Improving 1-year mortality prediction in ACS patients using machine learning.

Weichwald, Sebastian; Candreva, Alessandro; Burkholz, Rebekka; Klingenberg, Roland; Räber, Lorenz; Heg, Dik; Manka, Robert; Gencer, Baris; Mach, François; Nanchen, David; Rodondi, Nicolas; Windecker, Stephan; Laaksonen, Reijo; Hazen, Stanley L; von Eckardstein, Arnold; Ruschitzka, Frank; Lüscher, Thomas F; Buhmann, Joachim M; Matter, Christian M (2021). Improving 1-year mortality prediction in ACS patients using machine learning. (In Press). European Heart Journal: Acute Cardiovascular Care Sage 10.1093/ehjacc/zuab030

[img] Text
Weichwald_EurHeartJAcuteCardiovascCare_2021_epub.pdf - Published Version
Restricted to registered users only
Available under License Publisher holds Copyright.

Download (970kB) | Request a copy

BACKGROUND

The Global Registry of Acute Coronary Events (GRACE) score is an established clinical risk stratification tool for patients with acute coronary syndromes (ACS). We developed and internally validated a model for 1-year all-cause mortality prediction in ACS patients.

METHODS

Between 2009 and 2012, 2'168 ACS patients were enrolled into the Swiss SPUM-ACS Cohort. Biomarkers were determined in 1'892 patients and follow-up was achieved in 95.8% of patients. 1-year all-cause mortality was 4.3% (n = 80). In our analysis we consider all linear models using combinations of 8 out of 56 variables to predict 1-year all-cause mortality and to derive a variable ranking.

RESULTS

1.3% of 1'420'494'075 models outperformed the GRACE 2.0 Score. The SPUM-ACS Score includes age, plasma glucose, NT-proBNP, left ventricular ejection fraction (LVEF), Killip class, history of peripheral artery disease (PAD), malignancy, and cardio-pulmonary resuscitation. For predicting 1-year mortality after ACS, the SPUM-ACS Score outperformed the GRACE 2.0 Score which achieves a 5-fold cross-validated AUC of 0.81 (95% CI 0.78-0.84). Ranking individual features according to their importance across all multivariate models revealed age, trimethylamine N-oxide, creatinine, history of PAD or malignancy, LVEF, and haemoglobin as the most relevant variables for predicting 1-year mortality.

CONCLUSIONS

The variable ranking and the selection for the SPUM-ACS Score highlight the relevance of age, markers of heart failure, and comorbidities for prediction of all-cause death. Before application, this score needs to be externally validated and refined in larger cohorts.

CLINICAL TRIAL REGISTRATION

NCT01000701.

Item Type:

Journal Article (Original Article)

Division/Institute:

04 Faculty of Medicine > Department of General Internal Medicine (DAIM) > Clinic of General Internal Medicine > Centre of Competence for General Internal Medicine
04 Faculty of Medicine > Medical Education > Institute of General Practice and Primary Care (BIHAM)
04 Faculty of Medicine > Pre-clinic Human Medicine > CTU Bern
04 Faculty of Medicine > Department of Cardiovascular Disorders (DHGE) > Clinic of Cardiology

UniBE Contributor:

Räber, Lorenz; Heg, Dierik Hans; Rodondi, Nicolas and Windecker, Stephan

Subjects:

600 Technology > 610 Medicine & health
300 Social sciences, sociology & anthropology > 360 Social problems & social services

ISSN:

2048-8734

Publisher:

Sage

Language:

English

Submitter:

Andrea Flükiger-Flückiger

Date Deposited:

27 May 2021 17:19

Last Modified:

28 May 2021 21:40

Publisher DOI:

10.1093/ehjacc/zuab030

PubMed ID:

34015112

Uncontrolled Keywords:

Acute Coronary Syndromes GRACE 2.0 Score Machine Learning NT-proBNP age

BORIS DOI:

10.48350/156525

URI:

https://boris.unibe.ch/id/eprint/156525

Actions (login required)

Edit item Edit item
Provide Feedback