{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T02:32:02Z","timestamp":1787797922229,"version":"build-2784847793"},"reference-count":31,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"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. Med."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Sudden sensorineural hearing loss (SSNHL) is a common otologic emergency with variable prognosis. Reliable prognostic tools, particularly for patients undergoing integrated therapy, remain scarce.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective study enrolled 227 patients with unilateral SSNHL of the Qi stagnation and blood stasis syndrome who received standardized integrated therapy. Patients were partitioned into training (70%) and validation (30%) sets via outcome-based stratified sampling. To prevent information leakage, all preprocessing and feature selection were conducted strictly within the training set. Eight machine learning models were optimized through five-fold cross-validation (primary metric: AUC). Model performance was systematically evaluated across discrimination, calibration, and clinical utility, with SHapley Additive ExPlanations (SHAP) analysis applied to quantify interpretability and identify key prognostic predictors.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The XGBoost model demonstrated superior performance in the validation set (AUC: 0.718; 95% CI: 0.590\u20130.846), with robust calibration and positive clinical net benefit. SHAP analysis identified four key predictors: activated partial thromboplastin time (APTT), disease duration, platelet count (PLT), and total protein (TP). Non-linear interpretability revealed distinct prognostic thresholds: a critical intervention window was identified within 10\u202fdays of symptom onset; optimal recovery was associated with PLT counts of 200\u2013250\u202f\u00d7\u202f10\n                      <jats:sup>9<\/jats:sup>\n                      \/L (risk increased &amp;gt;300\u202f\u00d7\u202f10\n                      <jats:sup>9<\/jats:sup>\n                      \/L) and APTT values of 25\u201330\u202fs (&amp;lt;25\u202fs indicated higher failure risk). Furthermore, TP exhibited a tri-phasic association, with peak prognostic probability at 65\u201375\u202fg\/L, whereas hypoproteinemia (&amp;lt;60\u202fg\/L) and elevated levels (&amp;gt;75\u202fg\/L) correlated with reduced recovery likelihood.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This study developed an explainable XGBoost-based model, providing an initial framework for prognostic prediction in SSNHL patients. It demonstrates the integration of machine learning with TCM-informed therapy, suggesting potential pathways for personalized care. While promising, the results should be interpreted with caution due to the lack of external validation. Further multicenter prospective studies are crucial to confirm the model\u2019s generalizability and validate the identified biological predictors.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1845137","type":"journal-article","created":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T04:18:20Z","timestamp":1780287500000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["An explainable machine learning model for prognosis prediction in sudden sensorineural hearing loss under integrated therapy"],"prefix":"10.3389","volume":"13","author":[{"given":"Xiaoxiao","family":"Ye","sequence":"first","affiliation":[{"name":"Faculty of Chinese Medicine, Macau University of Science and Technology","place":["Taipa, Macao SAR, China"]},{"name":"Department of Otolaryngology-Head and Neck Surgery, Zhuhai Hospital of Integrated Traditional Chinese and Western Medicine","place":["Zhuhai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxin","family":"Deng","sequence":"additional","affiliation":[{"name":"Faculty of Chinese Medicine, Macau University of Science and Technology","place":["Taipa, Macao SAR, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Binbin","family":"Xiong","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology-Head and Neck Surgery, Zhuhai Hospital of Integrated Traditional Chinese and Western Medicine","place":["Zhuhai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Chen","sequence":"additional","affiliation":[{"name":"Faculty of Chinese Medicine, Macau University of Science and Technology","place":["Taipa, Macao SAR, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Chen","sequence":"additional","affiliation":[{"name":"Faculty of Chinese Medicine, Macau University of Science and Technology","place":["Taipa, Macao SAR, China"]},{"name":"Department of Otolaryngology-Head and Neck Surgery, Zhuhai Hospital of Integrated Traditional Chinese and Western Medicine","place":["Zhuhai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Huang","sequence":"additional","affiliation":[{"name":"Faculty of Chinese Medicine, Macau University of Science and Technology","place":["Taipa, Macao SAR, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,1]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"443","DOI":"10.3760\/cma.j.issn.1673-0860.2015.06.002","article-title":"Clinical practice guideline for the diagnosis and treatment of sudden sensorineural hearing loss (2015)","volume":"50","year":"2015","journal-title":"Chin J Otorhinolaryngol Head Neck Surg"},{"key":"ref2","first-page":"87","volume-title":"Chinese Otorhinolaryngology","author":"Liu","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"378","DOI":"10.12677\/TCM.2024.133059","article-title":"Treatment of refractory sudden deafness (qi stagnation and blood stasis type) based on \u201cTongqiao Huoxue method.\u201d","volume":"13","author":"Chen","year":"2024","journal-title":"Traditional Chinese Medicine"},{"key":"ref4","first-page":"636","article-title":"Cochlear ischemia induced by circulating iron particles under magnetic control: an animal model for sudden hearing loss","volume":"21","author":"Schweinfurth","year":"2000","journal-title":"Am J Otol"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.heares.2011.08.006","article-title":"Physiopathology of the cochlear microcirculation","volume":"282","author":"Shi","year":"2011","journal-title":"Hear Res"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"5221","DOI":"10.1038\/s41598-023-32085-7","article-title":"Etiological analysis of patients with sudden sensorineural hearing loss: a prospective case-control study","volume":"13","author":"Xie","year":"2023","journal-title":"Sci Rep"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"hcag021","DOI":"10.1093\/qjmed\/hcag021","article-title":"Acupuncture combined with intratympanic dexamethasone for sudden sensorineural hearing loss: a randomised controlled trial","author":"Yang","year":"2026","journal-title":"QJM"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"242","DOI":"10.2471\/BLT.21.285643","article-title":"The world report on hearing, 2021","volume":"99","author":"Chadha","year":"2021","journal-title":"Bull World Health Organ"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1177\/0194599819859885","article-title":"Clinical practice guideline: sudden hearing loss (update)","volume":"161","author":"Chandrasekhar","year":"2019","journal-title":"Otolaryngol Head Neck Surg"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"754","DOI":"10.1177\/00034894251344767","article-title":"Exploring research challenges in the study of sudden sensorineural hearing loss: an investigation utilizing a large single clinical practice database","volume":"134","author":"Hodge","year":"2025","journal-title":"Ann Otol Rhinol Laryngol"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"2071","DOI":"10.1001\/jama.2011.679","article-title":"Oral vs intratympanic corticosteroid therapy for idiopathic sudden sensorineural hearing loss: a randomized trial","volume":"305","author":"Rauch","year":"2011","journal-title":"JAMA"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"751","DOI":"10.1016\/j.ccc.2023.02.003","article-title":"Making the improbable possible: generalizing models designed for a syndrome-based, heterogeneous patient landscape","volume":"39","author":"Le","year":"2023","journal-title":"Crit Care Clin"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"1444763","DOI":"10.3389\/frobt.2024.1444763","article-title":"Enhancing interpretability and accuracy of AI models in healthcare: a comprehensive review on challenges and future directions","volume":"11","author":"Ennab","year":"2024","journal-title":"Front Robot AI"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"101087","DOI":"10.1016\/j.imr.2024.101087","article-title":"The efficacy and safety of acupuncture in the treatment of sudden sensorineural hearing loss: a systematic review and meta-analysis","volume":"13","author":"Ren","year":"2024","journal-title":"Integrat Med Res"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat Mach Intell"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"1212","DOI":"10.1152\/jn.00058.2023","article-title":"Correlation of coagulation states with prognosis of sudden deafness","volume":"129","author":"Zhang","year":"2023","journal-title":"J Neurophysiol"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"3631","DOI":"10.1182\/blood-2004-03-1042","article-title":"A shortened activated partial thromboplastin time is associated with the risk of venous thromboembolism","volume":"104","author":"Tripodi","year":"2004","journal-title":"Blood"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1111\/j.1538-7836.2011.04600.x","article-title":"Dynamic APTT parameters: applications in thrombophilia","volume":"10","author":"S\u00f8rensen","year":"2012","journal-title":"J Thromb Haemost"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"464","DOI":"10.1097\/MAO.0b013e31816fdcb4","article-title":"Prognostic model for predicting hearing recovery in idiopathic sudden sensorineural hearing loss","volume":"29","author":"Cvorovi\u0107","year":"2008","journal-title":"Otol Neurotol"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1177\/000348947708600406","article-title":"Natural history of sudden sensorineural hearing loss","volume":"86","author":"Mattox","year":"1977","journal-title":"Ann Otol Rhinol Laryngol"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"2875","DOI":"10.1007\/s00405-013-2348-9","article-title":"Increased levels of mean platelet volume: a possible relationship with idiopathic sudden hearing loss","volume":"270","author":"Ulu","year":"2013","journal-title":"Eur Arch Otorrinolaringol"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"S272","DOI":"10.1111\/jth.12972","article-title":"Acute and persistent platelet and coagulant activities in atherothrombosis","volume":"13","author":"Mastenbroek","year":"2015","journal-title":"J Thromb Haemost"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"09727531241301826","DOI":"10.1177\/09727531241301826","article-title":"Angiosome territories of vestibulocochlear nerve (VIII)","author":"Simhadri","year":"2025","journal-title":"Ann Neurosci"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1056\/NEJMcp0802129","article-title":"Idiopathic sudden sensorineural hearing loss","volume":"359","author":"Rauch","year":"2008","journal-title":"Clin. Pract."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"eadg7942","DOI":"10.1126\/science.adg7942","article-title":"Persistent complement dysregulation with signs of thromboinflammation in active long Covid","volume":"383","author":"Cervia-Hasler","year":"2024","journal-title":"Science"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"1718","DOI":"10.3390\/medicina59101718","article-title":"Endothelial dysfunction and metabolic disorders in patients with sudden sensorineural hearing loss","volume":"59","author":"Cavallaro","year":"2023","journal-title":"Medicina"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"102858","DOI":"10.1016\/j.amjoto.2020.102858","article-title":"Predicting hearing recovery following treatment of idiopathic sudden sensorineural hearing loss with machine learning models","volume":"42","author":"Uhm","year":"2021","journal-title":"Am J Otolaryngol"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"148","DOI":"10.21053\/ceo.2019.01858","article-title":"Machine learning models for predicting hearing prognosis in unilateral idiopathic sudden sensorineural hearing loss","volume":"13","author":"Park","year":"2020","journal-title":"Clin Exp Otorhinolaryngol"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"1125","DOI":"10.13201\/j.issn.1001-1781.2018.15.001","article-title":"Classification of sudden deafness prognosis based on deep learning method","volume":"32","author":"Bing","year":"2018","journal-title":"Lin Chung Er Bi Yan Hou Tou Jing Wai Ke Za Zhi"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"20058","DOI":"10.1038\/s41598-024-70436-0","article-title":"Prediction of hearing recovery with deep learning algorithm in sudden sensorineural hearing loss","volume":"14","author":"Seo","year":"2024","journal-title":"Sci Rep"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1097\/AUD.0000000000001711","article-title":"Machine-learning models with multiple imputation with sequential nearest neighbors imputation for predicting the prognosis of idiopathic sudden sensorineural hearing loss patients","volume":"47","author":"Jin","year":"2026","journal-title":"Ear Hear"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1845137\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T04:18:23Z","timestamp":1780287503000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1845137\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,1]]},"references-count":31,"alternative-id":["10.3389\/fmed.2026.1845137"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1845137","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,1]]},"article-number":"1845137"}}