Journal of internal medicine
-
Machine learning (ML) is a burgeoning field of medicine with huge resources being applied to fuse computer science and statistics to medical problems. Proponents of ML extol its ability to deal with large, complex and disparate data, often found within medicine and feel that ML is the future for biomedical research, personalized medicine, computer-aided diagnosis to significantly advance global health care. However, the concepts of ML are unfamiliar to many medical professionals and there is untapped potential in the use of ML as a research tool. In this article, we provide an overview of the theory behind ML, explore the common ML algorithms used in medicine including their pitfalls and discuss the potential future of ML in medicine.
-
Obesity prevalence continues to rise worldwide, posing a substantial burden on people's health. However, up to 45% of obese individuals do not suffer from cardiometabolic complications, also called the metabolically healthy obese (MHO). Concurrently, up to 30% of normal-weight individuals demonstrate cardiometabolic risk factors that are generally observed in obese individuals, the metabolically obese normal weight (MONW). ⋯ For some, this association was mediated through favourable effects on body fat distribution. Other studies that characterized the genetic susceptibility of insulin resistance found that a higher susceptibility was associated with lower overall adiposity due to less fat accumulation at hips and legs, suggesting that an impaired capacity to store fat subcutaneously or a preferential storage in the intra-abdominal cavity may be metabolically harmful. Clearly, more work remains to be done in this field, first through gene discovery and subsequently through functional follow-up of identified genes.
-
Environmental and socioeconomic changes over the past thirty years have contributed to a dramatic rise in the worldwide prevalence of obesity. Heart disease is amongst the most serious health risks of obesity, with increases in both atherosclerotic coronary heart disease and heart failure among obese individuals. In this review, we focus on primary myocardial alterations in obesity that include hypertrophic remodelling and diastolic dysfunction. ⋯ Lipotoxicity has been modelled in mice using high-fat diet feeding, inbred lines with mutations in leptin receptor signalling, and in genetically engineered mice with enhanced myocardial fatty acid uptake, altered lipid droplet homoeostasis or decreased cardiac fatty acid oxidation. These studies, along with findings in cell culture model systems, indicate that the molecular pathophysiology of lipid overload involves endoplasmic reticulum stress, alterations in autophagy, de novo ceramide synthesis, oxidative stress, inflammation and changes in gene expression. We highlight recent advances that extend our understanding of the impact of obesity and altered lipid metabolism on cardiac function.
-
Statin drugs have been used for more than two decades to treat hypercholesterolemia and as cardio-preventive drugs, resulting in a marked decrease in cardiovascular morbidity and mortality worldwide. Statins halt hepatic cholesterol biosynthesis by inhibiting the rate-limiting enzyme in the mevalonate pathway, hydroxymethylglutaryl-coenzyme A reductase (HMGCR). The mevalonate pathway regulates a host of biochemical processes in addition to cholesterol production. ⋯ Given the compelling evidence from performed trials in a variety of clinical settings, there have been calls for a clinical trial of statins in the adjuvant breast cancer setting. It would be imperative for such a trial to incorporate tumour biomarkers predictive of statin response in its design and analysis plan. Ongoing translational clinical trials aimed at biomarker discovery will help identify, which breast cancer patients are most likely to benefit from adjuvant statin therapy, and will add valuable clinical knowledge to the field.