[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-446268-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-446268-en":131},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","explainable-machine-learning-model-for-predicting-hearing-recovery-in-unilateral-sudden-sensorineural-hearing-loss-original-article","Explainable machine learning model for predicting hearing recovery in unilateral sudden sensorineural hearing loss - Original article","","Objective: Sudden sensorineural hearing loss (SSNHL) prognosis varies and depends on multiple factors. This study aimed to develop an explainable machine learning (ML) model using easily accessible features to predict SSNHL outcomes. Methods: A bi-center retrospective study included 534 SSNHL patients, with training/validation splits. Univariate analysis and LASSO selected key demographic, disease, and lab features; five ML models were assessed using AUC and calibration, with decision curve analysis and SHAP for interpretation. Results: The Random Forest model achieved the highest AUC (0.998). SHAP highlighted hearing loss degree, audiogram type, age, MCV, onset-to-treatment, and serum albumin. Conclusions: The explainable ML model performed strongly and supports clinical interpretation for guiding rehabilitation.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/healthcare/","Healthcare",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/explainable-machine-learning-model-for-predicting-hearing-recovery-in-unilateral-sudden-sensorineural-hearing-loss-original-article/446268/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/explainable-machine-learning-model-for-predicting-hearing-recovery-in-unilateral-sudden-sensorineural-hearing-loss-original-article/446268.png","ImageObject",300,407,{"name":42,"@type":43},"Bintang","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-31","2026-09-29",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",13,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What is the objective of this study on SSNHL?","Question",{"text":63,"@type":64},"To develop an explainable machine learning model that uses easily accessible features to predict hearing recovery outcomes in unilateral SSNHL.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How were key features selected for the ML models?",{"text":68,"@type":64},"The study used univariate analysis and LASSO regression to select predominant variables, including demographic characteristics, disease-specific factors, and laboratory items.",{"name":70,"@type":61,"acceptedAnswer":71},"Which model performed best and what did SHAP show?",{"text":72,"@type":64},"The Random Forest model achieved the highest AUC (0.998). SHAP indicated that major features included degree of hearing loss, audiogram type, age, MCV, onset to treatment, and serum albumin.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},446268,1790925230,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,110,115,120,123,127],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":108,"slug":109},7,40,"healthcare",{"id":111,"doc_module":4,"doc_module_name":25,"category_name":112,"show_sort_weight":113,"slug":114},8,"Research & Report",30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":25,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":25,"category_name":129,"show_sort_weight":97,"slug":130},19,"General","general",{"code":4,"msg":82,"data":132},{"doc_id":79,"user_id":133,"nickname":42,"user_avatar":134,"doc_module":4,"category_id":107,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":111,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":144,"read_time":118,"preview_page_count":4},962085564381,"https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8","Brazilian Journal of Otorhinolaryngology 92 (2026) 101730  \nContents lists available at ScienceDirect  \nBrazilian Journal of Otorhinolaryngology  \njournal [homepage:](homepage: www.bjorl.org)[ www.bjorl.org](homepage: www.bjorl.org)  \n| Original article\u003Cbr>Explainable machine learning model for predicting hearing recovery in unilateral sudden sensorineural hearing loss\u003Cbr>Jueting Wu a,b , Ruru Chenc , Yaxuan Liu a, Feng Zhao a, Huiying Chena, Xiaoyu Lina , Jiping Sua,*\u003Cbr>a The First Affiliated Hospital of Guangxi Medical University, Department of Otolaryngology-Head and Neck Surgery, Nanning, Guangxi, China\u003Cbr>b Department of Otolaryngology-Head and Neck Surgery, Lishui Hospital of Wenzhou Medical University, The First Affiliated Hospital of Lishui University, Lishui People’s Hospital, Lishui, Zhejiang 323000, China\u003Cbr>c The Second Affiliated Hospital and Yuying Children’s Hospital of Wenzhou Medical University, Department of Otolaryngology-Head and Neck Surgery, Wenzhou, Zhejiang, China |  |  | |\n| --- | --- | --- | --- |\n| A R T I C L E I N F O |  | A B S T R A C T |  |\n| Edited by Dr C Chone. |  | Objective: Sudden Sensorineural Hearing Loss (SSNHL) is routinely encountered in otolaryngology clinics. The prognosis of SSNHL varies dramatically and depends on multiple influence factors. This study aimed to develop an explainable Machine Learning (ML) model with easily accessible features to predict the prognosis of SSNHL. Methods: This bi-center retrospective study included 534 patients with SSNHL. We randomly split the data into training and validation sets. Univariate analysis and Least Absolute Shrinkage and Selection Operator (LASSO) regression were employed to select predominant features, including demographic, disease-specific characteristics, and laboratory items. We evaluated the performance of five ML models constructed with six crucial variables using the Area Under the receiver operating characteristic Curve (AUC), accuracy, specificity, sensitivity, and F1 scores. These models were further calibrated by calibration curve and Brier score. Clinical utility was evaluated by Decision Curve Analysis (DCA). The Shapley Additive Explanations (SHAP) method was applied to interpret feature contribution and explain the ML models.\u003Cbr>Results: The Random Forest (RF) model reached the highest AUC of 0.998. Its accuracy, sensitivity, specificity, and F1 score were 0.981, 0.963, 0.989, and 0.967, respectively. DCA curve analysis revealed a comparable net benefit of the models. The SHAP method revealed that the primary features were degree of hearing loss, audiogram type, age, Mean Corpuscular Volume (MCV), onset to treatment, and serum Albumin (ALB) accordingly.\u003Cbr>Conclusions: The explainable ML model was superb in predicting hearing outcome and providing information on feature contributions. Clinicians can better understand the contributors to hearing recovery and guide aural rehabilitation using the SHAP method.\u003Cbr>Level of evidence: Level 3. |  |\n| Keywords:\u003Cbr>Machine learning\u003Cbr>Sudden sensorineural hearing loss Serum albumin\u003Cbr>Mean corpuscular volume Shapley additive explanations |  |  |  |\n\nIntroduction  \nSudden Sensorineural Hearing Loss (SSNHL) is commonly encountered in otological emergencies and requires immediate medical attention. Despite extensive research, hearing recovery following SSNHL can occur, be partial, or complete.1 Therefore, early identification of principal predictive factors are conducive to forecasting recovery, monitoring treatment, and guide aural rehabilitation.  \nRecently, Machine Learning (ML) has demonstrated promising  \nresults in predicting the prognosis of SSNHL due to its capacity for handling complex interactions and non-linear relationships.2–6 However, this method is challenging to interpret. Understanding the decision-making processes and output generated by ML algorithms comprehensively will increase the acceptance of confidence in prediction models. Therefore, we established ML mod","cbCaihtsFrzHineq","https://ap.wps.com/l/cbCaihtsFrzHineq","pdf",4739646,"English","# Objective\n# Methods\n## Patient selection\n## Model development and evaluation\n# Results\n# Conclusions\n# Level of evidence","[{\"question\":\"What is the objective of this study on SSNHL?\",\"answer\":\"To develop an explainable machine learning model that uses easily accessible features to predict hearing recovery outcomes in unilateral SSNHL.\"},{\"question\":\"How were key features selected for the ML models?\",\"answer\":\"The study used univariate analysis and LASSO regression to select predominant variables, including demographic characteristics, disease-specific factors, and laboratory items.\"},{\"question\":\"Which model performed best and what did SHAP show?\",\"answer\":\"The Random Forest model achieved the highest AUC (0.998). SHAP indicated that major features included degree of hearing loss, audiogram type, age, MCV, onset to treatment, and serum albumin.\"}]","Explainable machine learning model for predicting hearing recovery in unilateral sudden sensorineural hearing loss - Original article | PDF",1790714649]