41586-023-06291-2"},{"key":"2370_CR17","doi-asserted-by":"crossref","unstructured":"V. Sciannameo et al., \u2018Information extraction from medical case reports using OpenAI InstructGPT\u2019, Computer Methods and Programs in Biomedicine, vol. 255, p. 108326, 2024.","DOI":"10.1016\/j.cmpb.2024.108326"},{"key":"2370_CR18","doi-asserted-by":"publisher","first-page":"1418","DOI":"10.1038\/s41467-024-45563-x","volume":"15","author":"J Dagdelen","year":"2024","unstructured":"J. Dagdelen et al., \u2018Structured information extraction from scientific text with large language models\u2019, Nature Communications, vol. 15, p. 1418, 2024.","journal-title":"Nature Communications"},{"key":"2370_CR19","doi-asserted-by":"publisher","DOI":"10.3233\/SHTI240524","volume-title":"Studies in Health Technology and Informatics","author":"L Heiler","year":"2024","unstructured":"L. Heiler, K. Kirchsteiger, S. Hartl, O. Perkics, S. Hanke, and M. B\u00f6denler, \u2018Integrating AI-Generated Summaries of Medication Leaflets into a Mobile Application for Medication Management\u2019, in Studies in Health Technology and Informatics, J. Mantas, A. Hasman, G. Demiris, K. Saranto, M. Marschollek, T. N. Arvanitis, I. Ognjanovi\u0107, A. Benis, P. Gallos, E. Zoulias, and E. Andrikopoulou, Eds, IOS Press, 2024. doi: https:\/\/doi.org\/10.3233\/SHTI240524."},{"key":"2370_CR20","unstructured":"beda.software, fhirpy. [Online]. Available: https:\/\/pypi.org\/project\/fhirpy\/1.4.2\/"},{"key":"2370_CR21","unstructured":"Nazrul Islam, fhir.resources. (Dec. 14, 2023). [Online]. Available: https:\/\/pypi.org\/project\/fhir.resources\/7.1.0\/"},{"key":"2370_CR22","unstructured":"fhirfli.dev, fhir. (Feb. 13, 2024). Dart\/Flutter. [Online]. Available: https:\/\/pub.dev\/packages\/fhir\/versions\/0.12.0"},{"key":"2370_CR23","unstructured":"HL7 International, HL7 FHIR IG Publisher. (2023). [Online]. Available: https:\/\/github.com\/HL7\/fhir-ig-publisher"},{"key":"2370_CR24","unstructured":"OpenAI, \u2018Models\u2019. [Online]. Available: https:\/\/platform.openai.com\/docs\/models"},{"key":"2370_CR25","doi-asserted-by":"publisher","unstructured":"Y. Li, B. Dong, F. Guerin, and C. Lin, \u2018Compressing Context to Enhance Inference Efficiency of Large Language Models\u2019, in Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, Singapore: Association for Computational Linguistics, 2023, pp. 6342\u20136353. doi: https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.391.","DOI":"10.18653\/v1\/2023.emnlp-main.391"},{"key":"2370_CR26","unstructured":"P. Lewis et al., \u2018Retrieval-augmented generation for knowledge-intensive NLP tasks\u2019, in NIPS\u201920: Proceedings of the 34th International Conference on Neural Information Processing Systems, Red Hook, NY, USA: Curran Associates Inc., Dec. 2020. [Online]. Available: https:\/\/arxiv.org\/abs\/2005.11401"},{"key":"2370_CR27","unstructured":"OpenAI, \u2018Prompt engineering\u2019. Accessed: Oct. 03, 2025. [Online]. Available: https:\/\/platform.openai.com\/docs\/guides\/prompt-engineering"}],"container-title":["Journal of Medical Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10916-026-02370-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10916-026-02370-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10916-026-02370-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T21:17:02Z","timestamp":1781644622000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10916-026-02370-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,1]]},"references-count":27,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2370"],"URL":"https:\/\/doi.org\/10.1007\/s10916-026-02370-9","relation":{},"ISSN":["1573-689X"],"issn-type":[{"value":"1573-689X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,1]]},"assertion":[{"value":"12 November 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics Approval and Consent to Participate"}},{"value":"The authors give the full consent for the publication to be published in the Journal of Medical Systems.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for Publication"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Clinical Trial Number"}},{"value":"The authors declare no competing interests.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}}],"article-number":"43"}}