Machine learning modeling identifies hypertrophic cardiomyopathy subtypes with genetic signature

作     者：Jiaqi Dai Tao Wang Ke Xu Yang Sun Zongzhe Li Peng Chen Hong Wang Dongyang Wu Yanghui Chen Lei Xiao Hao Liu Haoran Wei Rui Li Liyuan Peng Ting Yu Yan Wang Zhongsheng Sun Dao Wen Wang Jiaqi Dai;Tao Wang;Ke Xu;Yang Sun;Zongzhe Li;Peng Chen;Hong Wang;Dongyang Wu;Yanghui Chen;Lei Xiao;Hao Liu;Haoran Wei;Rui Li;Liyuan Peng;Ting Yu;Yan Wang;Zhongsheng Sun;Dao Wen Wang

作者机构：Division of CardiologyDepartment of Internal MedicineTongji HospitalTongji Medical CollegeHuazhong University of Science and TechnologyWuhan 430030China Beijing Institutes of Life ScienceChinese Academy of SciencesBeijing 100101China Hubei Key Laboratory of Genetics and Molecular Mechanism of Cardiologic DisordersHuazhong University of Science and TechnologyWuhan 430030China 

出 版 物：《Frontiers of Medicine》 (医学前沿(英文版))

年 卷 期：2023年第17卷第4期

页      面：768-780页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：the National Key R&D Program of China(No.2017YFC0909400) the National Natural Science Foundation of China(Nos.91439203,91839302,and 81700413) Shanghai Municipal Science and Technology Major Project(No.2017SHZDZX01) the Fundamental Research Funds for the Central Universities,HUST(No.2016JCTD117) 

主　　题：machine learning methods hypertrophic cardiomyopathy genetic risk 

摘      要：Previous studies have revealed that patients with hypertrophic cardiomyopathy(HCM)exhibit differences in symptom severity and prognosis,indicating potential HCM subtypes among these ***,793 patients with HCM were recruited at an average follow-up of 32.78±27.58 months to identify potential HCM subtypes by performing consensus clustering on the basis of their echocardiography ***,we proposed a systematic method for illustrating the relationship between the phenotype and genotype of each HCM subtype by using machine learning modeling and interactome network detection techniques based on whole-exome sequencing *** independent cohort that consisted of 414 patients with HCM was recruited to replicate the ***,two subtypes characterized by different clinical outcomes were identified in *** with subtype 2 presented asymmetric septal hypertrophy associated with a stable course,while those with subtype 1 displayed left ventricular systolic dysfunction and aggressive *** learning modeling based on personal whole-exome data identified 46 genes with mutation burden that could accurately predict subtype ***,the patients in another cohort predicted as subtype 1 by the 46-gene model presented increased left ventricular end-diastolic diameter and reduced left ventricular ejection *** employing echocardiography and genetic screening for the 46 genes,HCM can be classified into two subtypes with distinct clinical outcomes.