Identification of novel pheno-groups in heart failure with preserved ejection fraction using machine learning

• Published in: Heart (British Cardiac Society) Vol. 106; no. 5; pp. 342 - 349
• Main Authors: Hedman, Åsa K, Hage, Camilla, Sharma, Anil, Brosnan, Mary Julia, Buckbinder, Leonard, Gan, Li-Ming, Shah, Sanjiv J, Linde, Cecilia M, Donal, Erwan, Daubert, Jean-Claude, Mälarstig, Anders, Ziemek, Daniel, Lund, Lars
• Format: Journal Article
• Language: English
• Published: England BMJ Publishing Group Ltd and British Cardiovascular Society 01.03.2020; BMJ Publishing Group LTD; BMJ Publishing Group
• Subjects: association; Bioengineering; Biomarkers; Blood pressure; Body mass index; Cardiac arrhythmia; Cardiology and Cardiovascular Disease; Cardiovascular disease; Cardiovascular System & Cardiology; Chronic obstructive pulmonary disease; Diabetes; dysfunction; ECG/electrocardiogram; Ejection fraction; Genotype & phenotype; Heart failure; Heart failure and cardiomyopathies; heart failure with preserved ejection fraction; Kardiologi och kardiovaskulära sjukdomar; Kidney diseases; Laboratories; Life Sciences; Machine learning; Medical prognosis; outcomes; Patients; predicting survival; Proteins; Proteomics; risk score; subgroups; therapies; Variables; Velocity; Sweden; ECG/electrocardiogram; heart failure with preserved ejection fraction

ObjectiveHeart failure with preserved ejection fraction (HFpEF) is a heterogeneous syndrome. We aimed to derive HFpEF phenotype-based groups ('phenogroups') based on clinical and echocardiogram data using machine learning, and to compare clinical characteristics, proteomics and outcomes ac...