首页|University Medical Center Reports Findings in Dilated Cardiomyopathy (Integrated machine learning and multimodal data fusion for patho-phenotypic feature recognition in iPSC models of dilated cardiomyopathy)
University Medical Center Reports Findings in Dilated Cardiomyopathy (Integrated machine learning and multimodal data fusion for patho-phenotypic feature recognition in iPSC models of dilated cardiomyopathy)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - New research on Heart Disorders and Di seases - Dilated Cardiomyopathy is the subjectof a report. According to news re porting out of Gottingen, Germany, by NewsRx editors, research stated,“Integrat ion of multiple data sources presents a challenge for accurate prediction of mol ecular pathophenotypicfeatures in automated analysis of data from human model systems. Here, we applied a machinelearning-based data integration to distingui sh patho-phenotypic features at the subcellular level for dilatedcardiomyopathy (DCM).”Funders for this research include DZHK German Center for Cardiovascular Research , UniversitatsmedizinGottingen, Carl Zeiss Foundation, Deutsche Forschungsgemei nschaft, Germany’s Excellence Strategy.Our news journalists obtained a quote from the research from University Medical Center, “We employeda human induced pluripotent stem cell-derived cardiomyocyte (iPSC-CM) model of a DCM mutation inthe sarcomere protein troponin T (TnT), Tn T-R141W, compared to isogenic healthy (WT) control iPSCCMs.We established a mu ltimodal data fusion (MDF)-based analysis to integrate source datasets forCa tr ansients, force measurements, and contractility recordings. Data were acquired f or three additionallayer types, single cells, cell monolayers, and 3D spheroid iPSC-CM models. For data analysis, numericalconversion as well as fusion of dat a from Ca transients, force measurements, and contractility recordings,a non-ne gative blind deconvolution (NNBD)-based method was applied. Using an XGBoost alg orithm,we found a high prediction accuracy for fused single cell, monolayer, an d 3D spheroid iPSC-CM models (92 ? 0.08 %), as well as for fused C a transient, beating force, and contractility models (>9 6 ? 0.04 %).”
GottingenGermanyEuropeCardiologyCardiomyopathiesCardiovascularCardiovascular Diseases and ConditionsCyborg sDilated CardiomyopathyEmerging TechnologiesHealth and MedicineHeart Dis easeHeart Disorders and DiseasesMachine Learning
NETL
NSTL
