{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:43:04Z","timestamp":1785544984304,"version":"3.56.0"},"reference-count":27,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Perioper Med"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Surgical site infections (SSIs) affect 160,000 to 300,000 patients annually, increasing postoperative mortality, causing significant complications, and incurring US $3.5 to US $10 billion in excess costs each year. Effective SSI surveillance can inform strategies to mitigate these outcomes. Traditional SSI surveillance methods, primarily manual chart reviews, are costly and labor-intensive.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aimed to evaluate whether an automated SSI surveillance system built using newer natural language processing methods and deep learning could outperform previous approaches and whether such an approach could enable more efficient infection surveillance.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n \n Our dataset comprised approximately 30,000 surgical cases from the University of Washington Medical Center (UWMC) and Harborview Medical Center (HMC). Data from UWMC were captured for the National Surgical Quality Improvement Program, and data from HMC were captured for the National Healthcare Safety Network. Electronic health record (EHR) data for each surgical case included structured data pertaining to surgical procedure characteristics, laboratory values, and antibiotic administration, as well as clinical text notes for a surgical case from 7 days before to 90 days after surgery. Using this data, we applied a myriad of machine learning approaches to the task of SSI prediction. We reported the following performance metrics:\n F<\/jats:italic>\n 1<\/jats:sub>\n -score, precision (positive predictive value), recall (sensitivity), area under the precision-recall curve, and precision at 0.9 recall for each machine learning approach.\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n In a cohort of 5996 surgical cases, incorporating multimodal EHR information\u2014including contextual information from clinical text and temporal information from laboratory values\u2014improved SSI prediction performance. Models using structured data and clinical text outperformed structured data alone (\n F<\/jats:italic>\n 1<\/jats:sub>\n =0.68, 95% CI 0.68\u20100.69 vs\n F<\/jats:italic>\n 1<\/jats:sub>\n =0.55, 95% CI 0.54\u20100.56;\n P<\/jats:italic>\n <.001). Adding temporal features further improved performance (\n F<\/jats:italic>\n 1<\/jats:sub>\n =0.70, 95% CI 0.69\u20100.71;\n P<\/jats:italic>\n <.001). Deep learning approaches leveraging large language models also outperformed the state-of-the-art rule-based system (\n F<\/jats:italic>\n 1<\/jats:sub>\n =0.70, 95% CI 0.69\u20100.71 vs\n F<\/jats:italic>\n 1<\/jats:sub>\n =0.43;\n P<\/jats:italic>\n <.001). The optimal approach combined foundation models for text summarization with deep learning methods for clinical text and temporal data processing. This system achieved a precision of 0.38 at 0.9 recall, demonstrating its potential for efficient, data-driven SSI surveillance.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n Automated surveillance approaches\u2014particularly deep learning approaches\u2014in combination with voluminous, multimodal data from the EHR, can enable more efficient infection surveillance processes. This has the potential to increase the quantity of SSI surveillance data available to guide interventions aimed at reducing SSI rates.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/87896","type":"journal-article","created":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T20:22:58Z","timestamp":1782505378000},"page":"e87896-e87896","source":"Crossref","is-referenced-by-count":0,"title":["Automated Identification of Surgical Site Infections From Electronic Medical Records: Retrospective Observational Predictive Modeling Study"],"prefix":"10.2196","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2858-295X","authenticated-orcid":false,"given":"Arjun","family":"Chakraborty","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1047-179X","authenticated-orcid":false,"given":"Peter","family":"Tarczy-Hornoch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6365-953X","authenticated-orcid":false,"given":"Dustin","family":"Long","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9919-9811","authenticated-orcid":false,"given":"Meliha","family":"Yetisgen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,6,26]]},"reference":[{"key":"R1","doi-asserted-by":"crossref","unstructured":"Anderson DJ Perl TM . Basics of surgical site infection: surveillance and prevention. In: Practical Healthcare Epidemiology. Cambridge University Press; 2018:147-161. [doi: 10.1017\/9781107153165.015]","DOI":"10.1017\/9781107153165.015"},{"issue":"18","key":"R2","doi-asserted-by":"publisher","first-page":"1732","DOI":"10.1056\/NEJMoa1801550","article-title":"Changes in prevalence of health care-associated infections in U.S. hospitals","volume":"379","author":"Magill","journal-title":"N Engl J Med"},{"issue":"11","key":"R3","doi-asserted-by":"publisher","DOI":"10.3390\/antibiotics11111608","article-title":"Update on the management of surgical site infections","volume":"11","author":"Pinchera","journal-title":"Antibiotics (Basel)"},{"issue":"3","key":"R4","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1001\/jama.2022.24075","article-title":"Surgical site infection prevention: a review","volume":"329","author":"Seidelman","journal-title":"JAMA"},{"issue":"1","key":"R5","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2334-6-170","article-title":"Methods for identifying surgical wound infection after discharge from hospital: a systematic review","volume":"6","author":"Petherick","journal-title":"BMC Infect Dis"},{"issue":"1","key":"R6","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1001\/archsurg.137.1.20","article-title":"The comparative assessment and improvement of quality of surgical care in the Department of Veterans Affairs","volume":"137","author":"Khuri","journal-title":"Arch Surg"},{"issue":"2","key":"R7","doi-asserted-by":"publisher","first-page":"416","DOI":"10.1016\/j.jss.2015.02.072","article-title":"Comparing surgical infections in National Surgical Quality Improvement Project and an institutional database","volume":"196","author":"Selby","journal-title":"J Surg Res"},{"issue":"3","key":"R8","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1016\/j.jhin.2009.10.028","article-title":"Surveillance of surgical site infections by surgeons: biased underreporting or useful epidemiological data?","volume":"75","author":"Rosenthal","journal-title":"J Hosp Infect"},{"issue":"4","key":"R9","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1097\/SLA.0000000000004133","article-title":"Portable automated surveillance of surgical site infections using natural language processing: development and validation","volume":"272","author":"Bucher","journal-title":"Ann Surg"},{"issue":"9","key":"R10","doi-asserted-by":"publisher","first-page":"1160","DOI":"10.1093\/jamia\/ocy075","article-title":"Identifying surgical site infections in electronic health data using predictive models","volume":"25","author":"Grundmeier","journal-title":"J Am Med Inform Assoc"},{"key":"R11","volume":"216","author":"Hu","journal-title":"Stud Health Technol Inform"},{"issue":"5","key":"R12","doi-asserted-by":"publisher","first-page":"695","DOI":"10.1016\/j.spinee.2019.12.006","article-title":"Natural language processing for automated detection of incidental durotomy","volume":"20","author":"Karhade","journal-title":"Spine J"},{"key":"R13","volume":"2019","author":"Shi","journal-title":"AMIA Annu Symp Proc"},{"issue":"8","key":"R14","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0254937","article-title":"Stopwords in technical language processing","volume":"16","author":"Sarica","journal-title":"PLoS One"},{"issue":"5","key":"R15","doi-asserted-by":"publisher","first-page":"1420","DOI":"10.1148\/rg.2021210025","article-title":"Bag-of-words technique in natural language processing: a primer for radiologists","volume":"41","author":"Juluru","journal-title":"Radiographics"},{"issue":"Database issue","key":"R16","doi-asserted-by":"publisher","first-page":"D267","DOI":"10.1093\/nar\/gkh061","article-title":"The Unified Medical Language System (UMLS): integrating biomedical terminology","volume":"32","author":"Bodenreider","journal-title":"Nucleic Acids Res"},{"key":"R17","doi-asserted-by":"crossref","unstructured":"Neumann M King D Beltagy I Ammar W . ScispaCy: fast and robust models for biomedical natural language processing. Presented at: Proceedings of the 18th BioNLP Workshop and Shared Task; 319-327; Florence, Italy. [doi: 10.18653\/v1\/W19-5034]","DOI":"10.18653\/v1\/W19-5034"},{"key":"R18","unstructured":"Mikolov T Chen K Corrado G Dean J . Efficient estimation of word representations in vector space. arXiv. Preprint posted online on Jan 16, 2013. [doi: 10.48550\/arXiv.1301.3781]"},{"key":"R19","doi-asserted-by":"crossref","unstructured":"Alsentzer E Murphy JR Boag W Weng WH Jin D Naumann T . Publicly available clinical BERT embeddings. Presented at: Proceedings of the 2nd Clinical Natural Language Processing Workshop; Jun 7, 2019; Minneapolis, Minnesota, USA. [doi: 10.18653\/v1\/W19-1909]","DOI":"10.18653\/v1\/W19-1909"},{"key":"R20","unstructured":"U.S. Department of Health and Human Services. PART 164\u2014SECURITY AND PRIVACY. Code of Federal Regulations. URL: https:\/\/www.ecfr.gov\/current\/title-45\/subtitle-A\/subchapter-C\/part-164 [Accessed 17-06-2026]"},{"issue":"9","key":"R21","doi-asserted-by":"publisher","first-page":"1773","DOI":"10.1038\/s41591-022-01981-2","article-title":"Multimodal biomedical AI","volume":"28","author":"Acosta","journal-title":"Nat Med"},{"issue":"1","key":"R22","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-021-00444-8","article-title":"Review of deep learning: concepts, CNN architectures, challenges, applications, future directions","volume":"8","author":"Alzubaidi","journal-title":"J Big Data"},{"issue":"3","key":"R23","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1093\/cid\/ciaf619","article-title":"Using generative artificial intelligence for healthcare-associated infection surveillance","volume":"82","author":"Morgan","journal-title":"Clin Infect Dis"},{"issue":"6","key":"R24","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1136\/bmjqs-2025-019493","article-title":"Retrospective validation study of a large language model approach to screening for intraabdominal surgical site infections for quality and safety reporting","volume":"35","author":"Pierce","journal-title":"BMJ Qual Saf"},{"issue":"2","key":"R25","doi-asserted-by":"publisher","first-page":"102627","DOI":"10.1016\/j.jiph.2024.102627","article-title":"Evaluation of ChatGPT-4 for the detection of surgical site infections from electronic health records after colorectal surgery: a pilot diagnostic accuracy study","volume":"18","author":"Badia","journal-title":"J Infect Public Health"},{"key":"R26","unstructured":"Brown TB Mann B Ryder N Subbiah M Kaplan J Dhariwal P et al. Language models are few-shot learners. Presented at: NIPS \u201920: Proceedings of the 34th International Conference on Neural Information Processing Systems; Dec 6-12, 2020; Vancouver, BC, Canada. URL: https:\/\/dl.acm.org\/doi\/abs\/10.5555\/3495724.3495883 [Accessed 06-06-2026]"},{"issue":"7","key":"R27","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1089\/sur.2019.153","article-title":"Technological advances in clinical definition and surveillance methodology for surgical site infection incorporating surgical site imaging and patient-generated health data","volume":"20","author":"Sawyer","journal-title":"Surg Infect (Larchmt)"}],"container-title":["JMIR Perioperative Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/periop.jmir.org\/2026\/1\/e87896","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T22:25:06Z","timestamp":1785536706000},"score":1,"resource":{"primary":{"URL":"https:\/\/periop.jmir.org\/2026\/1\/e87896"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,26]]},"references-count":27,"URL":"https:\/\/doi.org\/10.2196\/87896","relation":{},"ISSN":["2561-9128"],"issn-type":[{"value":"2561-9128","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,26]]},"article-number":"v9i18e87896"}}