Abstract
The accurate assessment of a patient’s risk of adverse events remains a mainstay of clinical care. Commonly used risk metrics have been based on logistic regression models that incorporate aspects of the medical history, presenting signs and symptoms, and lab values. More sophisticated methods, such as Artificial Neural Networks (ANN), form an attractive platform to build risk metrics because they can easily incorporate disparate pieces of data, yielding classifiers with improved performance. Using two cohorts consisting of patients admitted with a non-ST-segment elevation acute coronary syndrome, we constructed an ANN that identifies patients at high risk of cardiovascular death (CVD). The ANN was trained and tested using patient subsets derived from a cohort containing 4395 patients (Area Under the Curve (AUC) 0.743) and validated on an independent holdout set containing 861 patients (AUC 0.767). The ANN 1-year Hazard Ratio for CVD was 3.72 (95% confidence interval 1.04–14.3) after adjusting for the TIMI Risk Score, left ventricular ejection fraction, and B-type natriuretic peptide. A unique feature of our approach is that it captures small changes in the ST segment over time that cannot be detected by visual inspection. These findings highlight the important role that ANNs can play in risk stratification.
Highlights
The Harvard community has made this article openly available
We restricted our analysis to patients who had at least one day of continuous ECG signal and values for seven baseline characteristics: age, gender, current smoker, history of hypertension, history of diabetes, previous myocardial infarction (MI), and a history of previous angiography
Our results demonstrate that signal processing and machine learning can be used to generate patient risk models with improved performance compared to traditional logistic regression techniques
Summary
The Harvard community has made this article openly available. Please share how this access benefits you. Used risk metrics have been based on logistic regression models that incorporate aspects of the medical history, presenting signs and symptoms, and lab values More sophisticated methods, such as Artificial Neural Networks (ANN), form an attractive platform to build risk metrics because they can incorporate disparate pieces of data, yielding classifiers with improved performance. A unique feature of our approach is that it captures small changes in the ST segment over time that cannot be detected by visual inspection These findings highlight the important role that ANNs can play in risk stratification. The effective treatment of patients who have suffered an ACS necessitates an accurate assessment of that patient’s risk of subsequent adverse cardiovascular events, thereby permitting accurate risk stratification and the delivery of appropriate therapy. The process of categorising patients according to their risk – a process called risk stratification – is a core part of the management of patients post-ACS
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
