Machine learning-based biomarker profile derived from 4210 serially measured proteins predicts clinical outcome of patients with heart failure

Marie de Bakker; Teun B Petersen; Anja J Rueten-Budde; K Martijn Akkerhuis; Victor A Umans; Jasper J Brugts; Tjeerd Germans; Marcel J T Reinders; Peter D Katsikis; Peter J van der Spek; Rachel Ostroff; Ruicong She; David Lanfear; Folkert W Asselbergs; Eric Boersma; Dimitris Rizopoulos; Isabella Kardys

doi:10.1093/ehjdh/ztad056

Machine learning-based biomarker profile derived from 4210 serially measured proteins predicts clinical outcome of patients with heart failure

Eur Heart J Digit Health. 2023 Oct 4;4(6):444-454. doi: 10.1093/ehjdh/ztad056. eCollection 2023 Dec.

Authors

Marie de Bakker¹, Teun B Petersen^{1

2}, Anja J Rueten-Budde², K Martijn Akkerhuis¹, Victor A Umans³, Jasper J Brugts¹, Tjeerd Germans³, Marcel J T Reinders⁴, Peter D Katsikis⁵, Peter J van der Spek⁶, Rachel Ostroff⁷, Ruicong She⁸, David Lanfear^{9

10}, Folkert W Asselbergs^{11

12}, Eric Boersma¹, Dimitris Rizopoulos^{2

13}, Isabella Kardys¹

Affiliations

¹ Department of Cardiology, Erasmus MC, University Medical Center Rotterdam, Dr. Molenwaterplein 40, 3015GD, Rotterdam, The Netherlands.
² Department of Biostatistics, Erasmus MC, University Medical Center Rotterdam, Dr. Molenwaterplein 40, 3015GD, Rotterdam, The Netherlands.
³ Department of Cardiology, Northwest Clinics, Wilhelminalaan 12, 1815 JD, Alkmaar, The Netherlands.
⁴ Delft Bioinformatics Lab, Delft University of Technology, Van Mourik Broekmanweg 6, 2628 XE, Delft, The Netherlands.
⁵ Department of Immunology, Erasmus MC, University Medical Center Rotterdam, Dr. Molenwaterplein 40, 3015GD, Rotterdam, The Netherlands.
⁶ Department of Pathology, Erasmus MC, University Medical Center Rotterdam, Dr. Molenwaterplein 40, 3015GD, Rotterdam, The Netherlands.
⁷ SomaLogic, Inc., 2945 Wilderness Pl., Boulder, CO 80301, USA.
⁸ Department of Public Health Sciences, Henry Ford Health System, 1 Ford Pl, Detroit, MI 48202, USA.
⁹ Center for Individualized and Genomic Medicine Research (CIGMA), Henry Ford Hospital, 2799 W. Grand Boulevard, Detroit MI, 48202, USA.
¹⁰ Heart and Vascular Institute, Henry Ford Hospital, 2799 W. Grand Boulevard, Detroit, MI 48202, USA.
¹¹ Amsterdam University Medical Centers, Department of Cardiology, University of Amsterdam, Meibergdreef 9, 1105 AZ, Amsterdam, The Netherlands.
¹² Health Data Research UK and Institute of Health Informatics, University College London, Gower St, London, WC1E 6BT, UK.
¹³ Department of Epidemiology, Erasmus MC, University Medical Center Rotterdam, Dr. Molenwaterplein 40, 3015GD, Rotterdam, The Netherlands.

Abstract

Aims: Risk assessment tools are needed for timely identification of patients with heart failure (HF) with reduced ejection fraction (HFrEF) who are at high risk of adverse events. In this study, we aim to derive a small set out of 4210 repeatedly measured proteins, which, along with clinical characteristics and established biomarkers, carry optimal prognostic capacity for adverse events, in patients with HFrEF.

Methods and results: In 382 patients, we performed repeated blood sampling (median follow-up: 2.1 years) and applied an aptamer-based multiplex proteomic approach. We used machine learning to select the optimal set of predictors for the primary endpoint (PEP: composite of cardiovascular death, heart transplantation, left ventricular assist device implantation, and HF hospitalization). The association between repeated measures of selected proteins and PEP was investigated by multivariable joint models. Internal validation (cross-validated c-index) and external validation (Henry Ford HF PharmacoGenomic Registry cohort) were performed. Nine proteins were selected in addition to the MAGGIC risk score, N-terminal pro-hormone B-type natriuretic peptide, and troponin T: suppression of tumourigenicity 2, tryptophanyl-tRNA synthetase cytoplasmic, histone H2A Type 3, angiotensinogen, deltex-1, thrombospondin-4, ADAMTS-like protein 2, anthrax toxin receptor 1, and cathepsin D. N-terminal pro-hormone B-type natriuretic peptide and angiotensinogen showed the strongest associations [hazard ratio (95% confidence interval): 1.96 (1.17-3.40) and 0.66 (0.49-0.88), respectively]. The multivariable model yielded a c-index of 0.85 upon internal validation and c-indices up to 0.80 upon external validation. The c-index was higher than that of a model containing established risk factors (P = 0.021).

Conclusion: Nine serially measured proteins captured the most essential prognostic information for the occurrence of adverse events in patients with HFrEF, and provided incremental value for HF prognostication beyond established risk factors. These proteins could be used for dynamic, individual risk assessment in a prospective setting. These findings also illustrate the potential value of relatively 'novel' biomarkers for prognostication.

Clinical trial registration: https://clinicaltrials.gov/ct2/show/NCT01851538?term=nCT01851538&draw=2&rank=1 24.

Keywords: Elastic net; Heart failure; NT-proBNP; Prediction; Proteomics; Repeated measurements.

Associated data

ClinicalTrials.gov/NCT01851538