{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T19:04:17Z","timestamp":1782846257908,"version":"3.54.5"},"reference-count":65,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Clinical data warehouses store large volumes of unstructured text containing valuable information about patients\u2019 medical status. Traditional extraction systems based on named entity recognition (NER) identify medical terms but often fail to capture the contextual cues needed for accurate interpretation. Existing approaches to context-aware extraction differ in their reliance on expert annotation, computational power, and lexical resources, leading to uneven feasibility across institutions. Combined with heterogeneity in documentation practices and data-sharing restrictions, these limitations hinder the scalability and reuse of trained models. There is thus a need for practical frameworks that can be deployed and adapted locally within medical institutions.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n \n This study aimed to introduce the Medical Status Extraction Pipeline (MSEP)\n ,<\/jats:bold>\n a methodological framework that extracts patients\u2019 medical status from clinical narratives through sentence classification and supports the local deployment of hybrid extractors, illustrated through an institutional case study.\n <\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n \n MSEP extracts medical status by classifying sentences into predefined categories (presence\n ,<\/jats:italic>\n absence, or unknown) for each targeted condition. The pipeline combines modules for data selection, expert annotation, and model development, with parameters customizable to different settings. It was applied within our institutional environment on 6 conditions: smoking, hypertension, diabetes, heart failure, chronic obstructive pulmonary disease, and family history of cancer, using 12,119 manually annotated sentences from the eHOP Clinical Data Warehouse (Rennes University Hospital). Three types of extractors were compared: fine-tuned CamemBERT, large language model (LLM) prompt, and a rule-based baseline, evaluated through stratified 3-fold cross-validation, measuring precision, recall, specificity, macro\n F<\/jats:italic>\n -score, balanced accuracy, as well as manual annotation time and model inference speed.\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n Among the tested approaches, the CamemBERT-based extractor achieved the best overall performance, with macro\n F<\/jats:italic>\n -scores above 0.94 for 5 of the 6 medical conditions. The study also highlights that when a medical status is very sparsely represented in the training data, rule-based extractors can outperform learned models (average macro\n F<\/jats:italic>\n -score 0.94 vs 0.73 for family history of cancer). This shows the pragmatic value of choosing the extraction method according to data availability. Manual annotation time per sentence ranged from 1.2 to 2.9 seconds within the pipeline (2.23 to 4.25 seconds for informative sentences), compared with 7.8 to 16.5 seconds for named entity recognition\u2013based systems. In our institutional experiments, the minimum time to complete all pipeline modules, from dataset construction to final extractor refinement, was 8 hours.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n In our institutional case study, MSEP enabled rapid construction of datasets and extractors across multiple clinical conditions while reducing the effort required for local development. Its modular and configurable design allowed the adoption of hybrid extraction approaches and adaptation to different resource settings. These features highlight MSEP\u2019s value as a research tool and upstream component that facilitates local deployment of clinical information extraction workflows.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/77409","type":"journal-article","created":{"date-parts":[[2025,12,27]],"date-time":"2025-12-27T18:25:07Z","timestamp":1766859907000},"page":"e77409-e77409","source":"Crossref","is-referenced-by-count":0,"title":["A Sentence Classification\u2013Based Medical Status Extraction Pipeline for Electronic Health Records: Institutional Case Study"],"prefix":"10.2196","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3232-8177","authenticated-orcid":false,"given":"Chuanming","family":"Dong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6055-6935","authenticated-orcid":false,"given":"Boris","family":"Delange","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8750-0329","authenticated-orcid":false,"given":"Alex","family":"Poiron","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4741-9820","authenticated-orcid":false,"given":"Mohamed","family":"El Azzouzi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7459-1527","authenticated-orcid":false,"given":"Cl\u00e9ment","family":"Fran\u00e7ois","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3637-6558","authenticated-orcid":false,"given":"Guillaume","family":"Bouzill\u00e9","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6943-3937","authenticated-orcid":false,"given":"Marc","family":"Cuggia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7847-0916","authenticated-orcid":false,"given":"Sandie","family":"Cabon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,3,26]]},"reference":[{"issue":"2","key":"R1","doi-asserted-by":"publisher","first-page":"8","DOI":"10.47912\/jscdm.320","article-title":"Clinical data warehousing: a scoping review","volume":"4","author":"Wang","journal-title":"J Soc Clin Data Manag"},{"key":"R2","doi-asserted-by":"publisher","DOI":"10.2196\/42477","article-title":"Applying natural language processing to textual data from clinical data warehouses: systematic review","volume":"11","author":"Bazoge","journal-title":"JMIR Med Inform"},{"key":"R3","doi-asserted-by":"publisher","DOI":"10.2196\/56946","article-title":"Combining a risk factor score designed from electronic health records with a digital cytology image scoring system to improve bladder cancer detection: proof-of-concept study","volume":"27","author":"Cabon","journal-title":"J Med Internet Res"},{"issue":"1","key":"R4","doi-asserted-by":"publisher","DOI":"10.1093\/ehjopen\/oead133","article-title":"Phenotyping of heart failure with preserved ejection faction using electronic health records and echocardiography","volume":"4","author":"Pierre-Jean","journal-title":"Eur Heart J Open"},{"issue":"4","key":"R5","doi-asserted-by":"publisher","first-page":"1060","DOI":"10.1111\/jgs.18786","article-title":"Safety of subcutaneous versus intravenous ceftriaxone administration in older patients: a retrospective study","volume":"72","author":"Pardo","journal-title":"J Am Geriatr Soc"},{"issue":"1","key":"R6","doi-asserted-by":"publisher","DOI":"10.2196\/24008","article-title":"Family history extraction from synthetic clinical narratives using natural language processing: overview and evaluation of a challenge data set and solutions for the 2019 national NLP clinical challenges (n2c2)\/open health natural language processing (OHNLP) competition","volume":"9","author":"Shen","journal-title":"JMIR Med Inform"},{"issue":"3","key":"R7","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1093\/jamia\/ocz207","article-title":"medExtractR: a targeted, customizable approach to medication extraction from electronic health records","volume":"27","author":"Weeks","journal-title":"J Am Med Inform Assoc"},{"key":"R8","volume":"2012","author":"Lependu","journal-title":"AMIA Jt Summits Transl Sci Proc"},{"issue":"1","key":"R9","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1016\/j.jbi.2011.10.007","article-title":"Enhancing clinical concept extraction with distributional semantics","volume":"45","author":"Jonnalagadda","journal-title":"J Biomed Inform"},{"key":"R10","unstructured":"Lerner I Jouffroy J Burgun A . Learning the grammar of drug prescription: recurrent neural network grammars for medication information extraction in clinical texts. arXiv. Preprint posted online on Apr 24, 2020. [doi: 10.48550\/arXiv.2004.11622]"},{"issue":"1","key":"R11","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1055\/s-0040-1702001","article-title":"Medical information extraction in the age of deep learning","volume":"29","author":"Hahn","journal-title":"Yearb Med Inform"},{"key":"R12","doi-asserted-by":"crossref","unstructured":"Musen MA Friedman C . Semantic text parsing for patient records. In: Kulikowski CA , editor. Medical Informatics: Knowledge Management and Data Mining in Biomedicine. Springer; 2006:423-448. [doi: 10.1007\/0-387-25739-X_15] ISBN: 9780387257396","DOI":"10.1007\/0-387-25739-X_15"},{"key":"R13","unstructured":"Oxford University Press. Medical status - oxford reference. Oxford Reference. 2011. URL: https:\/\/www.oxfordreference.com\/display\/10.1093\/oi\/ authority.20110803100146893 [Accessed 28-02-2025]"},{"issue":"11","key":"R14","doi-asserted-by":"publisher","first-page":"1297","DOI":"10.1093\/jamia\/ocz096","article-title":"Enhancing clinical concept extraction with contextual embeddings","volume":"26","author":"Si","journal-title":"J Am Med Inform Assoc"},{"key":"R15","doi-asserted-by":"crossref","unstructured":"Bhatia P Celikkaya B Khalilia M . Joint entity extraction and assertion detection for clinical text. Presented at: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Jul 28 to Aug 2, 2019:Association for Computational Linguistics. 954-959; Florence, Italy. URL: https:\/\/aclanthology.org\/P19-1 [doi: 10.18653\/v1\/P19-1091]","DOI":"10.18653\/v1\/P19-1091"},{"issue":"6","key":"R16","doi-asserted-by":"publisher","first-page":"1280","DOI":"10.1093\/jamia\/ocae069","article-title":"Collaborative and privacy-enhancing workflows on a clinical data warehouse: an example developing natural language processing pipelines to detect medical conditions","volume":"31","author":"Petit-Jean","journal-title":"J Am Med Inform Assoc"},{"issue":"8","key":"R17","doi-asserted-by":"publisher","DOI":"10.2196\/20773","article-title":"Natural language processing for rapid response to emergent diseases: case study of calcium channel blockers and hypertension in the COVID-19 pandemic","volume":"22","author":"Neuraz","journal-title":"J Med Internet Res"},{"key":"R18","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2022.100511","article-title":"Neural natural language processing for unstructured data in electronic health records: a review","volume":"46","author":"Li","journal-title":"Comput Sci Rev"},{"issue":"10","key":"R19","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000347","article-title":"Challenges and best practices for digital unstructured data enrichment in health research: a systematic narrative review","volume":"2","author":"Sedlakova","journal-title":"PLOS Digit Health"},{"key":"R20","volume":"2018","author":"Wei","journal-title":"AMIA Annu Symp Proc"},{"key":"R21","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112682","article-title":"ALDANER: active learning based data augmentation for named entity recognition","volume":"305","author":"Moscato","journal-title":"Knowl Based Syst"},{"issue":"Suppl 11","key":"R22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1471-2105-9-S11-S8","article-title":"Accelerating the annotation of sparse named entities by dynamic sentence selection","volume":"9 Suppl 11","author":"Tsuruoka","journal-title":"BMC Bioinformatics"},{"key":"R23","unstructured":"Settles B Craven M Friedland L . Active learning with real annotation costs. Presented at: Proceedings of the NIPS Workshop on Cost-Sensitive Learning; Dec 13, 2008; Vancouver, BC, Canada."},{"issue":"3","key":"R24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3570328","article-title":"Deep neural network with embedding fusion for chinese named entity recognition","volume":"22","author":"Long","journal-title":"ACM Trans Asian Low-Resour Lang Inf Process"},{"key":"R25","doi-asserted-by":"crossref","unstructured":"Kalyan KS Rajasekharan A Sangeetha S . AMMUS: a survey of transformer-based pretrained models in natural language processing. arXiv. Preprint posted online on 2021. [doi: 10.48550\/arXiv.2108.05542]","DOI":"10.1016\/j.jbi.2021.103982"},{"key":"R26","doi-asserted-by":"crossref","unstructured":"Devlin J Chang MW Lee K Toutanova K . BERT: pre-training of deep bidirectional transformers for language understanding. Presented at: Proceedings of the 2019 Conference of the North; Jun 2-7, 2019; Minneapolis, MN, USA. [doi: 10.18653\/v1\/N19-1423]","DOI":"10.18653\/v1\/N19-1423"},{"key":"R27","doi-asserted-by":"crossref","unstructured":"Martin L Muller B Ortiz Su\u00e1rez PJ et al. CamemBERT: a tasty french language model. Presented at: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics; Jul 6-8, 2020; Online. [doi: 10.18653\/v1\/2020.acl-main.645]","DOI":"10.18653\/v1\/2020.acl-main.645"},{"key":"R28","doi-asserted-by":"crossref","unstructured":"Grie\u00dfhaber D Maucher J Vu NT . Fine-tuning BERT for low-resource natural language understanding via active learning. Presented at: Proceedings of the 28th International Conference on Computational Linguistics; Dec 8-13, 2020; Barcelona, Spain (Online. URL: https:\/\/www.aclweb.org\/anthology\/2020.coling-main [doi: 10.18653\/v1\/2020.coling-main.100]","DOI":"10.18653\/v1\/2020.coling-main.100"},{"key":"R29","unstructured":"OpenAI. Introducing chatgpt. OpenAI. 2022. URL: https:\/\/openai.com\/blog\/chatgpt [Accessed 28-02-2025]"},{"key":"R30","unstructured":"Mistral AI. Mistral 7B: a new paradigm for open-weight language models. Mistral AI. 2023. URL: https:\/\/mistral.ai\/news\/announcing-mistral-7b\/ [Accessed 28-02-2025]"},{"key":"R31","unstructured":"LLMs accelerate annotation for medical information extraction. Presented at: Proceedings of the 3rd Machine Learning for Health Symposium; Dec 10, 2023; New Orleans, LA, USA."},{"key":"R32","doi-asserted-by":"publisher","DOI":"10.2196\/50638","article-title":"Prompt engineering as an important emerging skill for medical professionals: tutorial","volume":"25","author":"Mesk\u00f3","journal-title":"J Med Internet Res"},{"key":"R33","unstructured":"Posada A Rueckert D Meissen F M\u00fcller P . Evaluation of language models in the medical context under resource-constrained settings. arXiv. Preprint posted online on Jun 24, 2024. [doi: 10.48550\/arXiv.2406.16611]"},{"issue":"6","key":"R34","doi-asserted-by":"publisher","first-page":"116","DOI":"10.3390\/asi7060116","article-title":"Addressing the interoperability of electronic health records: the technical and semantic interoperability, preserving privacy and security framework","volume":"7","author":"Ademola","journal-title":"ASI"},{"key":"R35","unstructured":"Hu Y Zuo X Zhou Y et al. Information extraction from clinical notes: are we ready to switch to large language models. arXiv. Preprint posted online on Nov 15, 2024. [doi: 10.48550\/arXiv.2411.10020]"},{"issue":"6","key":"R36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3636424","article-title":"A survey of generative adversarial networks for synthesizing structured electronic health records","volume":"56","author":"Ghosheh","journal-title":"ACM Comput Surv"},{"key":"R37","unstructured":"Hier DB Carrithers MD Do TS Obafemi-Ajayi T . Efficient standardization of clinical notes using large language models. arXiv. Preprint posted online on Dec 31, 2024. [doi: 10.48550\/ARXIV.2501.00644]"},{"key":"R38","doi-asserted-by":"publisher","DOI":"10.1016\/j.mlwa.2025.100683","article-title":"Benchmarking transformer embedding models for biomedical terminology standardization","volume":"21","author":"Lahiri","journal-title":"Mach Learn Appl"},{"issue":"8","key":"R39","doi-asserted-by":"publisher","first-page":"2374","DOI":"10.3390\/s25082374","article-title":"Privacy-preserving federated learning framework for multi-source electronic health records prognosis prediction","volume":"25","author":"Zhao","journal-title":"Sensors (Basel)"},{"key":"R40","unstructured":"Fowl L Geiping J Reich S et al. Decepticons: corrupted transformers breach privacy in federated learning for language models. arXiv. Preprint posted online on Jan 29, 2022. [doi: 10.48550\/ARXIV.2201.12675]"},{"issue":"1","key":"R41","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-025-02948-2","article-title":"NLP modeling recommendations for restricted data availability in clinical settings","volume":"25","author":"Villena","journal-title":"BMC Med Inform Decis Mak"},{"key":"R42","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2020.103526","article-title":"Clinical concept extraction: a methodology review","volume":"109","author":"Fu","journal-title":"J Biomed Inform"},{"issue":"7","key":"R43","doi-asserted-by":"publisher","first-page":"1451","DOI":"10.1093\/jamia\/ocae091","article-title":"Comparing natural language processing representations of coded disease sequences for prediction in electronic health records","volume":"31","author":"Beaney","journal-title":"J Am Med Inform Assoc"},{"key":"R44","doi-asserted-by":"publisher","DOI":"10.3233\/SHTI190522","article-title":"eHOP clinical data warehouse: from a prototype to the creation of an inter-regional clinical data centers network","volume":"264","author":"Madec","journal-title":"Stud Health Technol Inform"},{"issue":"15","key":"R45","doi-asserted-by":"publisher","first-page":"3064","DOI":"10.3390\/electronics14153064","article-title":"Strengths and weaknesses of LLM-based and rule-based NLP technologies and their potential synergies","volume":"14","author":"Karanikolas","journal-title":"Electronics (Basel)"},{"key":"R46","doi-asserted-by":"publisher","DOI":"10.1016\/j.redii.2023.100027","article-title":"BERT-based natural language processing analysis of French CT reports: application to the measurement of the positivity rate for pulmonary embolism","volume":"6","author":"Jupin-Delevaux","journal-title":"Res Diagn Interv Imaging"},{"issue":"3","key":"R47","doi-asserted-by":"publisher","first-page":"1953","DOI":"10.3390\/make6030096","article-title":"Assessing fine-tuned NER models with limited data in French: automating detection of new technologies, technological domains, and startup names in renewable energy","volume":"6","author":"MacLean","journal-title":"MAKE"},{"key":"R48","unstructured":"Touchent R Romary L Clergerie E . CamemBERT-bio: leveraging continual pre-training for cost-effective models on french biomedical data. arXiv. Preprint posted online on Jun 27, 2023. [doi: 10.48550\/ARXIV.2306.15550]"},{"key":"R49","doi-asserted-by":"crossref","unstructured":"Baldini I Wei D Natesan Ramamurthy K Singh M Yurochkin M . Your fairness may vary: pretrained language model fairness in toxic text classification. Presented at: Findings of the Association for Computational Linguistics; May 22-27, 2022; Dublin, Ireland. URL: https:\/\/aclanthology.org\/2022.findings-acl [doi: 10.18653\/v1\/2022.findings-acl.176]","DOI":"10.18653\/v1\/2022.findings-acl.176"},{"key":"R50","doi-asserted-by":"crossref","unstructured":"Hendrycks D Liu X Wallace E Dziedzic A Krishnan R Song D . Pretrained transformers improve out-of-distribution robustness. Presented at: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics; Jul 5-10, 2020; Online. URL: https:\/\/www.aclweb.org\/anthology\/2020.acl-main [doi: 10.18653\/v1\/2020.acl-main.244]","DOI":"10.18653\/v1\/2020.acl-main.244"},{"key":"R51","unstructured":"Jiang AQ Sablayrolles A Roux A Mensch A Savary B Bamford C et al. Mixtral of experts. arXiv. Preprint posted online on Jan 8, 2024. [doi: 10.48550\/arXiv.2401.04088]"},{"key":"R52","unstructured":"Honnibal M Montani I . SpaCy 2: natural language understanding with bloom embeddings, convolutional neural networks and incremental parsing. Sentometrics Research. 2017. URL: https:\/\/sentometrics-research.com\/publication\/72\/ [Accessed 28-02-2025]"},{"key":"R53","unstructured":"Wajsburt P Petit-Jean T Dura B Cohen A Jean C Bey R . EDS-NLP: efficient information extraction from french clinical notes. GitHub. URL: http:\/\/aphp.github.io\/edsnlp [Accessed 22-04-2025]"},{"key":"R54","unstructured":"Explosion. Prodigy. 2022. URL: https:\/\/prodi.gy\/ [Accessed 22-04-2025]"},{"issue":"3","key":"R55","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1177\/001316447303300309","article-title":"The equivalence of weighted kappa and the intraclass correlation coefficient as measures of reliability","volume":"33","author":"Fleiss","journal-title":"Educ Psychol Meas"},{"key":"R56","doi-asserted-by":"publisher","DOI":"10.3233\/SHTI240535","article-title":"How trueness of clinical decision support systems based on machine learning is assessed?","volume":"316","author":"Poiron","journal-title":"Stud Health Technol Inform"},{"issue":"4","key":"R57","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3218820","article-title":"Comparison of methods to annotate named entity corpora","volume":"17","author":"Komiya","journal-title":"ACM Trans Asian Low-Resour Lang Inf Process"},{"issue":"1","key":"R58","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1093\/bib\/bbz130","article-title":"An extensive review of tools for manual annotation of documents","volume":"22","author":"Neves","journal-title":"Brief Bioinform"},{"key":"R59","unstructured":"Galileo AI. What is NER and why it\u2019s hard to get right. Galileo AI; URL: https:\/\/www.galileo.ai\/blog\/what-is-ner-and-why-it-s-hard-to-get-right [Accessed 22-04-2025]"},{"key":"R60","unstructured":"Explosion AI. Named entity recognition. Prodigy. URL: https:\/\/prodi.gy\/docs\/named-entity-recognition [Accessed 22-04-2025]"},{"key":"R61","doi-asserted-by":"publisher","DOI":"10.2196\/59680","article-title":"Is boundary annotation necessary? evaluating boundary-free approaches to improve clinical named entity annotation efficiency: case study","volume":"12","author":"Herman Bernardim Andrade","journal-title":"JMIR Med Inform"},{"issue":"9","key":"R62","doi-asserted-by":"publisher","first-page":"1812","DOI":"10.1093\/jamia\/ocad259","article-title":"Improving large language models for clinical named entity recognition via prompt engineering","volume":"31","author":"Hu","journal-title":"J Am Med Inform Assoc"},{"key":"R63","unstructured":"Baldridge J Osborne M . Active learning and the total cost of annotation. Presented at: Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing; 2004; Barcelona, Spain."},{"key":"R64","doi-asserted-by":"crossref","unstructured":"Aggarwal U Popescu A Hudelot C . Active learning for imbalanced datasets. Presented at: 2020 IEEE Winter Conference on Applications of Computer Vision (WACV); Mar 1-5, 2020; Snowmass Village, CO, USA. [doi: 10.1109\/WACV45572.2020.9093475]","DOI":"10.1109\/WACV45572.2020.9093475"},{"key":"R65","unstructured":"Ollama. Ollama. URL: https:\/\/ollama.com\/ [Accessed 16-04-2025]"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e77409","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:09:35Z","timestamp":1782842975000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e77409"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,26]]},"references-count":65,"URL":"https:\/\/doi.org\/10.2196\/77409","relation":{},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,26]]},"article-number":"v14i2e77409"}}