{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T09:38:07Z","timestamp":1792661887921,"version":"4.5.0"},"reference-count":23,"publisher":"Public Library of Science (PLoS)","issue":"4","license":[{"start":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T00:00:00Z","timestamp":1745884800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003625","name":"Ministry of Health and Welfare","doi-asserted-by":"publisher","award":["HI21C1138"],"award-info":[{"award-number":["HI21C1138"]}],"id":[{"id":"10.13039\/501100003625","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT, South Korea","doi-asserted-by":"publisher","award":["RS-2022-00143911"],"award-info":[{"award-number":["RS-2022-00143911"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosmedicine.org"],"crossmark-restriction":false},"short-container-title":["PLoS Med"],"abstract":"<jats:sec id=\"sec024\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Postoperative acute kidney injury (PO-AKI) prediction models for non-cardiac major surgeries typically rely solely on preoperative clinical characteristics.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec025\">\n                    <jats:title>Methods and findings<\/jats:title>\n                    <jats:p>In this study, we developed and externally validated a deep-learning-based model that integrates preoperative data with minute-scale intraoperative vital signs to predict PO-AKI. Using data from three hospitals, we constructed a convolutional neural network-based EfficientNet framework to analyze intraoperative data and created an ensemble model incorporating 103 baseline variables of demographics, medication use, comorbidities, and surgery-related characteristics. Model performance was compared with the conventional SPARK model from a previous study. Among 110,696 patients, 51,345 were included in the development cohort, and 59,351 in the external validation cohorts. The median age of the cohorts was 60, 61, and 66 years, respectively, with males comprising 54.9%, 50.8%, and 42.7% of each cohort. The intraoperative vital sign-based model demonstrated comparable predictive power (AUROC (Area Under the Receiver Operating Characteristic Curve): discovery cohort 0.707, validation cohort 0.637 and 0.607) to preoperative-only models (AUROC: discovery cohort 0.724, validation cohort 0.697 and 0.745). Adding 11 key clinical variables (e.g., age, sex, estimated glomerular filtration rate (eGFR), albuminuria, hyponatremia, hypoalbuminemia, anemia, diabetes, renin-angiotensin-aldosterone inhibitors, emergency surgery, and the estimated surgery time) improved the model\u2019s performance (AUROC: discovery cohort 0.765, validation cohort 0.716 and 0.761). The ensembled deep-learning model integrating both preoperative and intraoperative data achieved the highest predictive accuracy (AUROC: discovery cohort 0.795, validation cohort 0.762 and 0.786), outperforming the conventional SPARK model. The retrospective design in a single-nation cohort with non-inclusion of some potential AKI-associated variables is the main limitation of this study.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec026\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This deep-learning-based PO-AKI risk prediction model provides a comprehensive approach to evaluating PO-AKI risk prediction by combining preoperative clinical data with real-time intraoperative vital sign information, offering enhanced predictive performance for better clinical decision-making.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pmed.1004566","type":"journal-article","created":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T13:33:37Z","timestamp":1745933617000},"page":"e1004566","update-policy":"https:\/\/doi.org\/10.1371\/journal.pmed.corrections_policy","source":"Crossref","is-referenced-by-count":8,"title":["A deep-learning algorithm using real-time collected intraoperative vital sign signals for predicting acute kidney injury after major non-cardiac surgeries: A modelling study"],"prefix":"10.1371","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4221-2453","authenticated-orcid":true,"given":"Sehoon","family":"Park","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soomin","family":"Chung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yisak","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6332-5396","authenticated-orcid":true,"given":"Sun-Ah","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0878-5469","authenticated-orcid":true,"given":"Soie","family":"Kwon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeong Min","family":"Cho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2429-1568","authenticated-orcid":true,"given":"Min Jae","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7848-2642","authenticated-orcid":true,"given":"Eunbyeol","family":"Cho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiwon","family":"Ryu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sejoong","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3199-635X","authenticated-orcid":true,"given":"Jeonghwan","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4432-4894","authenticated-orcid":true,"given":"Hyung Jin","family":"Yoon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5958-3509","authenticated-orcid":true,"given":"Edward","family":"Choi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kwangsoo","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1873-1587","authenticated-orcid":true,"given":"Hajeong","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,4,29]]},"reference":[{"issue":"6","key":"pmed.1004566.ref001","doi-asserted-by":"crossref","first-page":"872","DOI":"10.1053\/j.ajkd.2015.07.022","article-title":"Acute kidney injury after major surgery: a retrospective analysis of veterans health administration data","volume":"67","author":"ME Grams","year":"2016","journal-title":"Am J Kidney Dis"},{"issue":"1","key":"pmed.1004566.ref002","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1016\/j.amjsurg.2013.04.006","article-title":"Incidence, risk factors, and outcomes of perioperative acute kidney injury in noncardiac and nonvascular surgery","volume":"207","author":"M Biteker","year":"2014","journal-title":"Am J Surg"},{"key":"pmed.1004566.ref003","doi-asserted-by":"crossref","first-page":"h5639","DOI":"10.1136\/bmj.h5639","article-title":"Risk of postoperative acute kidney injury in patients undergoing orthopaedic surgery\u2013development and validation of a risk score and effect of acute kidney injury on survival: observational cohort study","volume":"351","author":"S Bell","year":"2015","journal-title":"BMJ"},{"issue":"1","key":"pmed.1004566.ref004","doi-asserted-by":"crossref","first-page":"170","DOI":"10.1681\/ASN.2018070757","article-title":"Simple postoperative AKI risk (SPARK) classification before noncardiac surgery: a prediction index development study with external validation","volume":"30","author":"S Park","year":"2019","journal-title":"J Am Soc Nephrol"},{"issue":"1","key":"pmed.1004566.ref005","doi-asserted-by":"crossref","first-page":"35","DOI":"10.2215\/CJN.06620619","article-title":"Intraoperative arterial pressure variability and postoperative acute kidney injury","volume":"15","author":"S Park","year":"2020","journal-title":"Clin J Am Soc Nephrol"},{"issue":"11","key":"pmed.1004566.ref006","doi-asserted-by":"crossref","first-page":"1174","DOI":"10.1111\/j.1365-2044.2008.05604.x","article-title":"Development of a risk stratification model for predicting acute renal failure in orthotopic liver transplantation recipients","volume":"63","author":"A Rueggeberg","year":"2008","journal-title":"Anaesthesia"},{"issue":"2","key":"pmed.1004566.ref007","doi-asserted-by":"crossref","first-page":"2266458","DOI":"10.1080\/07853890.2023.2266458","article-title":"Incorporating intraoperative blood pressure time-series variables to assist in prediction of acute kidney injury after type a acute aortic dissection repair: an interpretable machine learning model","volume":"55","author":"A Dai","year":"2023","journal-title":"Ann Med"},{"issue":"21","key":"pmed.1004566.ref008","doi-asserted-by":"crossref","first-page":"6264","DOI":"10.3390\/jcm11216264","article-title":"Explainable preoperative automated machine learning prediction model for cardiac surgery-associated acute kidney injury","volume":"11","author":"C Thongprayoon","year":"2022","journal-title":"J Clin Med"},{"issue":"5","key":"pmed.1004566.ref009","doi-asserted-by":"crossref","first-page":"e2313359","DOI":"10.1001\/jamanetworkopen.2023.13359","article-title":"Characterization of risk prediction models for acute kidney injury: a systematic review and meta-analysis","volume":"6","author":"Y Feng","year":"2023","journal-title":"JAMA Netw Open"},{"issue":"2","key":"pmed.1004566.ref010","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1097\/01.anes.0000270724.40897.8e","article-title":"Incidence of intraoperative hypotension as a function of the chosen definition: literature definitions applied to a retrospective cohort using automated data collection","volume":"107","author":"JB Bijker","year":"2007","journal-title":"Anesthesiology"},{"key":"pmed.1004566.ref011","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1016\/j.amjsurg.2024.02.001","article-title":"Intraoperative hypotension and postoperative acute kidney injury: a systematic review","volume":"232","author":"Y Penev","year":"2024","journal-title":"Am J Surg"},{"issue":"3","key":"pmed.1004566.ref012","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1097\/ALN.0b013e3182a10e26","article-title":"Relationship between intraoperative mean arterial pressure and clinical outcomes after noncardiac surgery: toward an empirical definition of hypotension","volume":"119","author":"M Walsh","year":"2013","journal-title":"Anesthesiology"},{"issue":"1","key":"pmed.1004566.ref013","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1097\/ALN.0000000000001432","article-title":"Relationship between intraoperative hypotension, defined by either reduction from baseline or absolute thresholds, and acute kidney and myocardial injury after noncardiac surgery: a retrospective cohort analysis","volume":"126","author":"V Salmasi","year":"2017","journal-title":"Anesthesiology"},{"issue":"4","key":"pmed.1004566.ref014","doi-asserted-by":"crossref","first-page":"e0214904","DOI":"10.1371\/journal.pone.0214904","article-title":"Improved predictive models for acute kidney injury with IDEA: intraoperative data embedded analytics","volume":"14","author":"L Adhikari","year":"2019","journal-title":"PLoS One"},{"issue":"9","key":"pmed.1004566.ref015","doi-asserted-by":"crossref","first-page":"604","DOI":"10.7326\/0003-4819-150-9-200905050-00006","article-title":"A new equation to estimate glomerular filtration rate","volume":"150","author":"AS Levey","year":"2009","journal-title":"Ann Intern Med"},{"issue":"9","key":"pmed.1004566.ref016","doi-asserted-by":"crossref","first-page":"605","DOI":"10.1038\/s41581-021-00418-2","article-title":"Postoperative acute kidney injury in adult non-cardiac surgery: joint consensus report of the acute disease quality initiative and perioperative quality initiative","volume":"17","author":"JR Prowle","year":"2021","journal-title":"Nat Rev Nephrol"},{"issue":"1","key":"pmed.1004566.ref017","first-page":"6","article-title":"KDIGO clinical practice guideline for acute kidney injury","volume":"2","author":"KAW Group","year":"2012","journal-title":"Kidney Int Suppl"},{"key":"pmed.1004566.ref018","first-page":"3319","article-title":"Axiomatic attribution for deep networks.","volume-title":"Proceedings of the 34th International Conference on Machine Learning; Proceedings of Machine Learning Research: PMLR","author":"M Sundararajan","year":"2017"},{"issue":"3","key":"pmed.1004566.ref019","doi-asserted-by":"crossref","first-page":"837","DOI":"10.2307\/2531595","article-title":"Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach","volume":"44","author":"ER DeLong","year":"1988","journal-title":"Biometrics"},{"issue":"1","key":"pmed.1004566.ref020","doi-asserted-by":"crossref","first-page":"478","DOI":"10.1186\/s13054-020-03179-9","article-title":"Prediction of the development of acute kidney injury following cardiac surgery by machine learning","volume":"24","author":"P-Y Tseng","year":"2020","journal-title":"Crit Care"},{"issue":"1","key":"pmed.1004566.ref021","doi-asserted-by":"crossref","first-page":"3739","DOI":"10.1038\/s41467-023-39474-6","article-title":"Predicting in-hospital outcomes of patients with acute kidney injury","volume":"14","author":"C Wu","year":"2023","journal-title":"Nat Commun"},{"key":"pmed.1004566.ref022","doi-asserted-by":"crossref","first-page":"104393","DOI":"10.1016\/j.jbi.2023.104393","article-title":"Identifying acute kidney injury subphenotypes using an outcome-driven deep-learning approach","volume":"143","author":"Y Tan","year":"2023","journal-title":"J Biomed Inform"},{"issue":"1","key":"pmed.1004566.ref023","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1186\/s40537-021-00444-8","article-title":"Review of deep learning: concepts, CNN architectures, challenges, applications, future directions","volume":"8","author":"L Alzubaidi","year":"2021","journal-title":"J Big Data"}],"container-title":["PLOS Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pmed.1004566","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T10:18:44Z","timestamp":1747045124000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pmed.1004566"}},"subtitle":[],"editor":[{"given":"Maarten W.","family":"Taal","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,4,29]]},"references-count":23,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,4,29]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pmed.1004566","relation":{},"ISSN":["1549-1676"],"issn-type":[{"value":"1549-1676","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,29]]}}}