{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T00:58:28Z","timestamp":1781917108150,"version":"3.54.5"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T00:00:00Z","timestamp":1750377600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T00:00:00Z","timestamp":1750377600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Fraunhofer-Institut f\u00fcr Algorithmen und Wissenschaftliches Rechnen SCAI"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Data Harmonization is an important yet time-consuming process. With the recent popularity of applications using Language Models (LMs) due to their high capabilities in text understanding, we investigated whether LMs could facilitate data harmonization for clinical use cases. To evaluate this, we created PASSIONATE, a novel Parkinson\u2019s disease (PD) variable mapping schema as a ground truth source for pairwise cohort harmonization using LLMs. Additionally, we extended our investigation using an existing Alzheimer\u2019s disease (AD) CDM. We computed text embeddings based on two language models to perform automated cohort harmonization for both AD and PD. We additionally compared the results to a baseline method using fuzzy string matching to determine the degree to which the semantic capabilities of language models can be utilized for automated cohort harmonization. We found that mappings based on text embeddings performed significantly better than those generated by fuzzy string matching, reaching an average accuracy of over 80% for almost all tested PD cohorts. When extended to a further neighborhood of possible matches, the accuracy could be improved to up to 96%. Our results suggest that language models can be used for automated harmonization with a high accuracy that can potentially be improved in the future by applying domain-trained models.<\/jats:p>","DOI":"10.1038\/s41598-025-06447-2","type":"journal-article","created":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T10:03:56Z","timestamp":1750413836000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Evaluating language model embeddings for Parkinson\u2019s disease cohort harmonization using a novel manually curated variable mapping schema"],"prefix":"10.1038","volume":"15","author":[{"given":"Yasamin","family":"Salimi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tim","family":"Adams","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mehmet Can","family":"Ay","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Helena","family":"Balabin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marc","family":"Jacobs","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin","family":"Hofmann-Apitius","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,6,20]]},"reference":[{"key":"6447_CR1","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1186\/s13195-022-01009-4","volume":"14","author":"Y Salimi","year":"2022","unstructured":"Salimi, Y. et al. ADataViewer: exploring semantically harmonized alzheimer\u2019s disease cohort datasets. Alzheimers Res. Ther. 14, 69 (2022).","journal-title":"Alzheimers Res. Ther."},{"key":"6447_CR2","doi-asserted-by":"publisher","first-page":"c214","DOI":"10.1159\/000235241","volume":"113","author":"AM Euser","year":"2009","unstructured":"Euser, A. M., Zoccali, C., Jager, K. J. & Dekker, F. W. Cohort studies: prospective versus retrospective. Nephron Clin. Pract. 113, c214\u2013c217 (2009).","journal-title":"Nephron Clin. Pract."},{"key":"6447_CR3","doi-asserted-by":"publisher","first-page":"185","DOI":"10.14283\/jpad.2023.100","volume":"11","author":"Y Salimi","year":"2024","unstructured":"Salimi, Y., Domingo-Fern\u00e1ndez, D., Hofmann-Apitius, M. & Birkenbihl, C. Data-Driven thresholding statistically biases ATN profiling across cohort datasets. J. Prev. Alzheimers Dis. 11, 185\u2013195 (2024).","journal-title":"J. Prev. Alzheimers Dis."},{"key":"6447_CR4","doi-asserted-by":"publisher","unstructured":"Stroganov, O. et al. Unpacking unstructured data: A pilot study on extracting insights from neuropathological reports of Parkinson\u2019s disease patients using large language models. Preprint at (2023). https:\/\/doi.org\/10.1101\/2023.09.12.557252","DOI":"10.1101\/2023.09.12.557252"},{"key":"6447_CR5","doi-asserted-by":"publisher","first-page":"168","DOI":"10.4258\/hir.2023.29.2.168","volume":"29","author":"GH Lee","year":"2023","unstructured":"Lee, G. H. et al. Feasibility study of federated learning on the distributed research network of OMOP common data model. Healthc. Inf. Res. 29, 168\u2013173 (2023).","journal-title":"Healthc. Inf. Res."},{"key":"6447_CR6","doi-asserted-by":"publisher","first-page":"160018","DOI":"10.1038\/sdata.2016.18","volume":"3","author":"MD Wilkinson","year":"2016","unstructured":"Wilkinson, M. D. et al. The FAIR guiding principles for scientific data management and stewardship. Sci. Data. 3, 160018 (2016).","journal-title":"Sci. Data"},{"key":"6447_CR7","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1007\/978-3-319-99713-1_4","volume-title":"Fundamentals of Clinical Data Science","author":"P Jansen","year":"2019","unstructured":"Jansen, P., van den Berg, L., van Overveld, P. & Boiten, J. W. Research data stewardship for healthcare professionals. in Fundamentals of Clinical Data Science (eds Kubben, P., Dumontier, M. & Dekker, A.) 37\u201353 (Springer International Publishing, 2019)."},{"key":"6447_CR8","doi-asserted-by":"publisher","first-page":"1409","DOI":"10.3233\/JAD-240116","volume":"99","author":"P Wegner","year":"2024","unstructured":"Wegner, P. et al. Semantic harmonization of alzheimer\u2019s disease datasets using AD-Mapper. J. Alzheimers Dis. 99, 1409\u20131423 (2024).","journal-title":"J. Alzheimers Dis."},{"key":"6447_CR9","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1007\/s12597-020-00467-4","volume":"58","author":"A Dutta","year":"2021","unstructured":"Dutta, A., Deb, T. & Pathak, S. Automated data harmonization (ADH) using artificial intelligence (AI). OPSEARCH 58, 257\u2013275 (2021).","journal-title":"OPSEARCH"},{"key":"6447_CR10","doi-asserted-by":"publisher","first-page":"3850","DOI":"10.1093\/bioinformatics\/btac375","volume":"38","author":"P Wegner","year":"2022","unstructured":"Wegner, P. et al. Integrative data semantics through a model-enabled data stewardship. Bioinformatics 38, 3850\u20133852 (2022).","journal-title":"Bioinformatics"},{"key":"6447_CR11","doi-asserted-by":"crossref","unstructured":"Pergl, R., Hooft, R., Such\u00e1nek, M., Knaisl, V. & Slifka, J. Data stewardship wizard: a tool bringing together researchers, data stewards, and data experts around data management planning. Data Sci. J. 18, 59\u201359 (2019).","DOI":"10.5334\/dsj-2019-059"},{"key":"6447_CR12","doi-asserted-by":"publisher","unstructured":"Wang, L. et al. Document-level machine translation with large language models. Preprint at (2023). https:\/\/doi.org\/10.48550\/arXiv.2304.02210","DOI":"10.48550\/arXiv.2304.02210"},{"key":"6447_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41746-023-00896-7","volume":"6","author":"L Tang","year":"2023","unstructured":"Tang, L. et al. Evaluating large Language models on medical evidence summarization. Npj Digit. Med. 6, 1\u20138 (2023).","journal-title":"Npj Digit. Med."},{"key":"6447_CR14","doi-asserted-by":"publisher","unstructured":"Van Veen, D. et al. Clinical text summarization: adapting large language models can outperform human experts. Preprint at (2023). https:\/\/doi.org\/10.48550\/arXiv.2309.07430","DOI":"10.48550\/arXiv.2309.07430"},{"key":"6447_CR15","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","volume":"620","author":"K Singhal","year":"2023","unstructured":"Singhal, K. et al. Large Language models encode clinical knowledge. Nature 620, 172\u2013180 (2023).","journal-title":"Nature"},{"key":"6447_CR16","doi-asserted-by":"publisher","first-page":"792","DOI":"10.1001\/jama.2023.14311","volume":"330","author":"E Harris","year":"2023","unstructured":"Harris, E. Large Language models answer medical questions accurately, but can\u2019t match clinicians\u2019 knowledge. JAMA 330, 792\u2013794 (2023).","journal-title":"JAMA"},{"key":"6447_CR17","doi-asserted-by":"publisher","unstructured":"Zhang, W., Deng, Y., Liu, B., Pan, S. J. & Bing, L. Sentiment analysis in the era of large language models: A reality check. Preprint at (2023). https:\/\/doi.org\/10.48550\/arXiv.2305.15005","DOI":"10.48550\/arXiv.2305.15005"},{"key":"6447_CR18","doi-asserted-by":"publisher","first-page":"605","DOI":"10.12669\/pjms.39.2.7653","volume":"39","author":"RA Khan","year":"2023","unstructured":"Khan, R. A., Jawaid, M., Khan, A. R. & Sajjad, M. ChatGPT - Reshaping medical education and clinical management. Pak J. Med. Sci. 39, 605\u2013607 (2023).","journal-title":"Pak J. Med. Sci."},{"key":"6447_CR19","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s10916-023-01925-4","volume":"47","author":"M Cascella","year":"2023","unstructured":"Cascella, M., Montomoli, J., Bellini, V. & Bignami, E. Evaluating the feasibility of ChatGPT in healthcare: an analysis of multiple clinical and research scenarios. J. Med. Syst. 47, 33 (2023).","journal-title":"J. Med. Syst."},{"key":"6447_CR20","doi-asserted-by":"publisher","first-page":"e48568","DOI":"10.2196\/48568","volume":"25","author":"J Liu","year":"2023","unstructured":"Liu, J., Wang, C. & Liu, S. Utility of ChatGPT in clinical practice. J. Med. Internet Res. 25, e48568 (2023).","journal-title":"J. Med. Internet Res."},{"key":"6447_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s43856-023-00370-1","volume":"3","author":"J Clusmann","year":"2023","unstructured":"Clusmann, J. et al. The future landscape of large Language models in medicine. Commun. Med. 3, 1\u20138 (2023).","journal-title":"Commun. Med."},{"key":"6447_CR22","doi-asserted-by":"publisher","first-page":"1237","DOI":"10.1093\/jamia\/ocad072","volume":"30","author":"S Liu","year":"2023","unstructured":"Liu, S. et al. Using AI-generated suggestions from ChatGPT to optimize clinical decision support. J. Am. Med. Inf. Assoc. JAMIA. 30, 1237\u20131245 (2023).","journal-title":"J. Am. Med. Inf. Assoc. JAMIA"},{"key":"6447_CR23","doi-asserted-by":"publisher","unstructured":"Rao, A. et al. Evaluating ChatGPT as an adjunct for radiologic decision-making. 02.02.23285399 Preprint at https:\/\/doi.org\/10.1101\/2023.02.02.23285399 (2023).","DOI":"10.1101\/2023.02.02.23285399"},{"key":"6447_CR24","unstructured":"Observational health data sciences and informatics. Usagi. (2021)."},{"key":"6447_CR25","unstructured":"Jupp, S. et al. A new ontology lookup service at EMBL-EBI. in Proceedings of SWAT4LS International Conference  2 118\u2013119 (2015)."},{"key":"6447_CR26","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1093\/jamia\/ocad247","volume":"31","author":"C Reich","year":"2024","unstructured":"Reich, C. et al. OHDSI standardized Vocabularies\u2014a large-scale centralized reference ontology for international data harmonization. J. Am. Med. Inf. Assoc. 31, 583\u2013590 (2024).","journal-title":"J. Am. Med. Inf. Assoc."},{"key":"6447_CR27","unstructured":"New and improved embedding model. https:\/\/openai.com\/blog\/new-and-improved-embedding-model"},{"key":"6447_CR28","doi-asserted-by":"publisher","unstructured":"Song, K. et al. Masked and permuted pre-training for language understanding. Preprint at (2020). https:\/\/doi.org\/10.48550\/ARXIV.2004.09297","DOI":"10.48550\/ARXIV.2004.09297"},{"key":"6447_CR29","unstructured":"SeatGeek GitHub (2023)."},{"key":"6447_CR30","unstructured":"Levenshtein, V. I. Binary codes capable of correcting deletions, insertions, and reversals. in Soviet physics doklady  10 707\u2013710 (Soviet Union, 1966)."},{"key":"6447_CR31","first-page":"2579","volume":"9","author":"L van der Maaten","year":"2008","unstructured":"van der Maaten, L. & Hinton, G. Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579\u20132605 (2008).","journal-title":"J. Mach. Learn. Res."},{"key":"6447_CR32","doi-asserted-by":"publisher","unstructured":"Ay, M. C., Salimi, Y., Adams, T., Niazpoor, M. & Zenodo Parkinson\u2019s disease variable mapping schema - PASSIONATE. (2024). https:\/\/doi.org\/10.5281\/ZENODO.10218362","DOI":"10.5281\/ZENODO.10218362"},{"key":"6447_CR33","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1159\/000501150","volume":"47","author":"FS Rodriguez","year":"2019","unstructured":"Rodriguez, F. S., Zheng, L. & Chui, H. C. Psychometric characteristics of cognitive reserve: how high education might improve certain cognitive abilities in aging. Dement. Geriatr. Cogn. Disord. 47, 335\u2013344 (2019).","journal-title":"Dement. Geriatr. Cogn. Disord"},{"key":"6447_CR34","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1016\/j.jalz.2009.04.1235","volume":"5","author":"GB Frisoni","year":"2009","unstructured":"Frisoni, G. B. et al. Markers of alzheimer\u2019s disease in a population attending a memory clinic. Alzheimers Dement. J. Alzheimers Assoc. 5, 307\u2013317 (2009).","journal-title":"Alzheimers Dement. J. Alzheimers Assoc."},{"key":"6447_CR35","first-page":"S226","volume":"10","author":"MW Weiner","year":"2014","unstructured":"Weiner, M. W. et al. Effects of traumatic brain injury and posttraumatic stress disorder on alzheimer\u2019s disease in veterans, using the alzheimer\u2019s disease neuroimaging initiative. Alzheimers Dement. J. Alzheimers Assoc. 10, S226\u2013235 (2014).","journal-title":"Alzheimers Dement. J. Alzheimers Assoc."},{"key":"6447_CR36","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1186\/s12916-018-1122-7","volume":"16","author":"H Fr\u00f6hlich","year":"2018","unstructured":"Fr\u00f6hlich, H. et al. From hype to reality: data science enabling personalized medicine. BMC Med. 16, 150 (2018).","journal-title":"BMC Med."},{"key":"6447_CR37","doi-asserted-by":"publisher","first-page":"941","DOI":"10.3233\/JAD-132666","volume":"40","author":"E Cavedo","year":"2014","unstructured":"Cavedo, E. et al. The Italian alzheimer\u2019s disease neuroimaging initiative (I-ADNI): validation of structural MR imaging. J. Alzheimers Dis. JAD. 40, 941\u2013952 (2014).","journal-title":"J. Alzheimers Dis. JAD"},{"key":"6447_CR38","doi-asserted-by":"publisher","first-page":"924","DOI":"10.1002\/mds.26613","volume":"31","author":"UJ Kang","year":"2016","unstructured":"Kang, U. J. et al. The BioFIND study: characteristics of a clinically typical parkinson\u2019s disease biomarker cohort. Mov. Disord. 31, 924\u2013932 (2016).","journal-title":"Mov. Disord"},{"key":"6447_CR39","doi-asserted-by":"publisher","first-page":"726","DOI":"10.1002\/mds.26964","volume":"32","author":"C Pont-Sunyer","year":"2017","unstructured":"Pont-Sunyer, C. et al. The prodromal phase of leucine-rich repeat kinase 2-associated Parkinson disease: clinical and imaging studies. Mov. Disord Off J. Mov. Disord Soc. 32, 726\u2013738 (2017).","journal-title":"Mov. Disord Off J. Mov. Disord Soc."},{"key":"6447_CR40","doi-asserted-by":"publisher","first-page":"326","DOI":"10.3389\/fnagi.2018.00326","volume":"10","author":"G Hipp","year":"2018","unstructured":"Hipp, G. et al. The Luxembourg parkinson\u2019s study: A comprehensive approach for stratification and early diagnosis. Front. Aging Neurosci. 10, 326 (2018).","journal-title":"Front. Aging Neurosci."},{"key":"6447_CR41","doi-asserted-by":"publisher","DOI":"10.48532\/036000","author":"M Hu","year":"2017","unstructured":"Hu, M. Oxford parkinson\u2019s disease centre discovery cohortopdc discovery. Dementias Platf. UK. https:\/\/doi.org\/10.48532\/036000 (2017).","journal-title":"Dementias Platf. UK"},{"key":"6447_CR42","doi-asserted-by":"publisher","first-page":"2946","DOI":"10.1093\/brain\/awab165","volume":"144","author":"S Verdi","year":"2021","unstructured":"Verdi, S., Marquand, A. F., Schott, J. M. & Cole, J. H. Beyond the average patient: how neuroimaging models can address heterogeneity in dementia. Brain J. Neurol. 144, 2946\u20132953 (2021).","journal-title":"Brain J. Neurol."},{"key":"6447_CR43","first-page":"947","volume":"5","author":"N Malek","year":"2015","unstructured":"Malek, N. et al. Tracking parkinson\u2019s: study design and baseline patient data. J. Park Dis. 5, 947\u2013959 (2015).","journal-title":"J. Park Dis."},{"key":"6447_CR44","unstructured":"EMBL-EBI. Ontology lookup service. (2023). https:\/\/www.ebi.ac.uk\/ols4\/index"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-06447-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-06447-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-06447-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T10:03:59Z","timestamp":1750413839000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-06447-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,20]]},"references-count":44,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["6447"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-06447-2","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-4108029\/v1","asserted-by":"object"}]},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,20]]},"assertion":[{"value":"15 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 June 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 June 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"20210"}}