Deep learning-based NT-proBNP prediction from the ECG for risk assessment in the community
Standard
Deep learning-based NT-proBNP prediction from the ECG for risk assessment in the community. / Neyazi, Meraj; Bremer, Jan P; Knorr, Marius S; Gross, Stefan; Brederecke, Jan; Schweingruber, Nils; Csengeri, Dora; Schrage, Benedikt; Bahls, Martin; Friedrich, Nele; Zeller, Tanja; Felix, Stephan; Blankenberg, Stefan; Dörr, Marcus; Vollmer, Marcus; Schnabel, Renate B.
In: CLIN CHEM LAB MED, Vol. 62, No. 4, 25.03.2024, p. 740-752.Research output: SCORING: Contribution to journal › SCORING: Journal article › Research › peer-review
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - JOUR
T1 - Deep learning-based NT-proBNP prediction from the ECG for risk assessment in the community
AU - Neyazi, Meraj
AU - Bremer, Jan P
AU - Knorr, Marius S
AU - Gross, Stefan
AU - Brederecke, Jan
AU - Schweingruber, Nils
AU - Csengeri, Dora
AU - Schrage, Benedikt
AU - Bahls, Martin
AU - Friedrich, Nele
AU - Zeller, Tanja
AU - Felix, Stephan
AU - Blankenberg, Stefan
AU - Dörr, Marcus
AU - Vollmer, Marcus
AU - Schnabel, Renate B
N1 - © 2023 Walter de Gruyter GmbH, Berlin/Boston.
PY - 2024/3/25
Y1 - 2024/3/25
N2 - OBJECTIVES: The biomarker N-terminal pro B-type natriuretic peptide (NT-proBNP) has predictive value for identifying individuals at risk for cardiovascular disease (CVD). However, it is not widely used for screening in the general population, potentially due to financial and operational reasons. This study aims to develop a deep-learning model as an efficient means to reliably identify individuals at risk for CVD by predicting serum levels of NT-proBNP from the ECG.METHODS: A deep convolutional neural network was developed using the population-based cohort study Hamburg City Health Study (HCHS, n=8,253, 50.9 % women). External validation was performed in two independent population-based cohorts (SHIP-START, n=3,002, 52.1 % women, and SHIP-TREND, n=3,819, 51.2 % women). Assessment of model performance was conducted using Pearson correlation (R) and area under the receiver operating characteristics curve (AUROC).RESULTS: NT-proBNP was predictable from the ECG (R, 0.566 [HCHS], 0.642 [SHIP-START-0], 0.655 [SHIP-TREND-0]). Across cohorts, predicted NT-proBNP (pNT-proBNP) showed good discriminatory ability for prevalent and incident heart failure (HF) (baseline: AUROC 0.795 [HCHS], 0.816 [SHIP-START-0], 0.783 [SHIP-TREND-0]; first follow-up: 0.669 [SHIP-START-1, 5 years], 0.689 [SHIP-TREND-1, 7.3 years]), comparable to the discriminatory value of measured NT-proBNP. pNT-proBNP also demonstrated comparable results for other incident CVD, including atrial fibrillation, stroke, myocardial infarction, and cardiovascular death.CONCLUSIONS: Deep learning ECG algorithms can predict NT-proBNP concentrations with high diagnostic and predictive value for HF and other major CVD and may be used in the community to identify individuals at risk. Long-standing experience with NT-proBNP can increase acceptance of such deep learning models in clinical practice.
AB - OBJECTIVES: The biomarker N-terminal pro B-type natriuretic peptide (NT-proBNP) has predictive value for identifying individuals at risk for cardiovascular disease (CVD). However, it is not widely used for screening in the general population, potentially due to financial and operational reasons. This study aims to develop a deep-learning model as an efficient means to reliably identify individuals at risk for CVD by predicting serum levels of NT-proBNP from the ECG.METHODS: A deep convolutional neural network was developed using the population-based cohort study Hamburg City Health Study (HCHS, n=8,253, 50.9 % women). External validation was performed in two independent population-based cohorts (SHIP-START, n=3,002, 52.1 % women, and SHIP-TREND, n=3,819, 51.2 % women). Assessment of model performance was conducted using Pearson correlation (R) and area under the receiver operating characteristics curve (AUROC).RESULTS: NT-proBNP was predictable from the ECG (R, 0.566 [HCHS], 0.642 [SHIP-START-0], 0.655 [SHIP-TREND-0]). Across cohorts, predicted NT-proBNP (pNT-proBNP) showed good discriminatory ability for prevalent and incident heart failure (HF) (baseline: AUROC 0.795 [HCHS], 0.816 [SHIP-START-0], 0.783 [SHIP-TREND-0]; first follow-up: 0.669 [SHIP-START-1, 5 years], 0.689 [SHIP-TREND-1, 7.3 years]), comparable to the discriminatory value of measured NT-proBNP. pNT-proBNP also demonstrated comparable results for other incident CVD, including atrial fibrillation, stroke, myocardial infarction, and cardiovascular death.CONCLUSIONS: Deep learning ECG algorithms can predict NT-proBNP concentrations with high diagnostic and predictive value for HF and other major CVD and may be used in the community to identify individuals at risk. Long-standing experience with NT-proBNP can increase acceptance of such deep learning models in clinical practice.
U2 - 10.1515/cclm-2023-0743
DO - 10.1515/cclm-2023-0743
M3 - SCORING: Journal article
C2 - 37982681
VL - 62
SP - 740
EP - 752
JO - CLIN CHEM LAB MED
JF - CLIN CHEM LAB MED
SN - 1434-6621
IS - 4
ER -