{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T12:48:45Z","timestamp":1792500525697,"version":"4.5.0"},"reference-count":23,"publisher":"SAGE Publications","issue":"3","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Innovations\ufffd(Phila)"],"published-print":{"date-parts":[[2026,5]]},"abstract":"<jats:sec>\n                    <jats:title>Objective:<\/jats:title>\n                    <jats:p>Cardiac surgery carries a significant risk of complications and mortality. Artificial intelligence (AI), particularly machine learning (ML), is increasingly being explored to enhance perioperative risk prediction and support clinical decision-making. This systematic review evaluates the clinical applications, predictive performance, and limitations of AI models in cardiac surgery.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods:<\/jats:title>\n                    <jats:p>PubMed and Embase were searched for studies published between January 2020 and July 2025. Of 939 records identified, 178 studies met the inclusion criteria following screening and full-text review. Included studies applied AI to predict clinical outcomes in patients undergoing cardiac surgery. Key outcomes assessed were model performance metrics and their clinical utility.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results:<\/jats:title>\n                    <jats:p>\n                      Among the 178 included studies, 114 (64%) were conducted in the United States or China. Most studies (\n                      <jats:italic toggle=\"yes\">n<\/jats:italic>\n                      = 168, 94%) used retrospective designs and focused on adult populations. Random forest (\n                      <jats:italic toggle=\"yes\">n<\/jats:italic>\n                      = 82, 46%), logistic regression (\n                      <jats:italic toggle=\"yes\">n<\/jats:italic>\n                      = 82, 46%), and eXtreme Gradient Boosting (\n                      <jats:italic toggle=\"yes\">n<\/jats:italic>\n                      = 70, 39%) were the most frequently used algorithms. AI applications primarily targeted the prediction of postoperative complications (\n                      <jats:italic toggle=\"yes\">n<\/jats:italic>\n                      = 102, 57%) and mortality (\n                      <jats:italic toggle=\"yes\">n<\/jats:italic>\n                      = 70, 39%), with common outcomes including acute kidney injury and stroke. ML models consistently outperformed traditional clinical risk scores (\n                      <jats:italic toggle=\"yes\">n<\/jats:italic>\n                      = 39). SHapley Additive exPlanations was the most common interpretability method (\n                      <jats:italic toggle=\"yes\">n<\/jats:italic>\n                      = 66, 37%). Only 26% of studies included external validation, and just 19% adhered to TRIPOD guidelines.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions:<\/jats:title>\n                    <jats:p>AI models demonstrate superior predictive performance in cardiac surgery compared with traditional risk scores, but concerns regarding validation, transparency, and generalizability must be addressed to enable implementation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1177\/15569845261457046","type":"journal-article","created":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T06:05:18Z","timestamp":1784009118000},"page":"210-216","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["Artificial Intelligence for Predicting Perioperative Outcomes in Cardiac Surgery: A Systematic Review"],"prefix":"10.1177","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1719-5543","authenticated-orcid":false,"given":"Jason","family":"Ha","sequence":"first","affiliation":[{"name":"University of Bristol, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hunaid A.","family":"Vohra","sequence":"additional","affiliation":[{"name":"University of Bristol, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2026,7,13]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.atssr.2023.11.019"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.hlc.2015.12.094"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2021.771607"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1097\/SLA.0000000000002693"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2023-078378"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1097\/JTO.0b013e3181ec173d"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1159\/000339789"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1093\/ejcts\/ezaa229"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00392-020-01691-0"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-82403-0"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2022.37970"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCOUTCOMES.120.007363"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.2196\/41142"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.21037\/jtd-24-711"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1002\/clc.23963"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1111\/jocs.16072"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.athoracsur.2011.09.010"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00392-009-0010-8"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1097\/JS9.0000000000002032"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13037-025-00458-8"},{"key":"e_1_3_2_22_2","unstructured":"SCTS. EuroSCORE 3 https:\/\/scts.org\/news\/599\/euroscore_3\/ (2023 accessed 21 December 2025)."},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12916-024-03273-7"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1093\/eurheartj\/ehad727"}],"container-title":["Innovations: Technology and Techniques in Cardiothoracic and Vascular Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/15569845261457046","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/15569845261457046","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/15569845261457046","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T12:19:03Z","timestamp":1792498743000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/15569845261457046"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":23,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["10.1177\/15569845261457046"],"URL":"https:\/\/doi.org\/10.1177\/15569845261457046","relation":{},"ISSN":["1556-9845","1559-0879"],"issn-type":[{"value":"1556-9845","type":"print"},{"value":"1559-0879","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}