[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122290-en":3,"doc-seo-122290-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},122290,1099514067438,"River Wang","https://ap-avatar.wpscdn.com/avatar/100002539ee87300030?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780474512215547542",8,"Research & Report","Construction of a machine learning-based prediction model for mitral annular calcification - Research report","Objective: develop a risk prediction model for mitral annular calcification (MAC) using multiple machine learning algorithms to support early identification and risk assessment. Methods: 500 hospitalized patients undergoing echocardiography from July 2022 to March 2024 were selected, with 250 MAC and 250 non-MAC, then split into a training set (350) and test set (150). Nine ML algorithms were compared using AUC, and SHAP was applied for feature importance and selection. Results: Random forest achieved the highest test AUC (0.913). After feature selection, a simplified model with TyG index, eGFR and age reached AUC 0.896 with good predictive accuracy. Conclusion: Random forest performed best and the simplified model enables efficient MAC risk screening as a convenient clinical tool.","Chin J Clin Res, May 2025, Vol.38, No.5   \nCite as: Li RQ,Tan YY, Ge TT, Qi L, Song B, Tong JY. Construction of a machine learning-based prediction model formitral annular calcification [J] . Chin J Clin Res,2025,38(5):689-694 .  \nDOI: 10.13429/j.cnki.cjcr.2025.05.008  \nConstruction of a machine learning-based prediction model for  \nmitral annular calcification  \nLI Runqian*, TAN Yanyi, GE Tiantian, QI Lei, SONG Bai, TONG Jiayi  \n*Department of Cardiology, Zhongda Hospital of Southeast University, Nanjing, Jiangsu 210009, China  \nCorresponding authors: TONG Jiayi, Email: [101007925@seu.edu.cn](101007925@seu.edu.cn); SONG Bai, Email: [baisong202410@163.com](baisong202410@163.com)[ ](baisong202410@163.com)Abstract: Objective To develop a risk prediction model for Mitral Annular Calcification (MAC) using various machine learning algorithms to enable early identification and risk assessment of MAC. Methods A total of 500 patients who were hospitalized and underwent echocardiography at Zhongda Hospital, Southeast University, from July 2022 to March 2024, were selected as subjects, including 250 patients with MAC and 250 without. Clinical data, such as general characteristics and laboratory test indicators, were collected. The subjects were randomly divided into a training set (350 cases) and a test set (150 cases) at a 70%:30% ratio. Nine machine learning algorithms, including Logistic Regression, Support Vector Classifier, Decision Tree, Elastic Net, Multi-layer Perceptron, K-Nearest Neighbors, random forest , extreme gradient boosting (XGBoost), and LightGBM, were used to build prediction models for MAC. The performance of the models was evaluated using the area under the receiver operating characteristic curve (AUC), and the best-performing model was selected. The Shapley Additive Explanations (SHAP) method was used to assess feature importance, and feature selection was performed to construct the final model. Results In the test set, the random forest model had the largest AUC (AUC = 0. 913), with a sensitivity and specificity of 89. 2% and 75. 0%, respectively. After feature selection, a simplified random forest model containing three important features, TyG index, eGFRand age, was built, and the final model had an AUC of 0.896 in the test set, with high prediction accuracy. Conclusion The random forest model performed best among the machine learning-based MAC risk prediction models, and the simplified model was able to efficiently predict the occurrence of MAC. This method provides a convenient clinical tool for early risk assessment of MAC.  \nKeywords: Mitral annular calcification; Machine learning; Insulin resistance; Triglyceride-glucose index; Shapley additive explanations  \nWith the increasing global aging population and changes in human lifestyles, the incidence of valvular heart disease has risen significantly, becoming one of the major health threats for the elderly in China. Mitral annular calcification (MAC), first identified in the early 20th century, is a chronic degenerative fibrotic lesion of the mitral valve apparatus characterized by calcium and lipid deposition within the mitral annulus [1] . Initially regarded as a localized degenerative process of calcium-phosphate deposition, growing evidence suggests it is an active process regulated by mechanical stress, lipid metabolism, chronic inflammation, and endothelial dysfunction, sharing similarities with atherosclerotic cardiovascular calcification [2] . According to large autopsy studies, the prevalence of MAC in the general population is approximately 10%[3], with significantly higher incidence of MAC observed in older individuals and those with cardiovascular risk factors such as hypertension, diabetes, hyperlipidemia, and smoking [4] . As MAC is often asymptomatic in early stages, most cases are incidentally detected during cardiovascular or pulmonary evaluations. However, its clinical significance cannot be overlooked. The Framingham Heart Study revealed t","cbCaiqojpBYBx08l","https://ap.wps.com/l/cbCaiqojpBYBx08l","pdf",2977488,1,11,"English","en",105,"# Materials and methods\n## General data","[{\"question\":\"What is the main objective of the study on mitral annular calcification?\",\"answer\":\"To develop a machine learning-based risk prediction model for mitral annular calcification to enable early identification and risk assessment.\"},{\"question\":\"How were patients selected and divided in the study?\",\"answer\":\"A total of 500 hospitalized patients who underwent echocardiography were selected, with 250 having MAC and 250 without. Data were split into a training set (350) and a test set (150) in a 70%:30% ratio.\"},{\"question\":\"Which machine learning model performed best, and what was its test performance?\",\"answer\":\"The random forest model performed best, achieving the highest test AUC of 0.913 with sensitivity of 89.2% and specificity of 75.0%.\"}]","Construction of a machine learning-based prediction model for mitral annular calcification - Research report | PDF",1785809846,28,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"construction-of-a-machine-learning-based-prediction-model-for-mitral-annular-calcification-research-report","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/construction-of-a-machine-learning-based-prediction-model-for-mitral-annular-calcification-research-report/122290/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is the main objective of the study on mitral annular calcification?","Question",{"text":75,"@type":76},"To develop a machine learning-based risk prediction model for mitral annular calcification to enable early identification and risk assessment.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How were patients selected and divided in the study?",{"text":80,"@type":76},"A total of 500 hospitalized patients who underwent echocardiography were selected, with 250 having MAC and 250 without. Data were split into a training set (350) and a test set (150) in a 70%:30% ratio.",{"name":82,"@type":73,"acceptedAnswer":83},"Which machine learning model performed best, and what was its test performance?",{"text":84,"@type":76},"The random forest model performed best, achieving the highest test AUC of 0.913 with sensitivity of 89.2% and specificity of 75.0%.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]