Prediction of early death after atrial fibrillation diagnosis using a machine learning approach: A French nationwide cohort study.

Bisson, Arnaud ORCID: 0000-0002-3449-1800, Lemrini, Yassine, Romiti, Giulio Francesco, Proietti, Marco ORCID: 0000-0003-1452-2478, Angoulvant, Denis, Bentounes, Sidahmed, El-Bouri, Wahbi ORCID: 0000-0002-2732-5927, Lip, Gregory YH ORCID: 0000-0002-7566-1626 and Fauchier, Laurent (2023) Prediction of early death after atrial fibrillation diagnosis using a machine learning approach: A French nationwide cohort study. American heart journal, 265. S0002-8703(23)00203-X-S0002-8703(23)00203-X.

Text 1-s2.0-S000287032300203X-main.pdf - Author Accepted Manuscript Available under License Creative Commons Attribution. Download (1MB) | Preview

Abstract

<h4>Aims</h4>Atrial fibrillation is associated with important mortality but the usual clinical risk factor based scores only modestly predict mortality. This study aimed to develop machine learning models for the prediction of death occurrence within the year following atrial fibrillation diagnosis and compare predictive ability against usual clinical risk scores.<h4>Methods and results</h4>We used a nationwide cohort of 2,435,541 newly diagnosed atrial fibrillation patients seen in French hospitals from 2011 to 2019. Three machine learning models were trained to predict mortality within the first year using a training set (70% of the cohort). The best model was selected to be evaluate and compared with previously published scores on the validation set (30% of the cohort). Discrimination of the best model was evaluated using the C index. Within the first year following atrial fibrillation diagnosis, 342,005 patients (14.4%) died after a period of 83 (SD 98) days (median 37 [10-129]). The best machine learning model selected was a deep neural network with a C index of 0.785 (95% CI, 0.781-0.789) on the validation set. Compared to clinical risk scores, the selected model was superior to the CHA₂DS₂-VASc and HAS-BLED risk scores and superior to dedicated scores such as Charlson Comorbidity Index and Hospital Frailty Risk Score to predict death within the year following atrial fibrillation diagnosis (C indexes: 0.597; 0.562; 0.643; 0.626 respectively. P<0.0001).<h4>Conclusion</h4>Machine learning algorithms predict early death after atrial fibrillation diagnosis and may help clinicians to better risk stratify atrial fibrillation patients at high risk of mortality.<h4>Translational perspective</h4>Atrial fibrillation is responsible for a substantial proportion of short-term mortality making futile, complex and expensive, cardiovascular procedures/devices or therapies that will not change overall prognosis due to competing risk between cardiovascular and non-cardiovascular death. Machine learning algorithms predict early mortality in atrial fibrillation patients with a better ability than previously developed traditional clinical risk scores. A Machine learning approach may help clinicians to better stratify atrial fibrillation patients at high risk of mortality and may assist physicians in decision-making when managing atrial fibrillation patients in a holistic and integrated care manner.

Item Type:	Article
Uncontrolled Keywords:	Cardiovascular, Prevention, Heart Disease, 4 Detection, screening and diagnosis, 4.2 Evaluation of markers and technologies, 3 Good Health and Well Being
Divisions:	Faculty of Health and Life Sciences Faculty of Health and Life Sciences > Institute of Life Courses and Medical Sciences
Depositing User:	Symplectic Admin
Date Deposited:	30 Aug 2023 09:25
Last Modified:	15 Mar 2024 15:52
DOI:	10.1016/j.ahj.2023.08.006
Related URLs:	Author Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3172414