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