Citations
Citations
Citations
Citations
Citations
Citations
Machine learning (ML) applications have received extensive attention in endocrinology research during the last decade. This review summarizes the basic concepts of ML and certain research topics in endocrinology and metabolism where ML principles have been actively deployed. Relevant studies are discussed to provide an overview of the methodology, main findings, and limitations of ML, with the goal of stimulating insights into future research directions. Clear, testable study hypotheses stem from unmet clinical needs, and the management of data quality (beyond a focus on quantity alone), open collaboration between clinical experts and ML engineers, the development of interpretable high-performance ML models beyond the black-box nature of some algorithms, and a creative environment are the core prerequisites for the foreseeable changes expected to be brought about by ML and artificial intelligence in the field of endocrinology and metabolism, with actual improvements in clinical practice beyond hype. Of note, endocrinologists will continue to play a central role in these developments as domain experts who can properly generate, refine, analyze, and interpret data with a combination of clinical expertise and scientific rigor.
Citations
Increasing evidence supports interplay between aldosterone and parathyroid hormone (PTH), which may aggravate cardiovascular complications in various heart diseases. Negative structural cardiovascular remodeling by primary aldosteronism (PA) is also suspected to be associated with changes in calcium levels. However, to date, few clinical studies have examined how changes in calcium and PTH levels influence cardiovascular outcomes in PA patients. Therefore, we investigated the impact of altered calcium homeostasis caused by excessive aldosterone on cardiovascular parameters in patients with PA.
Forty-two patients (mean age 48.8±10.9 years; 1:1, male:female) whose plasma aldosterone concentration/plasma renin activity ratio was more than 30 were selected among those who had visited Severance Hospital from 2010 to 2014. All patients underwent adrenal venous sampling with complete access to both adrenal veins.
The prevalence of unilateral adrenal adenoma (54.8%) was similar to that of bilateral adrenal hyperplasia. Mean serum corrected calcium level was 8.9±0.3 mg/dL (range, 8.3 to 9.9). The corrected calcium level had a negative linear correlation with left ventricular end-diastolic diameter (LVEDD, ρ=−0.424,
Aldosterone-mediated hypercalciuria and subsequent hypocalcemia may be partly involved in the development of cardiac remodeling as well as a prolonged QTc interval, in subjects with PA, thereby triggering deleterious effects on target organs additively.
Citations
Adrenal venous sampling (AVS) is a gold standard for subtype classification of primary aldosteronism (PA). However, this procedure has a high failure rate because of the anatomical difficulties in accessing the right adrenal vein. We investigated whether C-arm computed tomography-assisted AVS (C-AVS) could improve the success rate of adrenal sampling.
A total of 156 patients, diagnosed with PA who underwent AVS from May 2004 through April 2017, were included. Based on the medical records, we retrospectively compared the overall, left, and right catheterization success rates of adrenal veins during the periods without C-AVS (2004 to 2010,
With C-AVS, the rates of adequate bilateral AVS increased from 40.6% to 88.7% (
C-AVS improved the overall success rate of AVS, possibly as a result of better catheterization of right adrenal vein.
Citations
Ezetimibe-statin combination therapy has been found to reduce low density lipoprotein cholesterol levels and the risk of major adverse cardiovascular events (MACEs) in large trials. We sought to examine the differential effect of ezetimibe on MACEs when added to statins according to the presence of diabetes.
Randomized clinical trials with a sample size of at least 50 participants and at least 24 weeks of follow-up that compared ezetimibe-statin combination therapy with a statin- or placebo-controlled arm and reported at least one MACE, stratified by diabetes status, were included in the meta-analysis and meta-regression.
A total of seven trials with 28,191 enrolled patients (mean age, 63.6 years; 75.1% men; 7,298 with diabetes [25.9%]; mean follow-up, 5 years) were analysed. MACEs stratified by diabetes were obtained from the published data (two trials) or through direct contact (five trials). No significant heterogeneity was observed among studies (
Ezetimibe-statin combination therapy was associated with greater cardiovascular benefits in patients with diabetes than in those without diabetes. Our findings suggest that ezetimibe-statin combination therapy might be a useful strategy in patients with diabetes at a residual risk of MACEs.
Citations
A recent animal study showed that parathyroid hormone-related peptide (PTHrP) is associated with cancer cachexia by promoting adipose tissue browning, and we previously demonstrated that PTHrP predicts weight loss (WL) in patients with cancer. In this study, we investigated whether prediction of WL by PTHrP is influenced by clinical factors such as serum albumin, corrected calcium levels, cancer stage, and performance status (PS).
A cohort of 219 patients with cancer whose PTHrP level was measured was enrolled and followed for body weight (BW) changes. Subjects were divided into two groups by serum albumin (cutoff value, 3.7 g/dL), corrected calcium (cutoff value, 10.5 mg/dL), cancer stage (stage 1 to 3 or 4), or PS (Eastern Cooperative Oncology Group 0 to 1 or 2 to 4), respectively. Clinically significant WL was defined as either percent of BW change (% BW) <−5% or % BW <−2% plus body mass index (BMI) <20 kg/m2.
After a median follow-up of 327 days, 74 patients (33.8%) experienced clinically significant WL. A positive PTHrP level was associated with a 2-fold increased risk of WL after adjusting for age, baseline BMI, serum albumin, corrected calcium level, cancer stage, and PS. The effect of PTHrP on WL remained significant in patients with low serum albumin, stage 4 cancer, and good PS. Regardless of calcium level, the effect of PTHrP on WL was maintained, although there was an additive effect of higher calcium and PTHrP levels.
Early recognition of patients with advanced cancer who are PTHrP positive with hypercalcemia or hypoalbuminemia is needed for their clinical management.
Citations