RESUMEN
Cardiovascular disease (CVD) related mortality and morbidity heavily strain society. The relationship between external risk factors and our genetics have not been well established.It is widely acknowledged that environmental influence and individual behaviours play a significant role in CVD vulnerability, leading to the development of polygenic risk scores (PRS). We employed the PRISMA search method to locate pertinent research and literature to extensively review artificial intelligence (AI)-based PRS models for CVD risk prediction.Furthermore, we analyzed and compared conventional vs. AI-based solutions for PRS. We summarized the recent advances in our understanding of the use of AI-based PRS for risk prediction of CVD. Our study proposes three hypotheses: i) Multiple genetic variations and risk factors can be incorporated into AI-based PRS to improve the accuracy of CVD risk predicting. ii) AI-based PRS for CVD circumvents the drawbacks of conventional PRS calculators by incorporating a larger variety of genetic and non-genetic components, allowing for more precise and individualised risk estimations. iii) Using AI approaches, it is possible to significantly reduce the dimensionality of huge genomic datasets, resulting in more accurate and effective disease risk prediction models. Our study highlighted that the AI-PRS model outperformed traditional PRS calculators in predicting CVD risk. Furthermore, using AI-based methods to calculate PRS may increase the precision of risk predictions for CVD and have significant ramifications for individualized prevention and treatment plans.
RESUMEN
OBJECTIVES: Our aim was to investigate the feasibility of digital variance angiography (DVA) in lower extremity CO2 angiography and to compare the quantitative and qualitative performance of the new image processing technique with that of the current reference standard digital subtraction angiography (DSA). MATERIALS AND METHODS: This prospective study enrolled 24 patients (mean age ± SD, 65.5 ± 9.2 years; 14 males, 65.1 ± 7.5 years; 10 females, 66.1 ± 11.6 years) undergoing lower-limb CO2 angiography between December 2017 and April 2018 at 2 clinical centers: The Heart and Vascular Center (HVC) of Semmelweis University, Budapest (7 patients), and the Bács-Kiskun County Hospital (BKCH) in Kecskemét (17 patients). The interventional protocol was similar at both sites, but the image acquisition instruments and protocols were different, which allowed us to investigate DVA in different settings. For comparison, the signal-to-noise ratio (SNR) of DSA and DVA images were calculated. The visual quality of DSA and DVA images were compared by independent clinical specialists using an online questionnaire. Interrater agreement was characterized by percent agreement and Fleiss kappa. The specialists also evaluated in a random and blinded manner the individual DSA and DVA images on a 5-grade scale ranging from poor (1) to outstanding (5) image quality, and the mean ± standard error of mean (SEM) was calculated. RESULTS: A total of 4912 regions of interest were carefully selected in 110 image pairs to determine the SNRs. The ratio of SNRDVA/SNRDSA was calculated. At HVC, it ranged between 2.58 and 4.16 in the anatomical regions (abdominal, iliac, femoral, popliteal, crural, talar), and the overall median value was 3.53, whereas at BKCH the range was 2.71 to 4.92 and the overall median value was 4.52. During the visual evaluation, 120 DSA and DVA image pairs were compared. At HVC in 78%, although at BKCH in 90% of comparisons, it was judged that DVA provided higher quality images. The interrater agreement was 88% (P < 0.001) and 90% (P < 0.01), respectively. DVA images received consistently higher individual rating than DSA images, regardless of the research site and anatomical region. At HVC, the overall DSA and DVA scores (mean ± SEM) were 2.75 ± 0.12 and 3.23 ± 0.16, respectively (P < 0.05), whereas at BKCH these values were 2.49 ± 0.10 and 3.03 ± 0.09, respectively (P < 0.001). CONCLUSIONS: These data show that lower-limb CO2 angiography DVA, regardless of the image acquisition instruments and protocols, produces higher SNR and significantly better image quality than DSA; therefore this new image processing technique might help the widespread use of CO2 as a safer contrast agent in clinical practice.
