Machine learning-based detection of sleep-disordered breathing in hypertrophic cardiomyopathy.

BACKGROUND: Hypertrophic cardiomyopathy (HCM) is often concomitant with sleep-disordered breathing (SDB), which can cause adverse cardiovascular events. Although an appropriate approach to SDB prevents cardiac remodelling, detection of concomitant SDB in patients with HCM remains suboptimal. Thus, we aimed to develop a machine learning-based discriminant model for SDB in HCM. METHODS: In the present multicentre study, we consecutively registered patients with HCM and performed nocturnal oximetry. The outcome was a high Oxygen Desaturation Index (ODI), defined as 3% ODI >10, which significantly correlated with the presence of moderate or severe SDB. We randomly divided the whole participants into a training set (80%) and a test set (20%). With data from the training set, we developed a random forest discriminant model for high ODI based on clinical parameters. We tested the ability of the discriminant model on the test set and compared it with a previous logistic regression model for distinguishing SDB in patients with HCM. RESULTS: Among 369 patients with HCM, 228 (61.8%) had high ODI. In the test set, the area under the receiver operating characteristic curve of the discriminant model was 0.86 (95% CI 0.77 to 0.94). The sensitivity was 0.91 (95% CI 0.79 to 0.98) and specificity was 0.68 (95% CI 0.48 to 0.84). When the test set was divided into low-probability and high-probability groups, the high-probability group had a higher prevalence of high ODI than the low-probability group (82.4% vs 17.4%, OR 20.9 (95% CI 5.3 to 105.8), Fisher's exact test p<0.001). The discriminant model significantly outperformed the previous logistic regression model (DeLong test p=0.03). CONCLUSIONS: Our study serves as the first to develop a machine learning-based discriminant model for the concomitance of SDB in patients with HCM. The discriminant model may facilitate cost-effective screening tests and treatments for SDB in the population with HCM.

Np95/Uhrf1 regulates tumor suppressor gene expression of neural stem/precursor cells, contributing to neurogenesis in the adult mouse brain.

Adult neurogenesis is a process of generating new neurons from neural stem/precursor cells (NS/PCs) in restricted adult brain regions throughout life. It is now generally known that adult neurogenesis in the hippocampal dentate gyrus (DG) and subventricular zone participates in various higher brain functions, such as learning and memory formation, olfactory discrimination and repair after brain injury. However, the mechanisms underlying adult neurogenesis remain to be fully understood. Here, we show that Nuclear protein 95 KDa (Np95, also known as UHRF1 or ICBP90), which is an essential protein for maintaining DNA methylation during cell division, is involved in multiple processes of adult neurogenesis. Specific ablation of Np95 in adult NS/PCs (aNS/PCs) led to a decrease in their proliferation and an impairment of neuronal differentiation and to suppression of neuronal maturation associated with the impairment of dendritic formation in the hippocampal DG. We also found that deficiency of Np95 in NS/PCs increased the expression of tumor suppressor genes p16 and p53, and confirmed that expression of these genes in NS/PCs recapitulates the phenotype of Np95-deficient NS/PCs. Taken together, our findings suggest that Np95 plays an essential role in proliferation and differentiation of aNS/PCs through the regulation of tumor suppressor gene expression in adult neurogenesis.

Morphological characteristics of the Holter P-waves associated with pulmonary vein pacing.

AIMS: Identification of arrhythmogenic pulmonary veins (PVs) initiating atrial fibrillation is helpful for catheter ablation. The aim of this study was to examine the possibility to recognize the arrhythmogenic PV using Holter ECG. METHODS AND RESULTS: In 20 patients, P-wave characteristics were studied during pacing from four PVs. Holter ECG was recorded using two leads: the modified CC5 (Lead 1) and NASA (Lead 2), and the P-wave amplitude and duration were evaluated. In Lead 1, P-waves produced by left PV pacing were significantly lower in amplitude than right PV pacing (-3 +/- 75 vs. 86 +/- 43 microV, P < 0.001). In Lead 2, pacing in superior PVs produced P-waves with higher amplitude than inferior PVs (210 +/- 74 vs. 125 +/- 66 muV, P < 0.001). The criteria proposed by the morphological characteristics of P-waves identified putative arrhythmogenic PVs with an accuracy of 78%. CONCLUSION: It might be possible to identify putative arrhythmogenic PVs by modified Holter ECG recording.

Diagnostic usefulness of postexercise systolic blood pressure response for detection of coronary artery disease in patients with echocardiographic left ventricular hypertrophy.

BACKGROUND: Although exercise-induced electrocardiographic ST segment changes are used to detect coronary artery disease (CAD), their diagnostic value is markedly decreased in patients with left ventricular (LV) hypertrophy. There have been no reports concerning postexercise systolic blood pressure (SBP) response in patients with ultrasound echocardiographic (UCG) LV hypertrophy and CAD. METHODS: Sixty-six patients with both UCG-LV hypertrophy (LV mass index 134 g/m2 or greater for men or 110 g/m2 or greater for women) and positive ST depression of at least 0.1 mV during treadmill exercise testing were studied. Coronary cineangiograms showed normal coronary arteries in 19 patients (group 1) and significant CAD in 47 patients (group 2). The SBP ratio was calculated by dividing the SBP 3 min after exercise (3 min SBP) by the SBP at peak exercise (peak SBP). RESULTS: There were no significant differences between the two groups in LV mass index, SBP at rest, exercise duration, ST depression (at rest and exercise-induced) or 3 min SBP. However, the SBP ratio was significantly higher in group 2 compared with group 1 (0.87+/-0.11 versus 1.01+/-0.18; P=0.004). Analysis of relative cumulative frequency distributions revealed an SBP ratio of 0.92 as the cutoff point for distinguishing a UCG-LV hypertrophy patient with CAD from one without CAD. The sensitivity, specificity and accuracy with an SBP ratio of 0.92 and an ST segment depression of at least 0.1 mV on treadmill exercise testing for detecting CAD in patients with UCG-LV hypertrophy were 77%, 74% and 76%, respectively. CONCLUSION: These findings suggest that the ratio of early post-exercise SBP to peak exercise SBP may be diagnostically useful in detecting CAD in patients with positive ST depression during an exercise test and UCG-LV hypertrophy.