[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122176-en":3,"doc-seo-122176-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},122176,7971461740886,"Theodore","https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2",8,"Research & Report","Machine Learning for Dynamic and Early Prediction of Acute Kidney Injury After Cardiac Surgery - Research Summary","Acute kidney injury (AKI) after cardiac surgery is linked to higher morbidity and mortality, while standard diagnosis based on oliguria or rising serum creatinine emerges 48–72 hours after injury. This study tests whether machine learning that integrates preoperative, intraoperative, and ICU data can dynamically predict AKI before conventional clinical identification. Using EMR data from cardiac surgery patients (2008–2019), an ensemble model generates hourly forecasts over a 48-hour horizon and is assessed with ROC-AUC and balanced accuracy.","The Texas Medical Center Library  \nDigitalCommons@TMC  \n\n| Faculty and Staff Publications | Baylor College of Medicine |\n| --- | --- |\n| 12-1-2023\u003Cbr>Machine Learning for Dynamic and Early Prediction of Acute Kidney Injury After Cardiac Surgery\u003Cbr>Christopher T Ryan Zijian Zeng Subhasis Chatterjee Matthew J Wall\u003Cbr>Marc R Moon\u003Cbr>See next page for additional authors\u003Cbr>Follow this and additional works at: [https://digitalcommons.library.tmc.edu/baylor_docs](https://digitalcommons.library.tmc.edu/baylor_docs)\u003Cbr> Part of the Cardiology Commons, Cardiovascular Diseases Commons, Medical Sciences Commons, Mental and Social Health Commons, Nephrology Commons, Pathological Conditions, Signs and Symptoms Commons, and the Surgery Commons |  |\n\nAuthors  \nChristopher T Ryan, Zijian Zeng, Subhasis Chatterjee, Matthew J Wall, Marc R Moon, Joseph S Coselli, Todd K Rosengart, Meng Li, and Ravi K Ghanta  \nAuthor Manuscript Author Manuscript Author Manuscript Author Manuscript  \n\n|  | HHS Public Access\u003Cbr>Author manuscript\u003Cbr>J Thorac Cardiovasc Surg. Author manuscript; available in PMC 2024 December 01. |\n| --- | --- |\n\nPublished in final edited form as:  \nJ Thorac Cardiovasc Surg. 2023 December ; 166(6): e551–e564. doi:10.1016/j.jtcvs.2022.09.045 .  \nMachine Learning for Dynamic and Early Prediction of Acute Kidney Injury after Cardiac Surgery  \nChristopher T. Ryan, MD 1 , Zijian Zeng, MS2 , Subhasis Chatterjee, MD 1,3 , Matthew J. Wall, MD 1 , Marc R. Moon 1,3 , Joseph S. Coselli, MD 1,3 , Todd K. Rosengart, MD 1,3 , Meng Li, PhD2 , Ravi K. Ghanta, MD 1  \n1Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, TX  \n2 Rice University, Department of Statistics, Houston, TX  \n3 Department of Cardiovascular Surgery, Texas Heart Institute, Houston, TX  \nAbstract  \nObjective: Acute kidney injury (AKI) after cardiac surgery increases morbidity and mortality.  \nDiagnosis relies on oliguria or increased serum creatinine, which develop 48–72 hours after injury. We hypothesized machine learning (ML) incorporating preoperative, operative, and intensive care unit (ICU) data could dynamically predict AKI before conventional identification.  \nMethods: Cardiac surgery patients at a tertiary hospital (2008–2019) were identified using electronic medical records (EMR) in the MIMIC-IV database. Pre-/intraoperative parameters included demographics, Charlson Comorbidity subcategories, and operative details. ICU data included hemodynamics, medications, fluid intake/output, and laboratory results. KDIGO creatinine criteria were used for AKI diagnosis. An ensemble ML model was trained for hourly predictions of future AKI within 48 hours. Performance was evaluated by area under the receiver operating characteristic curve (ROC-AUC) and balanced accuracy.  \nResults: Within the cohort (n=4,267) there were ~7 million data points. Median baseline creatinine was 1.0 g/dL [IQR 0.8–1.2], with 17%(735/4,267) of patients having chronic kidney disease. Postoperative Stage 1 AKI occurred in 50%(2,129/4,267), Stage 2 in 8%(324/4,267), and Stage 3 in 4%(183/4,267). For hourly prediction of any AKI over the next 48 hours, ROC-AUC was 0.82 and balanced accuracy 75%. For hourly prediction of stage 2 or greater AKI over the next 48 hours, ROC-AUC was 0.95 and balanced accuracy 86%. The model predicted AKI before clinical detection in 89% of cases.  \nCorresponding Author: Ravi K. Ghanta, MD, Michael E. DeBakey Department of Surgery, Baylor College of Medicine. One Baylor Plaza, MC-390, Houston, TX. 77030, [Ravi.Ghanta@bcm.edu](Ravi.Ghanta@bcm.edu).  \nDisclosures: No relevant financial Disclosures  \nIRB approval: H-44702, 12/17/2019 . Requirement for informed consent was waived for analysis of deidentified data.  \nCENTRAL PICTURE LEGEND:  \nDynamic prediction of postoperative acute kidney injury risk after cardiac surgery  \nPublisher's Disclaimer: This is a PDF file of an unedited manuscript that has been accepted for publication. As a service to our customers w","cbCaitqxAUoIxjNv","https://ap.wps.com/l/cbCaitqxAUoIxjNv","pdf",1180939,1,21,"English","en",105,"# Abstract\n## Objective\n## Methods\n## Results\n## Conclusion","[{\"question\":\"Why is early prediction of AKI after cardiac surgery clinically important?\",\"answer\":\"AKI diagnosis based on urine output or serum creatinine typically appears 48–72 hours after injury, which can miss the intervention window. Earlier detection may enable actions such as volume resuscitation and hemodynamic optimization to limit injury.\"},{\"question\":\"What data sources were used to build the machine learning model?\",\"answer\":\"The model used electronic medical record data from preoperative, intraoperative, and ICU settings, including demographics, comorbidity details, operative information, hemodynamics, medications, fluid intake/output, and laboratory results.\"},{\"question\":\"How well did the model predict AKI in hourly forecasts?\",\"answer\":\"For predicting any AKI within the next 48 hours, the model achieved ROC-AUC of 0.82 and balanced accuracy of 75%. For predicting stage 2 or greater AKI, ROC-AUC increased to 0.95 with balanced accuracy of 86%, and AKI was predicted before clinical detection in 89% of cases.\"}]","Machine Learning for Dynamic and Early Prediction of Acute Kidney Injury After Cardiac Surgery - Research Summary | PDF",1785809206,53,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-for-dynamic-and-early-prediction-of-acute-kidney-injury-after-cardiac-surgery-research-summary","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-for-dynamic-and-early-prediction-of-acute-kidney-injury-after-cardiac-surgery-research-summary/122176/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is early prediction of AKI after cardiac surgery clinically important?","Question",{"text":75,"@type":76},"AKI diagnosis based on urine output or serum creatinine typically appears 48–72 hours after injury, which can miss the intervention window. Earlier detection may enable actions such as volume resuscitation and hemodynamic optimization to limit injury.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What data sources were used to build the machine learning model?",{"text":80,"@type":76},"The model used electronic medical record data from preoperative, intraoperative, and ICU settings, including demographics, comorbidity details, operative information, hemodynamics, medications, fluid intake/output, and laboratory results.",{"name":82,"@type":73,"acceptedAnswer":83},"How well did the model predict AKI in hourly forecasts?",{"text":84,"@type":76},"For predicting any AKI within the next 48 hours, the model achieved ROC-AUC of 0.82 and balanced accuracy of 75%. For predicting stage 2 or greater AKI, ROC-AUC increased to 0.95 with balanced accuracy of 86%, and AKI was predicted before clinical detection in 89% of cases.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]