Personalized screening intervals for measurement of N-terminal pro-B-type natriuretic peptide improve efficiency of prognostication in patients with chronic heart failure

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

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.

Personalized screening intervals for kidney function in patients with chronic heart failure: a modeling study

Background

High mortality and rehospitalization rates demonstrate that improving risk assessment in heart failure patients remains challenging. Individual temporal evolution of kidney biomarkers is associated with poor clinical outcome in these patients and hence may carry the potential to move towards a personalized screening approach.

Methods

In 263 chronic heart failure patients included in the prospective Bio-SHiFT cohort study, glomerular and tubular biomarker measurements were serially obtained according to a pre-scheduled, fixed trimonthly scheme. The primary endpoint (PE) comprised cardiac death, cardiac transplantation, left ventricular assist device implantation or heart failure hospitalization. Personalized scheduling of glomerular and tubular biomarker measurements was compared to fixed scheduling in individual patients by means of a simulation study, based on clinical characteristics of the Bio-SHiFT study. For this purpose, repeated biomarker measurements and the PE were jointly modeled. For personalized scheduling, using this fitted joint model, we determined the optimal time point of the next measurement based on the patient’s individual risk profile as estimated by the joint model and the maximum information gain on the patient’s prognosis. We compared the schedule’s capability of enabling timely intervention before the occurrence of the PE and number of measurements needed.

Results

As compared to a pre-defined trimonthly scheduling approach, personalized scheduling of glomerular and tubular biomarker measurements showed similar performance with regard to prognostication, but required a median of 0.4–2.7 fewer measurements per year.

Conclusion

Personalized scheduling is expected to reduce the number of patient visits and healthcare costs. Thus, it may contribute to efficient monitoring of chronic heart failure patients and could provide novel opportunities for timely adaptation of treatment.

Graphic abstract

Supplementary Information

The online version contains supplementary material available at 10.1007/s40620-021-01014-0.