{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T06:47:42Z","timestamp":1771051662829,"version":"3.50.1"},"reference-count":61,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,7,21]],"date-time":"2023-07-21T00:00:00Z","timestamp":1689897600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,7,21]],"date-time":"2023-07-21T00:00:00Z","timestamp":1689897600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100006108","name":"U.S. Department of Health & Human Services | NIH | National Center for Advancing Translational Sciences","doi-asserted-by":"publisher","award":["U01TR002062"],"award-info":[{"award-number":["U01TR002062"]}],"id":[{"id":"10.13039\/100006108","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006108","name":"U.S. Department of Health & Human Services | NIH | National Center for Advancing Translational Sciences","doi-asserted-by":"publisher","award":["U01TR002062"],"award-info":[{"award-number":["U01TR002062"]}],"id":[{"id":"10.13039\/100006108","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006108","name":"U.S. Department of Health & Human Services | NIH | National Center for Advancing Translational Sciences","doi-asserted-by":"publisher","award":["U01TR002062"],"award-info":[{"award-number":["U01TR002062"]}],"id":[{"id":"10.13039\/100006108","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006108","name":"U.S. Department of Health & Human Services | NIH | National Center for Advancing Translational Sciences","doi-asserted-by":"publisher","award":["U01TR002062"],"award-info":[{"award-number":["U01TR002062"]}],"id":[{"id":"10.13039\/100006108","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006108","name":"U.S. Department of Health & Human Services | NIH | National Center for Advancing Translational Sciences","doi-asserted-by":"publisher","award":["U01TR002062"],"award-info":[{"award-number":["U01TR002062"]}],"id":[{"id":"10.13039\/100006108","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006108","name":"U.S. Department of Health & Human Services | NIH | National Center for Advancing Translational Sciences","doi-asserted-by":"publisher","award":["U01TR002062"],"award-info":[{"award-number":["U01TR002062"]}],"id":[{"id":"10.13039\/100006108","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000092","name":"U.S. Department of Health & Human Services | NIH | U.S. National Library of Medicine","doi-asserted-by":"publisher","award":["R01LM011934"],"award-info":[{"award-number":["R01LM011934"]}],"id":[{"id":"10.13039\/100000092","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000092","name":"U.S. Department of Health & Human Services | NIH | U.S. National Library of Medicine","doi-asserted-by":"publisher","award":["R01LM011934"],"award-info":[{"award-number":["R01LM011934"]}],"id":[{"id":"10.13039\/100000092","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000092","name":"U.S. Department of Health & Human Services | NIH | U.S. National Library of Medicine","doi-asserted-by":"publisher","award":["R01LM011934"],"award-info":[{"award-number":["R01LM011934"]}],"id":[{"id":"10.13039\/100000092","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000092","name":"U.S. Department of Health & Human Services | NIH | U.S. National Library of Medicine","doi-asserted-by":"publisher","award":["R01LM011934"],"award-info":[{"award-number":["R01LM011934"]}],"id":[{"id":"10.13039\/100000092","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000092","name":"U.S. Department of Health & Human Services | NIH | U.S. National Library of Medicine","doi-asserted-by":"publisher","award":["R01LM011934"],"award-info":[{"award-number":["R01LM011934"]}],"id":[{"id":"10.13039\/100000092","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000092","name":"U.S. Department of Health & Human Services | NIH | U.S. National Library of Medicine","doi-asserted-by":"publisher","award":["R01LM011934"],"award-info":[{"award-number":["R01LM011934"]}],"id":[{"id":"10.13039\/100000092","id-type":"DOI","asserted-by":"publisher"}]},{"name":"U.S. Department of Health & Human Services | NIH | National Center for Advancing Translational Sciences"},{"name":"U.S. Department of Health & Human Services | NIH | National Center for Advancing Translational Sciences"},{"name":"U.S. Department of Health & Human Services | NIH | National Center for Advancing Translational Sciences"},{"name":"U.S. Department of Health & Human Services | NIH | National Center for Advancing Translational Sciences"},{"name":"U.S. Department of Health & Human Services | NIH | U.S. National Library of Medicine"},{"name":"U.S. Department of Health & Human Services | NIH | U.S. National Library of Medicine"},{"name":"U.S. Department of Health & Human Services | NIH | National Center for Advancing Translational Sciences"},{"name":"U.S. Department of Health & Human Services | NIH | U.S. National Library of Medicine"},{"name":"U.S. Department of Health & Human Services | NIH | U.S. National Library of Medicine"},{"name":"U.S. Department of Health & Human Services | NIH | U.S. National Library of Medicine"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Clinical phenotyping is often a foundational requirement for obtaining datasets necessary for the development of digital health applications. Traditionally done via manual abstraction, this task is often a bottleneck in development due to time and cost requirements, therefore raising significant interest in accomplishing this task via in-silico means. Nevertheless, current in-silico phenotyping development tends to be focused on a single phenotyping task resulting in a dearth of reusable tools supporting cross-task generalizable in-silico phenotyping. In addition, in-silico phenotyping remains largely inaccessible for a substantial portion of potentially interested users. Here, we highlight the barriers to the usage of in-silico phenotyping and potential solutions in the form of a framework of several desiderata as observed during our implementation of such tasks. In addition, we introduce an example implementation of said framework as a software application, with a focus on ease of adoption, cross-task reusability, and facilitating the clinical phenotyping algorithm development process.<\/jats:p>","DOI":"10.1038\/s41746-023-00878-9","type":"journal-article","created":{"date-parts":[[2023,7,21]],"date-time":"2023-07-21T13:03:06Z","timestamp":1689944586000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["The IMPACT framework and implementation for accessible in silico clinical phenotyping in the digital era"],"prefix":"10.1038","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9090-8028","authenticated-orcid":false,"given":"Andrew","family":"Wen","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1312-4195","authenticated-orcid":false,"given":"Huan","family":"He","sequence":"additional","affiliation":[]},{"given":"Sunyang","family":"Fu","sequence":"additional","affiliation":[]},{"given":"Sijia","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Kurt","family":"Miller","sequence":"additional","affiliation":[]},{"given":"Liwei","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6525-5213","authenticated-orcid":false,"given":"Kirk E.","family":"Roberts","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0163-9397","authenticated-orcid":false,"given":"Steven D.","family":"Bedrick","sequence":"additional","affiliation":[]},{"given":"William R.","family":"Hersh","sequence":"additional","affiliation":[]},{"given":"Hongfang","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,7,21]]},"reference":[{"key":"878_CR1","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1016\/j.jbi.2009.12.004","volume":"43","author":"C Weng","year":"2010","unstructured":"Weng, C., Tu, S. W., Sim, I. & Richesson, R. Formal representation of eligibility criteria: a literature review. J. Biomed. Inf. 43, 451\u2013467 (2010).","journal-title":"J. Biomed. Inf."},{"key":"878_CR2","first-page":"215","volume":"9","author":"RL Richesson","year":"2014","unstructured":"Richesson, R. L., Horvath, M. M. & Rusincovitch, S. A. Clinical research informatics and electronic health record data. Yearb. Med. Inf. 9, 215\u2013223 (2014).","journal-title":"Yearb. Med. Inf."},{"key":"878_CR3","doi-asserted-by":"publisher","first-page":"869","DOI":"10.1197\/jamia.M3119","volume":"16","author":"SR Thadani","year":"2009","unstructured":"Thadani, S. R., Weng, C., Bigger, J. T., Ennever, J. F. & Wajngurt, D. Electronic screening improves efficiency in clinical trial recruitment. J. Am. Med. Inf. Assoc. 16, 869\u2013873 (2009).","journal-title":"J. Am. Med. Inf. Assoc."},{"key":"878_CR4","doi-asserted-by":"publisher","first-page":"e206","DOI":"10.1136\/amiajnl-2013-002428","volume":"20","author":"J Pathak","year":"2013","unstructured":"Pathak, J., Kho, A. N. & Denny, J. C. Electronic health records-driven phenotyping: challenges, recent advances, and perspectives. J. Am. Med. Inf. Assoc. 20, e206\u2013e211 (2013).","journal-title":"J. Am. Med. Inf. Assoc."},{"key":"878_CR5","doi-asserted-by":"publisher","first-page":"1352","DOI":"10.1093\/jamia\/ocaa089","volume":"27","author":"TR Campion","year":"2020","unstructured":"Campion, T. R., Craven, C. K., Dorr, D. A. & Knosp, B. M. Understanding enterprise data warehouses to support clinical and translational research. J. Am. Med. Inf. Assoc. 27, 1352\u20131358 (2020).","journal-title":"J. Am. Med. Inf. Assoc."},{"key":"878_CR6","first-page":"46","volume":"2010","author":"J Ross","year":"2010","unstructured":"Ross, J., Tu, S., Carini, S. & Sim, I. Analysis of eligibility criteria complexity in clinical trials. Summit Transl. Bioinform. 2010, 46\u201350 (2010).","journal-title":"Summit Transl. Bioinform."},{"key":"878_CR7","doi-asserted-by":"publisher","first-page":"645","DOI":"10.1093\/aje\/kwt010","volume":"178","author":"D Madigan","year":"2013","unstructured":"Madigan, D. et al. Evaluating the impact of database heterogeneity on observational study results. Am. J. Epidemiol. 178, 645\u2013651 (2013).","journal-title":"Am. J. Epidemiol."},{"key":"878_CR8","first-page":"196","volume":"2022","author":"S Fu","year":"2022","unstructured":"Fu, S. et al. Assessment of Data Quality Variability across Two EHR Systems through a Case Study of Post-Surgical Complications. AMIA Annu Symp. Proc. 2022, 196\u2013205 (2022).","journal-title":"AMIA Annu Symp. Proc."},{"key":"878_CR9","unstructured":"Elasticsearch B.V. Elasticsearch, https:\/\/github.com\/elasticsearch\/elasticsearch (2015)."},{"key":"878_CR10","unstructured":"MongoDB Inc. The MongoDB Database, https:\/\/github.com\/mongodb\/mongo (2009)."},{"key":"878_CR11","unstructured":"Google Inc. BigQuery: Enterprise Data Warehouse, https:\/\/cloud.google.com\/bigquery (2011)."},{"key":"878_CR12","unstructured":"Health Level 7 International. Fast Healthcare Interoperability Resources (FHIR), https:\/\/hl7.org\/fhir\/R4\/ (2019)."},{"key":"878_CR13","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1136\/amiajnl-2011-000376","volume":"19","author":"JM Overhage","year":"2012","unstructured":"Overhage, J. M., Ryan, P. B., Reich, C. G., Hartzema, A. G. & Stang, P. E. Validation of a common data model for active safety surveillance research. J. Am. Med. Inf. Assoc. 19, 54\u201360 (2012).","journal-title":"J. Am. Med. Inf. Assoc."},{"key":"878_CR14","doi-asserted-by":"publisher","first-page":"578","DOI":"10.1136\/amiajnl-2014-002747","volume":"21","author":"RL Fleurence","year":"2014","unstructured":"Fleurence, R. L. et al. Launching PCORnet, a national patient-centered clinical research network. J. Am. Med. Inf. Assoc. 21, 578\u2013582 (2014).","journal-title":"J. Am. Med. Inf. Assoc."},{"key":"878_CR15","doi-asserted-by":"crossref","unstructured":"Yadav, H., Du, Z. & Joachims, T. Policy-Gradient Training of Fair and Unbiased Ranking Functions. Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM SIGIR 2021, 1044\u20131053 (2021).","DOI":"10.1145\/3404835.3462953"},{"key":"878_CR16","unstructured":"Hanauer, D. A. EMERSE: The Electronic Medical Record Search Engine. AMIA Annu. Symp. Proc. 2006 Annual Symposium of the American Medical Informatics Association, 941 (2006)."},{"key":"878_CR17","doi-asserted-by":"publisher","first-page":"e17376","DOI":"10.2196\/17376","volume":"8","author":"S Liu","year":"2020","unstructured":"Liu, S. et al. Implementation of a Cohort Retrieval System for Clinical Data Repositories Using the Observational Medical Outcomes Partnership Common Data Model: Proof-of-Concept System Validation. JMIR Med. Inf. 8, e17376 (2020).","journal-title":"JMIR Med. Inf."},{"key":"878_CR18","unstructured":"Apache Software Foundation. Apache Lucene, https:\/\/lucene.apache.org\/ (2022)."},{"key":"878_CR19","doi-asserted-by":"crossref","unstructured":"Shahi, D. Apache Solr: A Practical Approach to Enterprise Search. (APress, 2015).","DOI":"10.1007\/978-1-4842-1070-3"},{"key":"878_CR20","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1016\/j.jbi.2017.11.011","volume":"77","author":"Y Wang","year":"2018","unstructured":"Wang, Y. et al. Clinical information extraction applications: A literature review. J. Biomed. Inform. 77, 34\u201349 (2018).","journal-title":"J. Biomed. Inform."},{"key":"878_CR21","doi-asserted-by":"publisher","first-page":"524","DOI":"10.1093\/gerona\/glaa275","volume":"77","author":"S Fu","year":"2022","unstructured":"Fu, S. et al. Ascertainment of Delirium Status Using Natural Language Processing From Electronic Health Records. J. Gerontol. A Biol. Sci. Med Sci. 77, 524\u2013530 (2022).","journal-title":"J. Gerontol. A Biol. Sci. Med Sci."},{"key":"878_CR22","doi-asserted-by":"publisher","first-page":"922","DOI":"10.1016\/j.arth.2020.09.029","volume":"36","author":"E Sagheb","year":"2021","unstructured":"Sagheb, E. et al. Use of Natural Language Processing Algorithms to Identify Common Data Elements in Operative Notes for Knee Arthroplasty. J. Arthroplast. 36, 922\u2013926 (2021).","journal-title":"J. Arthroplast."},{"key":"878_CR23","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/j.compmedimag.2018.09.004","volume":"70","author":"F Gao","year":"2018","unstructured":"Gao, F. et al. SD-CNN: A shallow-deep CNN for improved breast cancer diagnosis. Comput Med. Imaging Graph. 70, 53\u201362 (2018).","journal-title":"Comput Med. Imaging Graph."},{"key":"878_CR24","doi-asserted-by":"publisher","unstructured":"Sun, L. et al. Breast Mass Detection in Mammography Based on Image Template Matching and CNN. Sensors (Basel) 21 (2021). https:\/\/doi.org\/10.3390\/s21082855","DOI":"10.3390\/s21082855"},{"key":"878_CR25","doi-asserted-by":"publisher","first-page":"1537","DOI":"10.1007\/s11548-021-02414-0","volume":"16","author":"H Che","year":"2021","unstructured":"Che, H., Brown, L. G., Foran, D. J., Nosher, J. L. & Hacihaliloglu, I. Liver disease classification from ultrasound using multi-scale CNN. Int J. Comput. Assist Radio. Surg. 16, 1537\u20131548 (2021).","journal-title":"Int J. Comput. Assist Radio. Surg."},{"key":"878_CR26","doi-asserted-by":"publisher","first-page":"1142","DOI":"10.1093\/jamia\/ocac052","volume":"29","author":"YJ Juhn","year":"2022","unstructured":"Juhn, Y. J. et al. Assessing socioeconomic bias in machine learning algorithms in health care: a case study of the HOUSES index. J. Am. Med. Inf. Assoc. 29, 1142\u20131151 (2022).","journal-title":"J. Am. Med. Inf. Assoc."},{"key":"878_CR27","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1126\/science.aax2342","volume":"366","author":"Z Obermeyer","year":"2019","unstructured":"Obermeyer, Z., Powers, B., Vogeli, C. & Mullainathan, S. Dissecting racial bias in an algorithm used to manage the health of populations. Science 366, 447\u2013453 (2019).","journal-title":"Science"},{"key":"878_CR28","doi-asserted-by":"publisher","first-page":"866","DOI":"10.7326\/M18-1990","volume":"169","author":"A Rajkomar","year":"2018","unstructured":"Rajkomar, A., Hardt, M., Howell, M. D., Corrado, G. & Chin, M. H. Ensuring Fairness in Machine Learning to Advance Health Equity. Ann. Intern. Med. 169, 866\u2013872 (2018).","journal-title":"Ann. Intern. Med."},{"key":"878_CR29","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1007\/s41666-019-00044-5","volume":"3","author":"S Moon","year":"2019","unstructured":"Moon, S. et al. Salience of Medical Concepts of Inside Clinical Texts and Outside Medical Records for Referred Cardiovascular Patients. J. Health. Inf. Res. 3, 200\u2013219 (2019).","journal-title":"J. Health. Inf. Res."},{"key":"878_CR30","doi-asserted-by":"publisher","first-page":"1062","DOI":"10.1093\/jamia\/ocx019","volume":"24","author":"T Kang","year":"2017","unstructured":"Kang, T. et al. EliIE: An open-source information extraction system for clinical trial eligibility criteria. J. Am. Med. Inf. Assoc. 24, 1062\u20131071 (2017).","journal-title":"J. Am. Med. Inf. Assoc."},{"key":"878_CR31","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1016\/S0196-0644(96)70264-0","volume":"27","author":"EH Gilbert","year":"1996","unstructured":"Gilbert, E. H., Lowenstein, S. R., Koziol-McLain, J., Barta, D. C. & Steiner, J. Chart reviews in emergency medicine research: Where are the methods? Ann. Emerg. Med. 27, 305\u2013308 (1996).","journal-title":"Ann. Emerg. Med."},{"key":"878_CR32","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-020-1072-9","volume":"20","author":"S Fu","year":"2020","unstructured":"Fu, S. et al. Assessment of the impact of EHR heterogeneity for clinical research through a case study of silent brain infarction. BMC Med Inf. Decis. Mak. 20, 60 (2020).","journal-title":"BMC Med Inf. Decis. Mak."},{"key":"878_CR33","doi-asserted-by":"publisher","unstructured":"Pagali, S. R., Kumar, R., Fu, S., Sohn, S. & Yousufuddin, M. Natural Language Processing CAM Algorithm Improves Delirium Detection Compared With Conventional Methods. Am. J. Med. Qual. (2022). https:\/\/doi.org\/10.1097\/JMQ.0000000000000090","DOI":"10.1097\/JMQ.0000000000000090"},{"key":"878_CR34","doi-asserted-by":"publisher","first-page":"1230","DOI":"10.1016\/j.jacl.2016.08.001","volume":"10","author":"MS Safarova","year":"2016","unstructured":"Safarova, M. S., Liu, H. & Kullo, I. J. Rapid identification of familial hypercholesterolemia from electronic health records: The SEARCH study. J. Clin. Lipido. 10, 1230\u20131239 (2016).","journal-title":"J. Clin. Lipido."},{"key":"878_CR35","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1109\/TCBB.2018.2849968","volume":"16","author":"Z Zeng","year":"2019","unstructured":"Zeng, Z., Deng, Y., Li, X., Naumann, T. & Luo, Y. Natural Language Processing for EHR-Based Computational Phenotyping. IEEE\/ACM Trans. Comput. Biol. Bioinform. 16, 139\u2013153 (2019).","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinform."},{"key":"878_CR36","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1093\/jamia\/ocx138","volume":"25","author":"S Sohn","year":"2018","unstructured":"Sohn, S. et al. Clinical documentation variations and NLP system portability: a case study in asthma birth cohorts across institutions. J. Am. Med. Inf. Assoc. 25, 353\u2013359 (2018).","journal-title":"J. Am. Med. Inf. Assoc."},{"key":"878_CR37","first-page":"1224","volume":"192","author":"O Bodenreider","year":"2013","unstructured":"Bodenreider, O. et al. The NLM value set authority center. Stud. Health Technol. Inf. 192, 1224 (2013).","journal-title":"Stud. Health Technol. Inf."},{"key":"878_CR38","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1093\/jamia\/ocy178","volume":"26","author":"C Yuan","year":"2019","unstructured":"Yuan, C. et al. Criteria2Query: a natural language interface to clinical databases for cohort definition. J. Am. Med. Inf. Assoc. 26, 294\u2013305 (2019).","journal-title":"J. Am. Med. Inf. Assoc."},{"key":"878_CR39","first-page":"149","volume":"2013","author":"H Liu","year":"2013","unstructured":"Liu, H. et al. An information extraction framework for cohort identification using electronic health records. AMIA Jt Summits Transl. Sci. Proc. 2013, 149\u2013153 (2013).","journal-title":"AMIA Jt Summits Transl. Sci. Proc."},{"key":"878_CR40","doi-asserted-by":"publisher","first-page":"507","DOI":"10.1136\/jamia.2009.001560","volume":"17","author":"GK Savova","year":"2010","unstructured":"Savova, G. K. et al. Mayo clinical Text Analysis and Knowledge Extraction System (cTAKES): architecture, component evaluation and applications. J. Am. Med. Inf. Assoc. 17, 507\u2013513 (2010).","journal-title":"J. Am. Med. Inf. Assoc."},{"key":"878_CR41","doi-asserted-by":"publisher","first-page":"12","DOI":"10.3352\/jeehp.2013.10.12","volume":"10","author":"M Vassar","year":"2013","unstructured":"Vassar, M. & Holzmann, M. The retrospective chart review: important methodological considerations. J. Educ. Eval. Health Prof. 10, 12 (2013).","journal-title":"J. Educ. Eval. Health Prof."},{"key":"878_CR42","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1016\/S1532-0464(03)00013-3","volume":"35","author":"R Grishman","year":"2002","unstructured":"Grishman, R., Huttunen, S. & Yangarber, R. Information extraction for enhanced access to disease outbreak reports. J. Biomed. Inf. 35, 236\u2013246 (2002).","journal-title":"J. Biomed. Inf."},{"key":"878_CR43","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-10-S9-S12","volume":"10","author":"BR South","year":"2009","unstructured":"South, B. R. et al. Developing a manually annotated clinical document corpus to identify phenotypic information for inflammatory bowel disease. BMC Bioinforma. 10, S12 (2009).","journal-title":"BMC Bioinforma."},{"key":"878_CR44","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1038\/519158a","volume":"519","author":"WP Anderson","year":"2015","unstructured":"Anderson, W. P. Reproducibility: Stamp out shabby research conduct. Nature 519, 158 (2015).","journal-title":"Nature"},{"key":"878_CR45","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1038\/492041a","volume":"492","author":"D Baker","year":"2012","unstructured":"Baker, D., Lidster, K., Sottomayor, A. & Amor, S. Reproducibility: Research-reporting standards fall short. Nature 492, 41 (2012).","journal-title":"Nature"},{"key":"878_CR46","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1038\/525025a","volume":"525","author":"CG Begley","year":"2015","unstructured":"Begley, C. G., Buchan, A. M. & Dirnagl, U. Robust research: Institutions must do their part for reproducibility. Nature 525, 25\u201327 (2015).","journal-title":"Nature"},{"key":"878_CR47","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1038\/498170b","volume":"498","author":"E Kolker","year":"2013","unstructured":"Kolker, E. et al. Reproducibility: In praise of open research measures. Nature 498, 170 (2013).","journal-title":"Nature"},{"key":"878_CR48","doi-asserted-by":"publisher","first-page":"540","DOI":"10.1136\/amiajnl-2011-000465","volume":"18","author":"WW Chapman","year":"2011","unstructured":"Chapman, W. W. et al. Overcoming barriers to NLP for clinical text: the role of shared tasks and the need for additional creative solutions. J. Am. Med. Inf. Assoc. 18, 540\u2013543 (2011).","journal-title":"J. Am. Med. Inf. Assoc."},{"key":"878_CR49","first-page":"291","volume":"74","author":"MA Musen","year":"1987","unstructured":"Musen, M. A., Rohn, J. A., Fagan, L. M. & Shortliffe, E. H. Knowledge engineering for a clinical trial advice system: uncovering errors in protocol specification. Bull. Cancer 74, 291\u2013296 (1987).","journal-title":"Bull. Cancer"},{"key":"878_CR50","doi-asserted-by":"publisher","DOI":"10.1186\/s12883-021-02221-9","volume":"21","author":"LY Leung","year":"2021","unstructured":"Leung, L. Y. et al. Agreement between neuroimages and reports for natural language processingbased detection of silent brain infarcts and white matter disease. BMC Neurol. 21, 189 (2021).","journal-title":"BMC Neurol."},{"key":"878_CR51","doi-asserted-by":"publisher","first-page":"103526","DOI":"10.1016\/j.jbi.2020.103526","volume":"109","author":"S Fu","year":"2020","unstructured":"Fu, S. et al. Clinical concept extraction: A methodology review. J. Biomed. Inf. 109, 103526 (2020).","journal-title":"J. Biomed. Inf."},{"key":"878_CR52","unstructured":"Observational Health Data Sciences and Informatics. OHDSI\/Atlas - an Open Source Software Tool for Researchers to Conduct Scientific Analyses on Standardized Observational Data, https:\/\/github.com\/OHDSI\/Atlas (2022)."},{"key":"878_CR53","unstructured":"Wu, S. et al. in Proceedings of the 10th International Conference on Language Resources and Evaluation, LREC 2016 3412-3416 (European Language Resources Association (ELRA), Portoroz, Slovenia, 2016)."},{"key":"878_CR54","unstructured":"Apache Software Foundation. Apache Beam, https:\/\/beam.apache.org\/ (2022)."},{"key":"878_CR55","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1561\/1500000019","volume":"3","author":"H Zaragoza","year":"2009","unstructured":"Zaragoza, H. & Robertson, S. The Probabilistic Relevance Framework: BM25 and Beyond. Found. Trends\u00ae Inf. Retr. 3, 333\u2013389 (2009).","journal-title":"Found. Trends\u00ae Inf. Retr."},{"key":"878_CR56","doi-asserted-by":"crossref","unstructured":"Lv, Y. & Zhai, C. Lower-bounding term frequency normalization. Proceedings of the 20th ACM international conference on Information and knowledge management. CIKM '11, 7\u201316 (2011).","DOI":"10.1145\/2063576.2063584"},{"key":"878_CR57","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1038\/s41746-019-0208-8","volume":"2","author":"A Wen","year":"2019","unstructured":"Wen, A. et al. Desiderata for delivering NLP to accelerate healthcare AI advancement and a Mayo Clinic NLP-as-a-service implementation. NPJ Digit. Med. 2, 130 (2019).","journal-title":"NPJ Digit. Med."},{"key":"878_CR58","first-page":"74","volume":"2017","author":"N Hong","year":"2018","unstructured":"Hong, N. et al. Integrating Structured and Unstructured EHR Data Using an FHIR-based Type System: A Case Study with Medication Data. AMIA Jt Summits Transl. Sci. Proc. 2017, 74\u201383 (2018).","journal-title":"AMIA Jt Summits Transl. Sci. Proc."},{"key":"878_CR59","doi-asserted-by":"publisher","first-page":"570","DOI":"10.1093\/jamiaopen\/ooz056","volume":"2","author":"N Hong","year":"2019","unstructured":"Hong, N. et al. Developing a scalable FHIR-based clinical data normalization pipeline for standardizing and integrating unstructured and structured electronic health record data. JAMIA Open 2, 570\u2013579 (2019).","journal-title":"JAMIA Open"},{"key":"878_CR60","doi-asserted-by":"publisher","first-page":"D267","DOI":"10.1093\/nar\/gkh061","volume":"32","author":"O Bodenreider","year":"2004","unstructured":"Bodenreider, O. The Unified Medical Language System (UMLS): integrating biomedical terminology. Nucleic Acids Res. 32, D267\u2013D270 (2004).","journal-title":"Nucleic Acids Res."},{"key":"878_CR61","unstructured":"Observational Health Data Sciences and Informatics. Athena: Observational Health Data Sciences and Informatics \u2013 OHDSI, https:\/\/athena.ohdsi.org\/ (2022)."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00878-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00878-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00878-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,21]],"date-time":"2023-07-21T13:09:01Z","timestamp":1689944941000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00878-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,21]]},"references-count":61,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["878"],"URL":"https:\/\/doi.org\/10.1038\/s41746-023-00878-9","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,21]]},"assertion":[{"value":"19 February 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 July 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 July 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Author H.L. is an Editorial Board Member of <i>npj Digital Medicine<\/i>. They played no role in the peer review or decision to publish this paper. The authors declare no further financial or non-financial competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"132"}}