Artificial Intelligence and Cardiovascular Risk Prediction: All That Glitters is not Gold

Abstract

Artificial intelligence (AI) is a broad term referring to any automated systems that need ‘intelligence’ to carry out specific tasks. During the last decade, AI-based techniques have been gaining popularity in a vast range of biomedical fields, including the cardiovascular setting. Indeed, the dissemination of cardiovascular risk factors and the better prognosis of patients experiencing cardiovascular events resulted in an increase in the prevalence of cardiovascular disease (CVD), eliciting the need for precise identification of patients at increased risk for development and progression of CVD. AI-based predictive models may overcome some of the limitations that hinder the performance of classic regression models. Nonetheless, the successful application of AI in this field requires knowledge of the potential pitfalls of the AI techniques, to guarantee their safe and effective use in daily clinical practice. The aim of the present review is to summarise the pros and cons of different AI methods and their potential application in the cardiovascular field, with a focus on the development of predictive models and risk assessment tools.

Assisting the implementation of screening for type 1 diabetes by using artificial intelligence on publicly available data

“…Such strategies hold the potential to provide clinicians with interventions—whether they involve disease modification or prevention—tailored to the specific traits of individuals. Prediction algorithms using AI approaches for cancer [ 20 , 21 ], CVD [ 22 ] and autoimmunity [ 23 – 25 ] have shown promising results. AI has also been applied in type 1 diabetes, for instance in optimising insulin pump settings [ 26 ], in potentially identifying predictive biomarkers [ 27 ] and for the detection of complications [ 28 ].…”

Unveiling the future of cardiac care: advances in mechanical circulatory support

“…Moreover, the application of AI in cardiovascular medicine extends beyond risk prediction to encompass areas such as the development of AI-enabled models for early detection of conditions like left ventricular hypertrophy (LVH) and mortality prediction in young to middle-aged adults using electrocardiograms (ECGs) [79]. AI has also been instrumental in predicting patient age from ECGs, offering a potential biomarker for cardiovascular age that correlates with mortality and comorbidities [80].…”

Personalized Approaches to Antiplatelet Treatment for Cardiovascular Diseases: An Umbrella Review

“…Another well-known limitation of risk scores is that they are usually derived by applying classical statistic regression models and tend to underestimate interactions between variables in complex scenarios, especially when a large number of clinical, anatomical, and procedural features may be reciprocally influenced. 20 Novel opportunities may reside in the ability of artificial intelligence (AI) in generating decision pathways truly individualized for every single patient. 21 As an example, the PRAISE score, a risk score aimed to predict 1-year post-discharge all-cause death, myocardial infarction, and major bleeding, was recently derived using a machine learning model trained on a cohort of 19,826 ACS patients from the BleeMACS and RENAMI registries.…”