Background Several polygenic risk scores (PRS) have been developed for cardiovascular risk prediction, but the additive value of including PRS together with conventional risk factors for risk prediction is questionable. This study assesses the clinical utility of including four PRS generated from 194, 46K, 1.5M, and 6M SNPs, along with conventional risk factors, to predict risk of ischemic heart disease (IHD), myocardial infarction (MI), and first MI event on or before age 50 (early MI). Methods A cross-validated logistic regression (LR) algorithm was trained either on ~ 440K European ancestry individuals from the UK Biobank (UKB), or the full UKB population, including as features different combinations of conventional established-at-birth risk factors (ancestry, sex) and risk factors that are non-fixed over an individual’s lifespan (age, BMI, hypertension, hyperlipidemia, diabetes, smoking, family history), with and without also including PRS. The algorithm was trained separately with IHD, MI, and early MI as prediction labels. Results When LR was trained using risk factors established-at-birth, adding the four PRS significantly improved the area under the curve (AUC) for IHD (0.62 to 0.67) and MI (0.67 to 0.73), as well as for early MI (0.70 to 0.79). When LR was trained using all risk factors, adding the four PRS only resulted in a significantly higher disease prevalence in the 98th and 99th percentiles of both the IHD and MI scores. Conclusions PRS improve cardiovascular risk stratification early in life when knowledge of later-life risk factors is unavailable. However, by middle age, when many risk factors are known, the improvement attributed to PRS is marginal for the general population.

Modern drug discovery efforts have had mediocre success rates with increasing developmental costs, and this has encouraged pharmaceutical scientists to seek innovative approaches. Recently with the rise of the fields of systems biology and metabolomics, network pharmacology (NP) has begun to emerge as a new paradigm in drug discovery, with a focus on multiple targets and drug combinations for treating disease. Studies on the benefits of drug combinations lay the groundwork for a renewed focus on natural products in drug discovery. Natural products consist of a multitude of constituents that can act on a variety of targets in the body to induce pharmacodynamic responses that may together culminate in an additive or synergistic therapeutic effect. Although natural products cannot be patented, they can be used as starting points in the discovery of potent combination therapeutics. The optimal mix of bioactive ingredients in natural products can be determined via phenotypic screening. The targets and molecular mechanisms of action of these active ingredients can then be determined using chemical proteomics, and by implementing a reverse pharmacokinetics approach. This review article provides evidence supporting the potential benefits of natural product-based combination drugs, and summarizes drug discovery methods that can be applied to this class of drugs.

Abstract:The in utero environment plays an essential role in shaping future growth and development. Psychological distress during pregnancy has been shown to perturb the delicate physiological milieu of pregnancy, and has been associated with negative repercussions in the offspring, including adverse birth outcomes, long-term defects in cognitive development, behavioral problems during childhood and high baseline levels of stress-related hormones. Fetal epigenetic programming, involving epigenetic processes, may help explain the link between maternal prenatal stress and its negative effects on the child. Given the potential long-term effects of early-life stress on a child's health, it is crucial to minimize maternal distress during pregnancy. A number of recent studies have examined the usefulness of mindfulness-based programs to reduce prenatal psychological stress and improve maternal psychological health, and these are reviewed here. Overall, the findings are promising, but more research is needed with large studies using randomized controlled study designs. It remains unclear whether or not such interventions could also improve child health outcomes, and whether these changes are modulated at the epigenetic level during fetal development. Further studies in this area are needed.

Despite the myriad peer-reviewed papers demonstrating novel Artificial Intelligence (AI)-based solutions to COVID-19 challenges during the pandemic, few have made a significant clinical impact, especially in diagnosis and disease precision staging. One major cause for such low impact is the lack of model transparency, significantly limiting the AI adoption in real clinical practice. To solve this problem, AI models need to be explained to users. Thus, we have conducted a comprehensive study of Explainable Artificial Intelligence (XAI) using PRISMA technology. Our findings suggest that XAI can improve model performance, instill trust in the users, and assist users in decisionmaking. In this systematic review, we introduce common XAI techniques and their utility with specific examples of their application. We discuss the evaluation of XAI results because it is an important step for maximizing the value of AI-based clinical decision support systems. Additionally, we present the traditional, modern, and advanced XAI models to demonstrate the evolution of novel techniques. Finally, we provide a best practice guideline that developers can refer to during the model experimentation. We also offer potential solutions with specific examples for common challenges in AI model experimentation. This comprehensive review, hopefully, can promote AI adoption in biomedicine and healthcare.