Delirium, an acute alteration in attention and cognition, is the most common neurological complication after cardiac surgery in older patients, and it has been shown to be associated with multiple negative outcomes, such as mortality, morbidity, increased length of hospital stay, functional and cognitive decline, increased medical costs, and reduced health-related quality of life [1][2][3][4][5][6][7]. The incidence of delirium greatly increases with age [8-10], and it is expected to continue to increase as the population ages, especially in an aging society such as that in Japan.The rate of physical frailty and cognitive impairment also increases with age, and they are well-known risk factors for the incidence of delirium after surgery [11][12][13][14][15][16]. As delirium is thought to result from acute stress on the "vulnerable" body and brain, attention should be paid to both physical and cognitive functions for better perioperative care in older patients. Further, in a previous study, mild cognitive impairment (MCI), the transitional state between cognitive change associated with normal aging and dementia, has also been detected as a risk factor for delirium [17]. Therefore, close attention should be paid to patients who show even mild decline in cognitive function.Several cross-sectional studies have reported an association between physical frailty and cognitive function [18,19]. In addition,

AimsNon-linear models by machine learning may identify different risk factors with different weighting in comparison to conventional linear models.Methods and resultsThe analyses were performed in 15,933 patients included in the Shinken Database (SD) 2004–2014 (n = 22,022) for whom baseline data of blood sampling and ultrasound cardiogram and follow-up data at 2 years were available. Using non-linear models with machine learning software, 118 risk factors and their weighting of risk for all-cause mortality, heart failure (HF), acute coronary syndrome (ACS), ischemic stroke (IS), and intracranial hemorrhage (ICH) were identified, where the top two risk factors were albumin/hemoglobin, left ventricular ejection fraction/history of HF, history of ACS/anti-platelet use, history of IS/deceleration time, and history of ICH/warfarin use. The areas under the curve of the developed models for each event were 0.900, 0.912, 0.879, 0.758, and 0.753, respectively.ConclusionHere, we described our experience with the development of models for predicting cardiovascular prognosis by machine learning. Machine learning could identify risk predicting models with good predictive capability and good discrimination of the risk impact.

No abstract

No abstract

The relationship between myocardial bridging (MB) and coronary spasms during spasm provocation testing (SPT) remains unclear. We aimed to investigate whether MB was correlated with the SPT by ergonovine (ER) injections in a retrospective observational study. Of the 3340 patients who underwent a first coronary angiography, 166 underwent SPT using ER injections and were divided into 2 groups: MB(+) (n = 23), and MB(−) (n = 143). MB was defined as an angiographic reduction in the diameter of the coronary artery during systole. The patients who had severe organic stenosis in the left anterior descending coronary artery were excluded. The MB(+) group more frequently had diabetes mellitus and chronic kidney disease, and a thicker interventricular septum thickness. The rate of SPT-positivity was higher in the MB(+) group than MB(−) group (56.5% vs. 22.4%, P = 0.001). A multivariate regression analysis showed that the presence of MB was independently associated with SPT-positivity (odds ratio 5.587, 95% confidence interval 2.061–15.149, P = 0.001). In conclusion, coronary spasms during provocation tests with ER independently correlated with the MB. MB may predict coronary spasms.