Data-Driven Phenotyping in Heart Failure With Preserved Ejection Fraction

Overview

The goal of this observational study is to learn how people with Heart Failure with Preserved Ejection Fraction (HFpEF) can be grouped into different "phenotypes" based on their clinical information. The researchers want to understand whether these groups have different health profiles and different responses during a cardiopulmonary exercise test (CPET). The main questions this study aims to answer are: * Can clinical data be used to identify meaningful HFpEF phenotypes? * Do these phenotypes match well-known HFpEF scores, such as the H2FPEF and Heart Failure Association Pre-test Assessment, Echocardiography and Natriuretic Peptide (HFA-PEFF) scores? * Do people in different phenotypes show different results on a CPET? Participants will: * Have their past clinical records reviewed if they were diagnosed with HFpEF at the Local Health Unit of the Leiria Region (ULS RL); * A smaller group will attend one visit to complete a CPET, which measures how the heart, lungs and muscles respond during exercise. This study includes adults aged 18 years or older who have HFpEF. The study does not involve any new treatments or experimental drugs.

Detailed description

Heart Failure with Preserved Ejection Fraction (HFpEF) is a complex condition, and people with HFpEF can have different symptoms and clinical profiles. Understanding these differences may help improve how the condition is described and studied. This study has two parts: a retrospective analysis and a cross-sectional assessment.

In the retrospective part, the researchers will collect clinical information that was previously recorded in the hospital's clinical records during past hospitalizations for HFpEF at the Local Health Unit of the Leiria Region (ULS RL). The data will be reviewed and prepared for analysis using standard data quality procedures. After the database is complete, the researchers will use data-driven methods to look for patterns among participants, in order to identify groups of people who share similar characteristics ("phenotypes") without setting predefined categories. Methods will include descriptive statistics, correlation analysis and feature selection using algorithmic approaches such as ReliefF. For phenotyping, unsupervised machine-learning techniques including K-means clustering and principal component analysis (PCA) will be applied.

The cross-sectional part will invite a sample of participants selected to represent each phenotype (planned 15 participants for each phenotype) identified in the retrospective analysis. Selected participants will complete a single on-site visit including informed consent verification, a structured clinical review and a standardized cardiopulmonary exercise test (CPET) performed according to local and international guidelines. The CPET procedures will follow the laboratory protocol, namely calibration of equipment, resting measurements, incremental workload protocol, continuous gas exchange, and electrocardiogram (ECG) monitoring. CPET data will be recorded in digital format and transferred securely to the study database.

The study will also evaluate phenotype concordance with widely used HFpEF tools (H2FPEF and HFA-PEFF) and describe differences in physiological responses during CPET across phenotypes, to help clarify how useful they are in describing different forms of HFpEF. Analyses will emphasize exploratory, data-driven evaluation and estimation of effect sizes, consistent with the phenotyping objectives of the study. Where relevant, associations between phenotype membership and CPET variables will be explored descriptively and through correlation-based analyses.

Ethical and data protection procedures are in place. Personal identifiers will be removed and replaced by study ID codes. A linkage file (study ID to personal identifiers) will be stored on an encrypted device with access restricted to the student investigator. Electronic study data will be housed on secure servers with role-based access control. Data will be retained according to institutional policy and relevant legislation. Only de-identified datasets will be used for analysis and sharing. Safety procedures for CPET include pre-test screening for absolute contraindications, continuous ECG and blood pressure monitoring during the test, availability of emergency equipment and immediate clinical oversight by qualified personnel. Adverse events during CPET will be recorded and reported per the Ethics Committee requirements.

By combining clinical record information collected during previous hospitalizations with detailed exercise testing in a selected group, this study aims to provide new insight into the variation that exists among people with HFpEF. The findings may support more personalized approaches in future research.

Primary outcome measures

• Identification and characterization of HFpEF phenotypes using multimodal clustering analysis [Time frame: Up to December 2026 (completion of retrospective data collection and clustering analysis).]

Secondary outcome measures (3)

• Mean peak oxygen uptake (VO₂peak) during cardiopulmonary exercise testing [Time frame: December 2026 to July 2027 (single assessment per participant).]
• Concordance between H2FPEF and HFA-PEFF scores and identified HFpEF phenotypes [Time frame: Up to October 2027.]
• Mean plasma NT-proBNP concentration (pg/mL) by HFpEF phenotypes [Time frame: Up to February 2028.]

Eligibility criteria

Inclusion criteria

• Retropective observational phase (Phase I):

• Age ≥18 years;
• Established diagnosis of heart failure with preserved ejection fraction (LVEF ≥50%);
• Patients receiving care (outpatient or inpatient) at the Local Health Unit of the Leiria Region (ULS RL) since September 2018.
• Cross-sectional observational phase (Phase II - CPET):

• Age ≥18 years;
• Established diagnosis of HFpEF;
• Selection as a volunteer representative of phenotypes identified in the retrospective clustering analysis;
• Provision of written informed consent prior to any study-specific procedures.

Exclusion criteria

• Retropective observational phase (Phase I):

• Incomplete or inadequate medical records preventing full data extraction.
• Cross-sectional observational phase (Phase II - CPET):

• Medical contraindication or physical inability to perform cardiopulmonary exercise testing (CPET);
• Inability to provide informed consent.

Criteria are shown verbatim from the registry (in English). Final eligibility is always assessed by the study center.

Healthy volunteers: No

Study design

Observational model

Cohort

Study locations

Portugal · 2 centers

• Local Health Unit of the Leiria Region — Leiria
• ciTechCare - Center for Innovative Care and Health Technology — Leiria

Publications

• Ferreira JP, Dewan P, Jhund PS, Lorenzo-Almoros A, Duarte K, Petrie MC, Carson PE, McKelvie R, Komajda M, Zile M, Zannad F, McMurray JJV. Covariate adjusted reanalysis of the I-Preserve trial. Clin Res Cardiol. 2020 Nov;109(11):1358-1365. doi: 10.1007/s00392-020-01632-x. Epub 2020 Mar 25. PMID 32215700
• Massie BM, Carson PE, McMurray JJ, Komajda M, McKelvie R, Zile MR, Anderson S, Donovan M, Iverson E, Staiger C, Ptaszynska A; I-PRESERVE Investigators. Irbesartan in patients with heart failure and preserved ejection fraction. N Engl J Med. 2008 Dec 4;359(23):2456-67. doi: 10.1056/NEJMoa0805450. Epub 2008 Nov 11. PMID 19001508
• Cunningham JW, Vaduganathan M, Claggett BL, John JE, Desai AS, Lewis EF, Zile MR, Carson P, Jhund PS, Kober L, Pitt B, Shah SJ, Swedberg K, Anand IS, Yusuf S, McMurray JJV, Pfeffer MA, Solomon SD. Myocardial Infarction in Heart Failure With Preserved Ejection Fraction: Pooled Analysis of 3 Clinical Trials. JACC Heart Fail. 2020 Aug;8(8):618-626. doi: 10.1016/j.jchf.2020.02.007. Epub 2020 May 6. PMID 32387067
• Pereira PMM, Thomaz LA, Tavora LMN, Assuncao PAA, Fonseca-Pinto RM, Paiva RP, Faria SMM. Melanoma classification using light-Fields with morlet scattering transform and CNN: Surface depth as a valuable tool to increase detection rate. Med Image Anal. 2022 Jan;75:102254. doi: 10.1016/j.media.2021.102254. Epub 2021 Oct 7. PMID 34649195
• Grote T, Berens P. Uncertainty, Evidence, and the Integration of Machine Learning into Medical Practice. J Med Philos. 2023 Feb 17;48(1):84-97. doi: 10.1093/jmp/jhac034. PMID 36630292
• Shehab M, Abualigah L, Shambour Q, Abu-Hashem MA, Shambour MKY, Alsalibi AI, Gandomi AH. Machine learning in medical applications: A review of state-of-the-art methods. Comput Biol Med. 2022 Jun;145:105458. doi: 10.1016/j.compbiomed.2022.105458. Epub 2022 Mar 28. PMID 35364311
• Quazi S. Retraction Note: Artificial intelligence and machine learning in precision and genomic medicine. Med Oncol. 2025 Apr 26;42(6):180. doi: 10.1007/s12032-025-02732-2. No abstract available. PMID 40281258
• Bayes-Genis A, Liu PP, Lanfear DE, de Boer RA, Gonzalez A, Thum T, Emdin M, Januzzi JL. Omics phenotyping in heart failure: the next frontier. Eur Heart J. 2020 Sep 21;41(36):3477-3484. doi: 10.1093/eurheartj/ehaa270. PMID 32337540

Identifiers

NCT: NCT07429396 · FCT 2023.05000.BDANA

Primary sources (government registries)

• ClinicalTrials.gov (US NIH)

View this study on ClinicalTrials.gov ↗