TY - JOUR
T1 - Discovering Distinct Phenotypical Clusters in Heart Failure Across the Ejection Fraction Spectrum
T2 - a Systematic Review
AU - Meijs, Claartje
AU - Handoko, M. Louis
AU - Savarese, Gianluigi
AU - Vernooij, Robin W. M.
AU - Vaartjes, Ilonca
AU - Banerjee, Amitava
AU - Koudstaal, Stefan
AU - Brugts, Jasper J.
AU - Asselbergs, Folkert W.
AU - Uijl, Alicia
N1 - Funding Information: AB received research grants from AstraZeneca; outside the submitted work. Funding Information: This work has received support from the EU/EFPIA Innovative Medicines Initiative 2 Joint Undertaking BigData@Heart grant n° 116074. FA is supported by UCL Hospitals NIHR Biomedical Research Centre. IV is supported by the Dutch Heart Foundation, as part of “Facts and Figures”. RV and MLH are supported by the Dutch CardioVascular Alliance (2020B008 RECONNEXT). MLH is supported by the Dutch Heart Foundation (NHS; 2020T058). AB is supported by National Institute for Health and Care Research (NIHR), British Medical Association, UK Research and Innovation, European Union, and is trustee of the South Asian Health Foundation and Long COVID SOS. Publisher Copyright: © 2023, The Author(s).
PY - 2023/10
Y1 - 2023/10
N2 - Review Purpose: This systematic review aims to summarise clustering studies in heart failure (HF) and guide future clinical trial design and implementation in routine clinical practice. Findings: 34 studies were identified (n = 19 in HF with preserved ejection fraction (HFpEF)). There was significant heterogeneity invariables and techniques used. However, 149/165 described clusters could be assigned to one of nine phenotypes: 1) young, low comorbidity burden; 2) metabolic; 3) cardio-renal; 4) atrial fibrillation (AF); 5) elderly female AF; 6) hypertensive-comorbidity; 7) ischaemic-male; 8) valvular disease; and 9) devices. There was room for improvement on important methodological topics for all clustering studies such as external validation and transparency of the modelling process. Summary: The large overlap between the phenotypes of the clustering studies shows that clustering is a robust approach for discovering clinically distinct phenotypes. However, future studies should invest in a phenotype model that can be implemented in routine clinical practice and future clinical trial design. Graphical Abstract: HF = heart failure, EF = ejection fraction, HFpEF = heart failure with preserved ejection fraction, HFrEF = heart failure with reduced ejection fraction, CKD = chronic kidney disease, AF = atrial fibrillation, IHD = ischaemic heart disease, CAD = coronary artery disease, ICD = implantable cardioverter-defibrillator, CRT = cardiac resynchronization therapy, NT-proBNP = N-terminal pro b-type natriuretic peptide, BMI = Body Mass Index, COPD = Chronic obstructive pulmonary disease. [Figure not available: see fulltext.]
AB - Review Purpose: This systematic review aims to summarise clustering studies in heart failure (HF) and guide future clinical trial design and implementation in routine clinical practice. Findings: 34 studies were identified (n = 19 in HF with preserved ejection fraction (HFpEF)). There was significant heterogeneity invariables and techniques used. However, 149/165 described clusters could be assigned to one of nine phenotypes: 1) young, low comorbidity burden; 2) metabolic; 3) cardio-renal; 4) atrial fibrillation (AF); 5) elderly female AF; 6) hypertensive-comorbidity; 7) ischaemic-male; 8) valvular disease; and 9) devices. There was room for improvement on important methodological topics for all clustering studies such as external validation and transparency of the modelling process. Summary: The large overlap between the phenotypes of the clustering studies shows that clustering is a robust approach for discovering clinically distinct phenotypes. However, future studies should invest in a phenotype model that can be implemented in routine clinical practice and future clinical trial design. Graphical Abstract: HF = heart failure, EF = ejection fraction, HFpEF = heart failure with preserved ejection fraction, HFrEF = heart failure with reduced ejection fraction, CKD = chronic kidney disease, AF = atrial fibrillation, IHD = ischaemic heart disease, CAD = coronary artery disease, ICD = implantable cardioverter-defibrillator, CRT = cardiac resynchronization therapy, NT-proBNP = N-terminal pro b-type natriuretic peptide, BMI = Body Mass Index, COPD = Chronic obstructive pulmonary disease. [Figure not available: see fulltext.]
KW - Clustering
KW - Heart failure
KW - Machine learning
KW - Phenotyping
KW - Precision medicine
UR - http://www.scopus.com/inward/record.url?scp=85165242078&partnerID=8YFLogxK
U2 - https://doi.org/10.1007/s11897-023-00615-z
DO - https://doi.org/10.1007/s11897-023-00615-z
M3 - Review article
C2 - 37477803
SN - 1546-9530
VL - 20
SP - 333
EP - 349
JO - Current Heart Failure Reports
JF - Current Heart Failure Reports
IS - 5
ER -