IJCS | Volume 31, Nº6, November / December 2018

DOI: 10.5935/2359-4802.20180047 652 REVIEW ARTICLE International Journal of Cardiovascular Sciences. 2018;31(6)652-661 Mailing Address: Debora Carvalho Grion Avenida Marques do Paraná, 349, apto. 810. Postal Code: 24030-215, Centro, Niterói, RJ - Brazil. E-mail: deboragrion@yahoo.com.br , deboragrion@hotmail.com Phenotype Mapping of Heart Failure with Preserved Ejection Fraction Evandro Tinoco Mesquita, Debora Carvalho Grion, Miguel Camargo Kubrusly, Bernardo Barcelos Fernandes Fumagalli Silva, Érico Araújo Reis Santos Universidade Federal Fluminense (UFF), Niterói, RJ - Brazil Manuscript received September 20, 2017, revised manuscript January 03, 2018, accepted January 16, 2018. Heart Failure / physiopathology; Stroke Volume; Phenotype; Machine Learning; Artificial Intelligence. Keywords Abstract Heart failure with preserved ejection fraction (HFPEF) has become the main phenotypic model of heart failure (HF) in community and referral patients in Brazil and in the world. Despite advances in the development of new drugs for HF treatment, there has been no significant improvement in mortality of this condition. According tomany studies, this can be explained by the heterogeneous nature of HF physiopathology, whose basic mechanisms may result in different clinical presentations, culminating in the emerging of different phenogroups in this syndrome. In this context, phenotype mapping of HFPEF has emerged as a possible solution, since it enables the development of clinical trials that establish specific therapeutic strategies for each phenotypic profile. New technologies in the field of artificial intelligence have enabled the assessment of a large volume of data and infer intrinsic patterns and different outcomes. Thereby, it is possible to obtain mutually exclusive categories of HFPEF, with a phenotype mapping of the syndrome and grouping of patients according to their phenotypic features. Besides, other diseases can have the same clinical phenotype but different pathophysiological basis, the so called “phenocopies”. These tools enable the analysis and categorization of the wide spectrum of heart failure, contributing to solve the dilemmas of the treatment of this syndrome. Introduction Heart failure with preserved ejection fraction (HFPEF) has become the main phenotypic model of heart failure (HF) in community and referral patients in Brazil and in the world. 1,2 Only two forms of clinical presentations of HFPEF used to be recognized – first, in the outpatient setting, elderly women patients, intolerant to exercise, usually with no clinical evidence of congestion; 3,4 and second, patients admitted to emergency departments with hypertensive crisis, acute atrial fibrillation and acute pulmonary edema. 5 Clinical profiles of HFPEF have been gradually identified. For example, HFPEF has been associatedwith pulmonary arterial hypertension and valve diseases – aortic stenosis, mitral stenosis – and deposition diseases, such as senile amyloidosis. 6,7 In the last decades, progresses have been made in the understanding of pathophysiological mechanisms involved in HFPEF and the influence of comorbidities in the development and progression of the disease. In addition to diastolic dysfunction, abnormal chronotropic response, left atrial dysfunction, and altered physiology of coronary endothelium and systemic and pulmonary microcirculation have been reported. Molecular changes related to oxidative stress and a proinflammatory state have been also described, and seem to be associated with aging, hypertension, obesity and other cardiovascular and non-cardiovascular diseases. 8,9 Desp i t e advances i n the s tudy o f HFPEF pathophysiology and development of new drugs, there has been no significant improvement in mortality or clinical outcome of this condition. 10 A new discipline – phenomics – involving bioinformatics and artificial intelligence (machine learning) has been increasingly used for the study of phenotypes, including many areas of clinical medicine. More recently, it has been applied in cardiology for the study of HFPEF. Application of objective methods for identification of phenotypes goes in line with precision