No abstract

Driven by recent developments in computational power, algorithms and web-based storage resources, machine learning (ML)-based artificial intelligence (AI) has quickly gained ground as the solution for many technological and societal challenges. AI education has become very popular and is oversubscribed at Dutch universities. Major investments were made in 2018 to develop and build the first AI-driven hospitals to improve patient care and reduce healthcare costs. AI has the potential to greatly enhance traditional statistical analyses in many domains and has been demonstrated to allow the discovery of ‘hidden’ information in highly complex datasets. As such, AI can also be of significant value in the diagnosis and treatment of cardiovascular disease, and the first applications of AI in the cardiovascular field are promising. However, many professionals in the cardiovascular field involved in patient care, education or science are unaware of the basics behind AI and the existing and expected applications in their field. In this review, we aim to introduce the broad cardiovascular community to the basics of modern ML-based AI and explain several of the commonly used algorithms. We also summarise their initial and future applications relevant to the cardiovascular field.

We aimed to estimate the effects of a lifelong exposure to high systolic blood pressure (SBP) on left ventricular (LV) structure and function using Mendelian randomization. A total of 5596 participants of the UK Biobank were included for whom cardiovascular magnetic resonance imaging and genetic data were available. Major exclusion criteria included nonwhite ethnicity, major cardiovascular disease, and body mass index >30 or <18.5 kg/m 2 . A genetic risk score to estimate genetically predicted SBP (gSBP) was constructed based on 107 previously established genetic variants. Manual cardiovascular magnetic resonance imaging postprocessing analyses were performed in 300 individuals at the extremes of gSBP (150 highest and lowest). Multivariable linear regression analyses of imaging biomarkers were performed using gSBP as continuous independent variable. All analyses except myocardial strain were validated using previously derived imaging parameters in 2530 subjects. The mean (SD) age of the study population was 62 (7) years, and 52% of subjects were female. Corrected for age, sex, and body surface area, each 10 mm Hg increase in gSBP was significantly ( P <0.0056) associated with 4.01 g (SE, 1.28; P =0.002) increase in LV mass and with 2.80% (SE, 0.97; P =0.004) increase in LV global radial strain. In the validation cohort, after correction for age, sex, and body surface area, each 10 mm Hg increase in gSBP was associated with 5.27 g (SE, 1.50; P <0.001) increase in LV mass. Our study provides a novel line of evidence for a causal relationship between SBP and increased LV mass and with increased LV global radial strain.