Rosenson, Robert S.

Abstract BACKGROUND Dyslipoproteinemias can be classified by their distinct lipoprotein patterns, which helps determine atherosclerotic cardiovascular disease (ASCVD) risk and directs lipid management but this has required advanced laboratory testing. OBJECTIVE To develop a new algorithm for classifying lipoprotein disorders that only relies on the standard lipid panel. METHODS Lipid thresholds for defining the different lipoprotein phenotypes were derived for Non-High-Density Lipoprotein-Cholesterol (NonHDL-C) and Triglycerides (TG) to be concordant when possible with the current US Multi-Society guidelines for blood cholesterol management. RESULTS The new classification method categorizes patients into all the classical Fredrickson-like phenotypes except for Type III dysbetalipoproteinemia. In addition, a new hypolipidemic phenotype (Type VI) due to genetic mutations in apoB-metabolism is described. The validity of the new algorithm was confirmed by lipid analysis by NMR (N = 11,365) and by concordance with classification by agarose gel electrophoresis/beta-quantification (N = 5504). Furthermore, based on the Atherosclerosis Risk in Communities (ARIC) cohort (N = 14742), the lipoprotein phenotypes differ in their association with ASCVD (TypeV > IIb > IVb > IIa > IVa > normolipidemic) and can be used prognostically as risk enhancer conditions in the management of patients. CONCLUSIONS We describe a clinically useful lipoprotein phenotyping system that is only dependent upon the standard lipid panel. It, therefore, can be easily implemented for increasing compliance with current guidelines and for improving the care of patients at risk for ASCVD.

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.