Baber, Usman

Abstract Background Pulmonary embolism (PE) is a life-threatening cardiovascular condition. Studies showed that PE patients were associated with disorders of lipid metabolism and had higher triglyceride and lower HDL-C levels compared with healthy. We conducted the genome-wide association study to identify novel loci contributing to PE. Methods We conducted a large-scale GWAS of PE in 5,466 PE cases and 461,219 controls of European ancestry from the UK Biobank (466,685 participants total). We used genome-wide summary statistics to test for enrichment of functional annotations using ENRICHR. Example pathways included in Enrichr for testing include membership of genes in pathway databases such as the Kyoto Encyclopedia of Genes and Genomes (KEGG), Wikipathway, PANTHER, BioCarta or NCI-Nature pathways. We analyzed the pathways using combined score and p-values which were well validated by comparing to several methods. For pathway analyses, we considered a nominal P-value threshold of 0.05. Results We identified genome-wide significant genetic associations in 63 independent genetic loci for PE (P<5.0x10–7). Our findings for top pathways highlight that lipid metabolism (LIPC, LCAT, NPC2), caffeine metabolism (NAT2), and sudden cardiac death (ABCG8) related genetic loci play an important role in PE alongside genes already associated with coagulation-thrombosis pathway (VWF, THPO, PTPN11, INPP5D, UROS, HMBS) (all p-values p-values <0.05). Conclusion Our findings uncovered unexpected novel factors of PE etiology, suggesting novel mechanistic concepts of PE pathophysiology. Funding Acknowledgement Type of funding source: None

Abstract Deep learning (DL) is a branch of machine learning (ML) showing increasing promise in medicine, to assist in data classification, novel disease phenotyping and complex decision making. Deep learning is a form of ML typically implemented via multi-layered neural networks. Deep learning has accelerated by recent advances in computer hardware and algorithms and is increasingly applied in e-commerce, finance, and voice and image recognition to learn and classify complex datasets. The current medical literature shows both strengths and limitations of DL. Strengths of DL include its ability to automate medical image interpretation, enhance clinical decision-making, identify novel phenotypes, and select better treatment pathways in complex diseases. Deep learning may be well-suited to cardiovascular medicine in which haemodynamic and electrophysiological indices are increasingly captured on a continuous basis by wearable devices as well as image segmentation in cardiac imaging. However, DL also has significant weaknesses including difficulties in interpreting its models (the ‘black-box’ criticism), its need for extensive adjudicated (‘labelled’) data in training, lack of standardization in design, lack of data-efficiency in training, limited applicability to clinical trials, and other factors. Thus, the optimal clinical application of DL requires careful formulation of solvable problems, selection of most appropriate DL algorithms and data, and balanced interpretation of results. This review synthesizes the current state of DL for cardiovascular clinicians and investigators, and provides technical context to appreciate the promise, pitfalls, near-term challenges, and opportunities for this exciting new area.