{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T07:02:42Z","timestamp":1779692562885,"version":"3.53.1"},"reference-count":29,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T00:00:00Z","timestamp":1779667200000},"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>Kawasaki disease (KD) is an acute systemic vasculitis predominantly affecting children under 5 years of age. Its pathogenesis remains incompletely understood, and the lack of specific diagnostic biomarkers during the acute phase poses substantial challenges to clinical diagnosis. Such diagnostic uncertainty often results in missed or delayed cases, leading to lost therapeutic opportunities and the subsequent development of coronary artery lesions (CAL). The present study aimed to establish a machine learning\u2013based diagnostic model to optimize the KD diagnostic workflow, enable early identification, and reduce the incidence of CAL.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We retrospectively analyzed Pre-treatment clinical data from 4,469 patients admitted to Kunming Children\u2019s Hospital between January 2017 and December 2023, including 2,345 patients diagnosed with Kawasaki disease (case group) and 2,124 febrile non-KD patients (control group). A Light Gradient Boosting Machine (LightGBM) algorithm was employed to develop a diagnostic model for KD. Model performance was assessed using the area under the receiver operating characteristic curve (AUC), as well as accuracy, sensitivity, and specificity calculated from the confusion matrix at a classification threshold of 0.5. SHapley Additive exPlanations (SHAP) analysis was performed to identify key predictive features and interpret the model\u2019s decision-making mechanism. On the basis of SHAP-derived feature importance and clinical availability, six core variables were selected to establish a simplified diagnostic model, which was further deployed as an offline application.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The full-feature LightGBM model achieved an outstanding area under the receiver operating characteristic curve (AUC) of 0.9956. At a classification threshold of 0.5, the confusion matrix yielded an accuracy of 0.9653, a sensitivity of 0.9596, and a specificity of 0.9717. SHAP analysis revealed that C-reactive protein (CRP), activated partial thromboplastin time (APTT), total calcium (Ca\n                      <jats:sup>2+<\/jats:sup>\n                      ), erythrocyte sedimentation rate (ESR), serum chloride (Cl\n                      <jats:sup>\u2212<\/jats:sup>\n                      ), and several other variables exhibited strong predictive value. To achieve an optimal balance between predictive performance and clinical applicability, six core variables were selected: white blood cell count (WBC), platelet count (PLT), CRP, APTT, thrombin time (TT), and albumin (ALB). The simplified LightGBM model constructed using these parameters achieved an AUC of 0.9792; at the 0.5 classification threshold, it demonstrated an accuracy of 0.9340, a sensitivity of 0.9277, and a specificity of 0.9410, indicating robust discriminative capacity. Finally, an offline executable application was developed to support clinicians\u2014especially those in primary care settings\u2014in achieving rapid and accurate early diagnosis of KD.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Machine learning approaches enable effective simplification of the diagnostic process for KD. The predictive model constructed on the basis of WBC, PLT, CRP, APTT, TT, and ALB shows high diagnostic efficacy and favorable clinical applicability.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2026.1776007","type":"journal-article","created":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T06:04:59Z","timestamp":1779689099000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Study of a Kawasaki disease diagnostic prediction model based on the LightGBM machine learning algorithm"],"prefix":"10.3389","volume":"9","author":[{"given":"Hongyan","family":"Li","sequence":"first","affiliation":[{"name":"Department of Cardiology, Kunming Children\u2019s Hospital","place":["Kunming, Yunnan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yushan","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Science and Education, Kunming Children\u2019s Hospital","place":["Kunming, Yunnan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuxiong","family":"Gong","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Kunming Children\u2019s Hospital","place":["Kunming, Yunnan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Xiao","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Kunming Children\u2019s Hospital","place":["Kunming, Yunnan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongjian","family":"Su","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Kunming Children\u2019s Hospital","place":["Kunming, Yunnan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linfei","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Kunming Children\u2019s Hospital","place":["Kunming, Yunnan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Kunming Children\u2019s Hospital","place":["Kunming, Yunnan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"LiLi","family":"Deng","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Kunming Children\u2019s Hospital","place":["Kunming, Yunnan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Kunming Children\u2019s Hospital","place":["Kunming, Yunnan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanfei","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Kunming Children\u2019s Hospital","place":["Kunming, Yunnan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Kunming Children\u2019s Hospital","place":["Kunming, Yunnan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,5,25]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"110042","DOI":"10.1016\/j.jclinane.2020.110042","article-title":"Prediction models using machine learning:the focus remains on prevention","volume":"67","author":"Argalious","year":"2020","journal-title":"J. Clin. Anesth."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1007\/978-1-62703-748-8_7","article-title":"Introduction to machine learning","volume":"1107","author":"Ba\u015ftanlar","year":"2013","journal-title":"Methods Mol. Biol."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1016\/S0140-6736(03)12328-8","article-title":"Primary brain tumours in adults","volume":"361","author":"Behin","year":"2003","journal-title":"Lancet"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"4884","DOI":"10.1002\/14651858.CD014884.pub2","article-title":"Intravenous immunoglobulin for the treatment of Kawasaki disease","volume":"2023","author":"Broderick","year":"2023","journal-title":"Cochrane Database Syst. Rev."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"234","DOI":"10.5498\/wjp.v10.i10.234","article-title":"Development of a depression in Parkinson's disease prediction model using machine learning","volume":"10","author":"Byeon","year":"2020","journal-title":"World J Psychiatry"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"121","DOI":"10.5152\/TurkArchPediatr.2024.24002","article-title":"Artificial intelligence in pediatrics: learning to walk together","volume":"59","author":"Can Demirba\u015f","year":"2024","journal-title":"Turk Arch Pediatr."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"229","DOI":"10.3390\/jimaging8090229","article-title":"Shapley-additive explanations-based factor analysis for dengue severity prediction using machine learning","volume":"8","author":"Chowdhury","year":"2022","journal-title":"J. Imaging."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"76","DOI":"10.5206\/uwomj.v86i2.2060","article-title":"Machine learning in medicine","volume":"86","author":"Deo","year":"2015","journal-title":"Circulation"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"e2455251","DOI":"10.1001\/jamanetworkopen.2024.55251","article-title":"Use of albumin-adjusted calcium measurements in clinical practice","volume":"8","author":"Desgagn\u00e9s","year":"2025","journal-title":"JAMA Netw. Open"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"7927","DOI":"10.1038\/s41598-025-92277-1","article-title":"An interpretable machine learningassisted diagnostic model for Kawasaki disease in children","volume":"15","author":"Duan","year":"2025","journal-title":"Sci. Rep."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"525","DOI":"10.3389\/fped.2020.00525","article-title":"Neonatal sepsis diagnosis decision-making based on artificial neural networks","volume":"8","author":"Helguera-Repetto","year":"2020","journal-title":"Front. Pediatr."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"e481","DOI":"10.1161\/CIR.0000000000001295","article-title":"Update on diagnosis and management of Kawasaki disease: a scientific statement from the American Heart Association","volume":"150","author":"Jone","year":"2024","journal-title":"Circulation"},{"key":"ref13","first-page":"178","article-title":"Acute febrile mucocutaneous syndrome with lymphoid involvement with specific desquamation of the fingers and toes in children","volume":"16","author":"Kawasaki","year":"1967","journal-title":"Arerugi"},{"key":"ref14","first-page":"1","article-title":"Lightgbm: a highly efficient gradient boosting decision tree","volume":"30","author":"Ke","year":"2017","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1135","DOI":"10.1111\/ped.14326","article-title":"Revision of diagnosticguidelines for Kawasaki disease","volume":"62","author":"Kobayashi","year":"2020","journal-title":"PediatrInt."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1186\/s12887-024-04623-3","article-title":"Risk factors and scores for prediction of coronary artery aneurysms in Kawasaki disease: a European monocentric study","volume":"24","author":"La Vecchia","year":"2024","journal-title":"BMC Pediatr."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"620","DOI":"10.1080\/01443615.2021.1945006","article-title":"LightGBM: an efficient and accurate method for predicting pregnancy diseases","volume":"42","author":"Liao","year":"2022","journal-title":"J. Obstetr. Gynaecol."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1186\/s12859-022-04618-w","article-title":"Interpretable prediction of necrotizing enterocolitis from machine learning analysis of premature infant stool microbiota","volume":"23","author":"Lin","year":"2022","journal-title":"BMC Bioinformatics."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1038\/s41572-021-00332-8","article-title":"Juvenile idiopathic arthritis","volume":"8","author":"Martini","year":"2022","journal-title":"Nat. Rev. Dis. Prim."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1097\/CCM.0000000000005294","article-title":"Criteria for pediatric sepsis\u2014a systematic review and meta-analysis by the pediatric sepsis definition taskforce","volume":"50","author":"Menon","year":"2022","journal-title":"Crit. Care Med."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"172","DOI":"10.5152\/TurkArchPediatr.2025.24248","article-title":"Pharmacoeconomic analysis and considerations for the Management of Kawasaki Disease in the Arab countries-a multinational, multi-institutional project of the Kawasaki disease Arab initiative (Kawarabi) (a project methodology paper)","volume":"60","author":"Nait-Ladjemil","year":"2025","journal-title":"Turk Arch Pediatr."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"1633","DOI":"10.1056\/NEJM199106063242305","article-title":"A single intravenous infusion of gamma globulin as compared with four infusions in the treatment of acuteKawasaki syndrome","volume":"324","author":"Newburger","year":"1991","journal-title":"N. Engl. J. Med."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"1453","DOI":"10.1111\/1756-185X.14816","article-title":"An update on understanding the pathophysiology in Kawasaki disease: possible role of im-mune complexes in coronary arteryl esion revisited","volume":"26","author":"Philip","year":"2023","journal-title":"Int. J. Rheum. Dis."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1016\/j.yjmcc.2025.01.005","article-title":"MFN2-mediated decrease in mitochondria-associated endoplasmic reticulum membranes con-tributes to sunitinib-induced endothelial dysfunction and hyper-tension","volume":"200","author":"Qu","year":"2025","journal-title":"J. Mol. Cell. Cardiol."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"450","DOI":"10.1067\/mpd.2002.122469","article-title":"Early treatment with intravenous immunoglobulin in patientswith Kawasaki disease","volume":"140","author":"Tse","year":"2023","journal-title":"J. Pediatr."},{"key":"ref26","doi-asserted-by":"publisher","first-page":"865","DOI":"10.1017\/S1047951120004989","article-title":"Rare case of Kawasaki disease with cardiac tamponade and giant coronary artery aneurysms","volume":"31","author":"Vergara","year":"2021","journal-title":"Cardiol. Young"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"297","DOI":"10.3969\/j.issn.1007-5410.2023.04.001","article-title":"Interpretation of report on cardiovascular health and diseases in China 2022","volume":"28","author":"Wang","year":"2023","journal-title":"Chin J Cardiovasc Med."},{"key":"ref28","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1016\/j.ins.2022.04.058","article-title":"Corporate finance risk prediction based on LightGBM","volume":"602","author":"Wang","year":"2022","journal-title":"Inf. Sci."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"6799","DOI":"10.1038\/s41598-025-90919-y","article-title":"Machine learning for early diagnosis of Kawasaki disease in acute febrile children: retrospective cross-sectional study in China","volume":"15","author":"Zheng","year":"2025","journal-title":"Sci. Rep."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1776007\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T06:05:01Z","timestamp":1779689101000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1776007\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,25]]},"references-count":29,"alternative-id":["10.3389\/frai.2026.1776007"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1776007","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,25]]},"article-number":"1776007"}}