{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T06:15:31Z","timestamp":1783577731434,"version":"3.55.0"},"reference-count":42,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:00:00Z","timestamp":1783555200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>In recent years, advancements in our understanding of the pathophysiological mechanisms underlying coronary artery disease (CAD) have introduced new challenges regarding the clinical application of traditional risk scores. While studies suggest that machine learning (ML) algorithms surpass traditional statistical methods in risk prediction, their conclusions are often derived from heterogeneous datasets and varying model structures, which restrict their generalizability and persuasive power.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aims to evaluate the clinical performance of the GRACE, ACEF, and TIMI risk scores, while also enhancing their predictive accuracy through redevelopment utilizing six ML algorithms.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective study was undertaken at the First Hospital of Lanzhou University between January 1, 2019, and December 31, 2020. Six ML algorithms were employed to redevelop the original GRACE, TIMI, and ACEF risk scores. Model performance was evaluated using accuracy, sensitivity, precision, F1-score, the area under the receiver operating characteristic curve (AUROC), and the area under the precision-recall curve (AUPRC).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We retrospectively enrolled 1,682 patients diagnosed with acute myocardial infarction (AMI) who underwent emergency percutaneous coronary intervention (PCI). The derivation cohort from 2019 included 883 patients, among whom 48 (5.4%) experienced death during the follow-up period. The temporal validation cohort from 2020 consisted of 799 patients, with 26 (3.25%) reported deaths. The original GRACE, TIMI, and ACEF scores were validated using derivation data, resulting in AUROC values of 0.84, 0.68, and 0.69, and AUPRC values of 0.49, 0.19, and 0.34, respectively. The redevelopment of ML algorithms significantly enhanced predictive performance, with the ensemble algorithms yielding the most favorable results. The redeveloped GRACE, TIMI, and ACEF models achieved AUROC values of 0.89, 0.75, and 0.91, and AUPRC values of 0.55, 0.50, and 0.50, respectively. Demonstrating superior predictive performance for six-month mortality over the redeveloped ACEF and TIMI scores, the redeveloped GRACE score yielded an AUROC of 0.89 and an AUPRC of 0.32 in temporal validation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This study validated three established risk scores and found that the GRACE score exhibited superior predictive performance for six-month mortality compared to the ACEF and TIMI scores. The redevelopment of these scores using ML techniques significantly enhanced their predictive accuracy. This improvement reflects both the inherent strengths of ML algorithms and the recalibration of parameter weights to better align with contemporary clinical practice.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2026.1838324","type":"journal-article","created":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T05:35:00Z","timestamp":1783575300000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine learning redevelopment of GRACE, ACEF, and TIMI scores for 6-month mortality"],"prefix":"10.3389","volume":"9","author":[{"given":"Bing","family":"Han","sequence":"first","affiliation":[{"name":"Heart Center, The First Hospital of Lanzhou University","place":["Lanzhou, China"]},{"name":"The First Clinical Medical School, Lanzhou University","place":["Lanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaowei","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Cardiology, The Second Xiangya Hospital of Central South University","place":["Changsha, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Guo","sequence":"additional","affiliation":[{"name":"Department of Psychiatry, Qinghai Third People\u2019s Hospital","place":["Xining, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jizhe","family":"Xu","sequence":"additional","affiliation":[{"name":"Heart Center, The First Hospital of Lanzhou University","place":["Lanzhou, China"]},{"name":"The First Clinical Medical School, Lanzhou University","place":["Lanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yixin","family":"Zhang","sequence":"additional","affiliation":[{"name":"The First Clinical Medical School, Lanzhou University","place":["Lanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Heart Center, The First Hospital of Lanzhou University","place":["Lanzhou, China"]},{"name":"The First Clinical Medical School, Lanzhou University","place":["Lanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenqiang","family":"Li","sequence":"additional","affiliation":[{"name":"The First Clinical Medical School, Lanzhou University","place":["Lanzhou, China"]},{"name":"Department of Cardiology, Qinghai Cardio-Cerebrovascular Specialty Hospital","place":["Xining, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,9]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1016\/j.artmed.2007.10.003","article-title":"A decision support system to facilitate management of patients with acute gastrointestinal bleeding","volume":"42","author":"Chu","year":"2008","journal-title":"Artif. Intell. Med."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"1289","DOI":"10.1093\/eurheartj\/ehaa575","article-title":"2020 ESC guidelines for the management of acute coronary syndromes in patients presenting without persistent ST-segment elevation","volume":"42","author":"Collet","year":"2021","journal-title":"Eur. Heart J."},{"key":"ref3","first-page":"2727","article-title":"A validated prediction model for all forms of acute coronary syndrome: estimating the risk of 6-month postdischarge death in an international registry","volume-title":"JAMA","author":"Eagle","year":"2004"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"101210","DOI":"10.1016\/j.ijcha.2023.101210","article-title":"External validation of the GRACE risk score in patients with myocardial infarction in Hungary","volume":"46","author":"Ferenci","year":"2023","journal-title":"IJC Heart Vasc."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1016\/s0140-6736(22)02079-7","article-title":"Machine learning-based marker for coronary artery disease: derivation and validation in two longitudinal cohorts","volume":"401","author":"Forrest","year":"2023","journal-title":"Lancet"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"e073843","DOI":"10.1136\/bmj-2022-073843","article-title":"Effectiveness of GRACE risk score in patients admitted to hospital with non-ST elevation acute coronary syndrome (UKGRIS): parallel group cluster randomised controlled trial","volume":"381","author":"Gale","year":"2023","journal-title":"BMJ"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1097\/mca.0000000000000791","article-title":"Predictive value of the combination of age, creatinine, and ejection fraction score and diabetes in patients with ST-segment elevation myocardial infarction undergoing percutaneous coronary intervention","volume":"31","author":"Gao","year":"2020","journal-title":"Coron. Artery Dis."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"1611","DOI":"10.1016\/s0140-6736(23)00459-2","article-title":"Current concepts in coronary artery revascularisation","volume":"401","author":"Gaudino","year":"2023","journal-title":"Lancet"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"946","DOI":"10.1001\/jamacardio.2023.2741","article-title":"Modification of the GRACE risk score for risk prediction in patients with acute coronary syndromes","volume":"8","author":"Georgiopoulos","year":"2023","journal-title":"JAMA Cardiol."},{"key":"ref10","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1016\/j.ihj.2025.03.010","article-title":"Comparative evaluation of machine learning models versus TIMI score in ST-segment-elevation myocardial infarction patients","volume":"77","author":"Gupta","year":"2025","journal-title":"Indian Heart J."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1093\/eurheartj\/ehad836","article-title":"Merging machine learning and patient preference: a novel tool for risk prediction of percutaneous coronary interventions","volume":"45","author":"Hamilton","year":"2024","journal-title":"Eur. Heart J."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"1105","DOI":"10.1016\/j.amjcard.2016.07.029","article-title":"Performance of the GRACE risk score 2.0 simplified algorithm for predicting 1-year death after hospitalization for an acute coronary syndrome in a contemporary multiracial cohort","volume":"118","author":"Huang","year":"2016","journal-title":"Am. J. Cardiol."},{"key":"ref13","first-page":"2552","article-title":"Performance of the GRACE 2.0 score in patients with type 1 and type 2 myocardial infarction","volume-title":"Eur. Heart J.","author":"Hung","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"e091028","DOI":"10.1136\/bmjopen-2024-091028","article-title":"Assessment of the prognostic performance of TIMI, PAMI, CADILLAC and GRACE scores for short-term major adverse cardiovascular events in patients undergoing emergent percutaneous revascularisation: a prospective observational study","volume":"15","author":"Kumar","year":"2025","journal-title":"BMJ Open"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1001\/jamacardio.2022.0183","article-title":"Assessment of artificial intelligence in echocardiography diagnostics in differentiating takotsubo syndrome from myocardial infarction","volume":"7","author":"Laumer","year":"2022","journal-title":"JAMA Cardiol."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"39271","DOI":"10.31083\/rcm39271","article-title":"Machine learning approach on predictive model establishment for in-hospital mortality in acute myocardial infarction patients post-percutaneous coronary intervention: solutions for databases with dimensionality reduction and class imbalance","volume":"26","author":"Li","year":"","journal-title":"Rev. Cardiovasc. Med."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"1618492","DOI":"10.3389\/frai.2025.1618492","article-title":"Enhancing one-year mortality prediction in STEMI patients post-PCI: an interpretable machine learning model with risk stratification","volume":"8","author":"Li","year":"","journal-title":"Front. Artif. Intell."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"864312","DOI":"10.3389\/fcvm.2022.864312","article-title":"Early prediction of clinical scores for left ventricular reverse remodeling using extreme gradient random forest, boosting, and logistic regression algorithm representations","volume":"9","author":"Liu","year":"2022","journal-title":"Front. Cardiovasc. Med."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"e70077","DOI":"10.1002\/clc.70077","article-title":"Predictive value of lung ultrasound combined with ACEF score for the prognosis of acute myocardial infarction","volume":"48","author":"Lun","year":"2025","journal-title":"Clin. Cardiol."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"113623","DOI":"10.1109\/access.2023.3313977","article-title":"Recent advancements and future prospects in active deep learning for medical image segmentation and classification","volume":"11","author":"Mahmood","year":"2023","journal-title":"IEEE Access"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1186\/s40537-025-01114-9","article-title":"Breast cancer diagnosis with MFF-HistoNet: a multi-modal feature fusion network integrating CNNs and quantum tensor networks","volume":"12","author":"Mahmood","year":"2025","journal-title":"J. Big Data"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"123747","DOI":"10.1016\/j.eswa.2024.123747","article-title":"Harnessing the power of radiomics and deep learning for improved breast cancer diagnosis with multiparametric breast mammography","volume":"249","author":"Mahmood","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"693","DOI":"10.1093\/ehjacc\/zuad081","article-title":"Comparing the utility of clinical risk scores and integrated clinical judgement in patients with suspected acute coronary syndrome","volume":"12","author":"Meier","year":"2023","journal-title":"Eur. Heart J. Acute Cardiovasc. Care"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"106190","DOI":"10.1016\/j.cmpb.2021.106190","article-title":"A review of risk prediction models in cardiovascular disease: conventional approach vs. artificial intelligent approach","volume":"207","author":"Mohd Faizal","year":"2021","journal-title":"Comput. Methods Prog. Biomed."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"170","DOI":"10.5114\/aic.2021.107495","article-title":"Predictive value of the age, creatinine and ejection fraction score in patients undergoing primary percutaneous coronary intervention with bail-out tirofiban therapy","volume":"17","author":"\u00d6sken","year":"2021","journal-title":"Adv. Interv. Cardiol."},{"key":"ref26","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1093\/qjmed\/hcl133","article-title":"Risk prediction in patients presenting with suspected cardiac pain: the GRACE and TIMI risk scores versus clinical evaluation","volume":"100","author":"Ramsay","year":"2006","journal-title":"QJM"},{"key":"ref27","first-page":"4","article-title":"Deep learning for health informatics","volume-title":"IEEE J. Biomed. Health Inform.","author":"Ravi","year":"2017"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"2822","DOI":"10.1016\/j.jacc.2021.01.060","article-title":"Thrombolysis in myocardial infarction (TIMI) study group: JACC focus seminar 2\/8","volume":"77","author":"Sabatine","year":"2021","journal-title":"J. Am. Coll. Cardiol."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"14270","DOI":"10.1038\/s41598-022-16523-6","article-title":"Comparison of the modified Singapore myocardial infarction registry risk score with GRACE 2.0 in predicting 1-year acute myocardial infarction outcomes","volume":"12","author":"Sia","year":"2022","journal-title":"Sci. Rep."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"e70111","DOI":"10.1002\/clc.70111","article-title":"Predictive value of lung ultrasound combined with ACEF score for the prognosis of acute myocardial infarction","volume":"48","author":"Tahir","year":"2025","journal-title":"Clin. Cardiol."},{"key":"ref31","doi-asserted-by":"publisher","first-page":"1399","DOI":"10.1016\/s0140-6736(20)32114-0","article-title":"Redevelopment and validation of the SYNTAX score II to individualise decision making between percutaneous and surgical revascularisation in patients with complex coronary artery disease: secondary analysis of the multicentre randomised controlled SYNTAXES trial with external cohort validation","volume":"396","author":"Takahashi","year":"2020","journal-title":"Lancet"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/j.ahj.2006.10.004","article-title":"Global registry of acute coronary events (GRACE) hospital discharge risk score accurately predicts long-term mortality post acute coronary syndrome","volume":"153","author":"Tang","year":"2007","journal-title":"Am. Heart J."},{"key":"ref33","doi-asserted-by":"publisher","first-page":"e0229186","DOI":"10.1371\/journal.pone.0229186","article-title":"Comparison of the TIMI, GRACE, PAMI and CADILLAC risk scores for prediction of long-term cardiovascular outcomes in Taiwanese diabetic patients with ST-segment elevation myocardial infarction: from the registry of the Taiwan Society of Cardiology","volume":"15","author":"Taniyama","year":"2020","journal-title":"PLoS One"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1016\/s0140-6736(21)00038-6","article-title":"Risk scores in predicting adverse events following acute coronary syndrome","volume":"397","author":"Templin","year":"2021","journal-title":"Lancet"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"1525","DOI":"10.1093\/jamia\/ocac093","article-title":"The harm of class imbalance corrections for risk prediction models: illustration and simulation using logistic regression","volume":"29","author":"van den Goorbergh","year":"2022","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"ref36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2022\/5389072","article-title":"Comparison of different risk scores for prediction of in-hospital mortality in STEMI patients treated with PPCI","volume":"2022","author":"Wang","year":"2022","journal-title":"Emerg. Med. Int."},{"key":"ref37","doi-asserted-by":"publisher","first-page":"5078","DOI":"10.1007\/s12325-021-01908-2","article-title":"Application of artificial intelligence in acute coronary syndrome: a brief literature review","volume":"38","author":"Wang","year":"2021","journal-title":"Adv. Ther."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"744","DOI":"10.1016\/S0140-6736(22)01483-0","article-title":"Sex-specific evaluation and redevelopment of the GRACE score in non-ST-segment elevation acute coronary syndromes in populations from the UK and Switzerland: a multinational analysis with external cohort validation","volume":"400","author":"Wenzl","year":"2022","journal-title":"Lancet"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"2444401","DOI":"10.1080\/0886022x.2024.2444401","article-title":"Age, creatinine, and ejection fraction score is a risk factor for acute kidney injury after surgical aortic valve replacement","volume":"47","author":"Wu","year":"2025","journal-title":"Ren. Fail."},{"key":"ref40","doi-asserted-by":"publisher","first-page":"e096621","DOI":"10.1136\/bmjopen-2024-096621","article-title":"Predictive value of novel inflammatory markers combined with GRACE score for in-hospital outcome in patients with ST-segment elevation myocardial infarction: a retrospective observational study","volume":"15","author":"Xin","year":"2025","journal-title":"BMJ Open"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1186\/s12872-021-02311-z","article-title":"Comparison of GRACE and TIMI risk scores in the prediction of in-hospital and long-term outcomes among east Asian non-ST-elevation myocardial infarction patients","volume":"22","author":"Yanqiao","year":"2022","journal-title":"BMC Cardiovasc. Disord."},{"key":"ref42","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1186\/s41512-021-00102-w","article-title":"A relationship between the incremental values of area under the ROC curve and of area under the precision-recall curve","volume":"5","author":"Zhou","year":"2021","journal-title":"Diagn. Progn. Res."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1838324\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T05:35:01Z","timestamp":1783575301000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1838324\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,9]]},"references-count":42,"alternative-id":["10.3389\/frai.2026.1838324"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1838324","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,9]]},"article-number":"1838324"}}