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.

Pulmonary Tumor Thrombotic Microangiopathy Caused by Metastatic Ovarian Cancer: An Antemortem Diagnosis with Pulmonary Aspiration Cytopathology.

A 48-year-old woman with advanced ovarian cancer was diagnosed with pulmonary tumor thrombotic microangiopathy (PTTM) by antemortem pulmonary wedge aspiration cytopathology. Despite the initiation of anti-cancer treatment, she unfortunately died due to progressive respiratory failure. Histopathology of the autopsied lung revealed multiple tumor embolization with fibrin-rich clot and fibro-cellular intimal proliferation at the pulmonary arteriole. The embolized tumor showed strong immune-positivity for pro-thrombotic and fibrotic factors (tissue factor and vascular endothelial growth factor), suggesting the underlying mechanisms of PTTM development. This case suggests that a quick antemortem diagnosis and the early induction of specific treatments might ensure a better prognosis of PTTM.

Usefulness of P-wave peak time as an electrocardiographic parameter in predicting left ventricular diastolic dysfunction in patients with mitral regurgitation.

INTRODUCTION: Conventional Doppler measurements have limitations in predicting left ventricular diastolic dysfunction (LVDD) in patients with mitral regurgitation (MR). Recently, electrocardiographic P-wave peak time (PWPT) has been proposed as a parameter of detecting LVDD. This study aimed to evaluate the association between PWPT and left ventricular end-diastolic pressure (LVEDP) in patients with MR. METHODS: We performed echocardiography and cardiac catheterization in 82 patients with moderate or severe MR. We classified patients into two groups: low LVEDP group (L-LVEDP) (LVEDP <16 mmHg, n = 40) and high LVEDP group (H-LVEDP) (LVEDP ≥16 mmHg, n = 42). We evaluated LVDD and PWPT based on echocardiographic and electrocardiographic findings in both groups. RESULTS: The PWPT in lead II (PWPTII ) was significantly longer in patients in the H-LVEDP group than in those in the L-LVEDP group (67 vs. 47 ms, p < .001). Using correlation analysis, LVEDP was positively correlated with PWPTII (r = .577, p < .001). Using multivariate analysis, PWPTII was found to be an independent predictor of increased LVEDP (95% CI: 0.1030-0.110; p < .001). Using receiver operating characteristic (ROC) curve analysis, the optimal cutoff value of PWPTII for predicting elevated LVEDP was 58.9 ms, with a sensitivity of 80.0% and a specificity of 73.8% (area under curve: 0.809, 95% CI: 0.713-0.905). CONCLUSION: To the best of our knowledge, this is the first study to assess the effect of a significant valvular disease on PWPT in lead II. These findings suggest that prolonged PWPTII may be an independent predictor of increased LVEDP in patients with moderate or severe MR.

Safety of a Cardiac Resynchronization Therapy Device Implantation in a Patient with Unstable Heart Failure Who Require Impella-Device Assistance.

Implantation of a cardiac resynchronization therapy (CRT) device is usually scheduled in the compensated phase of heart failure; however, procedural safety may be sometimes disturbed in the decompensated phase. We report a case of a successful semi-urgent implantation of a CRT device temporary assisted with Impella in a patient with the decompensated phase of severe heart failure dependent on inotropic agents and who cannot maintain the supine position. Impella assistance with left ventricular (LV) unloading and maintenance of end-organ perfusion contributed to early recovery from acute heart failure. Furthermore, an acute effect of mechanical resynchronization by biventricular pacing plays an important role in weaning from the mechanical support or inotropic dependence. These mutual effects of mechanical support and CRT might contribute to a decrease in LV end-diastolic pressure and to a remarkable early recovery from a severely decompensated condition.

Impact of the Degree of Wire Bias in the Vessel's Healthy Portion on Coronary Perivascular Trauma in Rotational Atherectomy.

BACKGROUND: In rotational atherectomy (RA), the risk of coronary perforation is considered to increase when the wire is in contact with the healthy portion of the vessel. However, the relationship between the extent of wire bias in the healthy portion of the vessel and the risk of coronary perivascular trauma (CPT) has not been reported. METHODS: We examined 90 consecutive cases wherein intravascular ultrasound (IVUS) was performed before and after RA. The IVUS catheter in contact with the healthy region of the vessel was defined as the healthy portion wire bias (HWB), of which we measured the bias diameter, defined as the media-to-media length between the site where the IVUS catheter was in contact and the opposite side of the vessel. The bias ratio was defined as the ratio of the bias diameter to the short diameter at the region where the wire bias was the strongest. The relationship between the bias ratio and the CPT risk was evaluated. RESULTS: CPT was significantly higher in the HWB group than in the non-HWB group (9% vs. 0%, P = 0.048). In the HWB group, the bias ratio was significantly greater in the CPT group than in the non-CPT group (1.31 ±â€¯0.09 vs. 1.06 ±â€¯0.06; P < 0.0001). The cutoff value of the bias ratio for CPT was 1.2, which was the maximum value of the sum of sensitivity 100% and specificity 97%. CONCLUSIONS: Lesions without HWB had no CPT. CPT risk increased when the bias ratio exceeded 1.2.