Automated Pattern Recognition in Whole-Cardiac Cycle Echocardiographic Data: Capturing Functional Phenotypes with Machine Learning.

BACKGROUND: Echocardiography provides complex data on cardiac function that can be integrated into patterns of dysfunction related to the severity of cardiac disease. The aim of this study was to demonstrate the feasibility of applying machine learning (ML) to automate the integration of echocardiographic data from the whole cardiac cycle and to automatically recognize patterns in velocity profiles and deformation curves, allowing the identification of functional phenotypes. METHODS: Echocardiography was performed in 189 clinically managed patients with hypertension and 97 healthy individuals without hypertension. Speckle-tracking analysis of the left ventricle and atrium was performed, and deformation curves were extracted. Aortic and mitral blood pool pulsed-wave Doppler and mitral annular tissue pulsed-wave Doppler velocity profiles were obtained. These whole-cardiac cycle deformation and velocity curves were used as ML input. Unsupervised ML was used to create a representation of patients with hypertension in a virtual space in which patients are positioned on the basis of the similarity of their integrated whole-cardiac cycle echocardiography data. Regression methods were used to explore patterns of echocardiographic traces within this virtual ML-derived space, while clustering was used to define phenogroups. RESULTS: The algorithm captured different patterns in tissue and blood-pool velocity and deformation profiles and integrated the findings, yielding phenotypes related to normal cardiac function and others to advanced remodeling associated with pressure overload in hypertension. The addition of individuals without hypertension into the ML-derived space confirmed the interpretation of normal and remodeled phenotypes. CONCLUSIONS: ML-based pattern recognition is feasible from echocardiographic data obtained during the whole cardiac cycle. Automated algorithms can consistently capture patterns in velocity and deformation data and, on the basis of these patterns, group patients into interpretable, clinically comprehensive phenogroups that describe structural and functional remodeling. Automated pattern recognition may potentially aid interpretation of imaging data and diagnostic accuracy.

Lower Platelet Count Following Rabbit Antithymocyte Globulin Induction Is Associated With Less Acute Cellular Rejection in Heart Transplant Recipients.

BACKGROUND: Unlike lymphodepletion, a decrease in platelet count following induction immunosuppressive therapy with polyclonal rabbit antithymocyte globulin (rATG) is deemed as an adverse event. However, this phenomenon may represent a particular rATG antirejection mechanism. METHODS: This retrospective single-center study included 156 patients who received a heart transplant (HTx) between 2010 and 2018. All patients received rATG induction therapy for 5 days. Absolute lymphocyte count (ALC) and platelet counts were assessed on days 0, 7, and 14 following HTx. The primary outcome of the study was the first occurrence of acute cellular rejection (ACR) defined as grade ≥ 1B within 24 months after HTx. RESULTS: Both ALC and platelet counts decreased rapidly after induction. During the 24-month follow-up period, 17% of patients had ACR. Patients with ACR had significantly higher platelet count on day 7 (145 vs 104, P < .001) and higher ALC on day 14 (162 vs 130, P = .035) than those without rejection. Patients in the highest platelet count quartile showed more ACR (50% in quartile 4 vs 0% in quartile 1, P = .006) as well as a higher cumulative total rejection score. Univariate analysis showed that ACR was associated with platelet count on day 7, recipient age, and pretransplant cytomegalovirus IgG serology. In multivariable regression analysis, platelet count on day 7 was the most accurate predictor of ACR. CONCLUSIONS: Lower platelet count after induction with rATG is associated with less ACR. This suggests platelet involvement in antirejection mechanisms of rATG and a possible rationale for targeting platelets in future immunosuppressive strategies.

Distribution of myocardial work in arterial hypertension: insights from non-invasive left ventricular pressure-strain relations.

A index of non-invasive myocardial work (MWI) can account for pressure during the assessment of cardiac function, potentially separating the influence of loading conditions from the influence of the underlying tissue remodelling. The aim is to assess LV function accounted for loading and explore hypertensive MWI distribution by comparing healthy individuals to hypertensive patients without and with localized basal septal hypertrophy (BSH). An echocardiogram was performed in 170 hypertensive patients and 20 healthy individuals. BSH was defined by a basal-to-mid septal wall thickness ratio ≥ 1.4. LV speckle-tracking was performed, and the MWI calculated globally and regionally for the apical, mid and basal regions. An apex-to-base gradient, seen in regional strain values, was preserved in the distribution of myocardial work, with the apical region compensating for the impairment of the basal segments. This functional redistribution was further pronounced in patients with localized BSH. In these patients, segmental MWI analysis revealed underlying impairment of regional work unrelated to acute loading conditions. Non-invasive MWI analysis offers the possibility to compare LV function regardless of blood pressure at the time of observation. Changes in MWI distribution can be seen in hypertension unrelated to the load-dependency of strain. Accentuated functional changes affirm the role of BSH as an echocardiographic marker in hypertension.

Basal Ventricular Septal Hypertrophy in Systemic Hypertension.

Basal septal hypertrophy (BSH) is commonly seen in patients with systemic hypertension and has been associated with increased afterload. The impact of localized hypertrophy on left ventricular (LV) and left atrial (LA) function is still unclear. Our aim is to investigate if BSH is a marker of a more pronounced impact of hypertension on cardiac function in the early stages of hypertensive heart disease. An echocardiogram was performed in 163 well-controlled hypertensive patients and 22 healthy individuals. BSH was defined by a basal-to-mid septal thickness ratio ≥1.4. LV dimensions and mass were evaluated. LV global and regional deformation was assessed by 2-dimensional (2D) speckle tracking echocardiography, and LV diastolic function by 2D and Doppler imaging. LA function was evaluated with phasic volume indices calculated from 2D and 3-dimensional volumes, as well as speckle tracking echocardiography. The population was 54% men, mean age 57 (53 to 60) years. BSH was seen in 20% (n = 32) of the hypertensive cohort. Patients with BSH showed decreased regional LV systolic deformation, impaired LV relaxation with a higher proportion of indeterminate LV diastolic function, and LA functional impairment defined by a reduction of reservoir strain and a change in LA functional dynamics. In conclusion, in well-controlled hypertension impairment of LV and LA function is present in patients with early LV remodeling and localized hypertrophy. BSH might be useful as an early marker of the burden of hypertensive heart disease.

Left Ventricular Size and Ejection Fraction: Are They Still Relevant?

Despite the rapid development of emerging imaging technologies, left ventricular ejection fraction represents the cornerstone of diagnosis, choice of treatment, and prognosis in heart failure. However, true myocardial function often remains underestimated or overestimated in different conditions underlying this heterogeneous syndrome. Changes in left ventricular size and left ventricular ejection fraction, termed reverse remodeling, are among the main goals of treatment in heart failure, aimed at halting or attenuating disease progression. The lack of effective therapeutic approaches in nearly one-half of the heart failure population highlights the need for integrating novel echocardiographic measures to better understand the underlying pathophysiologic mechanisms.

Microcirculation and Heart Failure.

The idea of coronary microcirculation playing a role in the pathophysiology of heart failure dates from decades ago, with authors hypothesizing that structural and functional alterations in the coronary microcirculation could potentially contribute to heart failure. It is known that in a wide range of primary cardiomyopathies, from dilated to hypertrophic, there are pathological alterations in myocardial vasculature structure and function, playing a role in the clinical course of the disease. Needless to say, many patients with normal epicardial coronary arteries can suffer from coronary microvascular dysfunction, that could lead to a wide variety of clinical problems - from impaired functional capacity to stable and unstable angina, Takotsubo syndrome, myocardial infarction with normal coronary arteries and can also end up with either acute or chronic heart failure. Furthermore, nowadays, it has been recognized that pathophysiology of the heart failure with preserved ejection fraction (HFpEF) is mainly due to the myocardial microcirculatory impairment. In heart failure with reduced ejection fraction (HFrEF) neurohumoral mechanisms affecting the peripheral vasculature have been identified as important factors in the development and progression of heart failure, leading to unfavourable remodelling, and thus some of them being important treatment targets. Among many new clinical scenarios where both myocardial and peripheral microcirculation play an important role, raising field of implantable continuous flow assist devices opens many questions and implies better understanding of their effects of microcirculation, as they usually lead to the improvement of end organ dysfunction caused by previous heart failure, which is probably through the positive effects of peripheral microcirculation.

The expression of SFRP1, SFRP3, DVL1, and DVL2 proteins in testicular germ cell tumors.

Germ cell tumors of the testis are a heterogeneous group of neoplasms that affect male adolescents and young adults. Wnt signaling pathway components have been shown to be actively involved in normal and malignant germ cell differentiation and progression. In this study, we aimed to explore the expression patterns of the secreted frizzled-related protein (SFRP) and Disheveled protein family (DVL) in a subset of testicular germ cell tumors. Eighty-five formalin-fixed, paraffin-embedded tissue samples of the primary germ cell tumors of the testis were stained against SFRP1, SFRP3, DVL1, and DVL2 proteins using immunohistochemistry. SFRP1 and SFRP3 exhibited lower expression in both seminomas and mixed/non-seminomatous tumors, compared with atrophic/benign tissue (p < 0.001). SFRP3 expression was lower than SFRP1 expression within the seminoma group (p = 0.004), but not within the mixed/non-seminomatous group (p = 0.409). The majority of the tested cases (27/28, 96%) exhibited low DVL1 protein expression (median 0%, range 0-90%). In contrast, 20 out of 22 tested cases (91%) exhibited strong expression of DVL2 protein (median 80%, range 0-100%). No significant difference in DVL1 and DVL2 protein expression was observed between seminomas and mixed/non-seminomatous tumors (p = 0.68 and 0.29). The secreted frizzled-related protein and disheveled protein family members appear to be actively involved in the pathogenesis of primary testicular germ cell tumors.

Immunohistochemical expression of SFRP1 and SFRP3 proteins in normal and malignant reproductive tissues of rats and humans.

Secreted frizzled-related proteins 1 and 3 (SFRP1 and SFRP3) act as Wnt signaling pathway antagonists and play an important role in embryonic development and carcinogenesis. The aim of the present study was to analyze immunohistochemically the distribution of 2 SFRP family proteins, SFRP1 and SFRP3, in an experimental rat model, in normal and intrauterine growth-restricted (IUGR) human placentas, and in a subset of the corresponding human trophoblastic tumors (pure choriocarcinomas and mixed germ cell tumors with choriocarcinoma component). In rats, expression of both SFRP1 and SFRP3 was pronounced in the perimetrium and myometrium, whereas decidual cells showed only occasional positive cytoplasmic staining. The most prominent expression of both proteins was found in blood vessel endothelial cells. Stereological variable of volume density (Vv, mm) showed statistically higher expression of SFRP1 and SFRP3 in human IUGR placentas than in normal pregnancy placentas (P<0.0001). Compared with adjacent normal/benign tissues, reduced expression of SFRP1 and SFRP3 was observed in human trophoblastic tumors (58.5% and 31.25%, respectively), although none of the examined tumors exhibited complete loss of either protein. Our study indicates that increased expression of both SFRP1 and SFRP3 may contribute to the pathogenesis of IUGR placental dysfunction, whereas the loss of these proteins may be involved in the development of human trophoblastic tumors.

Impact of 5-azacytidine on rat decidual cell proliferation.

The DNA demethylating agent 5-azacytidine (5-azaC) has a teratogenic influence during rat development influencing both the embryo and the placenta. Our aim was to investigate its impact on early decidual cell proliferation before the formation of placenta. Thus, female Fischer rats received 5-azaC (5 mg/kg, i.p.) on the 2nd, 5th or 8th day of gestation and the decidual tissues were harvested on gestation day 9. They were then analysed immunohistochemically for expression of cell proliferation marker proliferating cell nuclear antigen (PCNA) in decidual cells and for global DNA methylation using the coupled restriction enzyme digestion, random amplification and pyrosequencing assays. We found that 5-azaC administered on the 5th and 8th (but not on 2nd) day of gestation led to increased PCNA expression in decidual cells compared with untreated controls. No significant changes in DNA methylation were detected, with either method, in any of the treated rat groups compared with untreated controls. Thus, we conclude that 5-azaC can stimulate decidual cell proliferation without simultaneously changing global DNA methylation level in treated cells.

Epigenetic control of cell invasion - the trophoblast model.

Abstract Trophoblast implantation and placentation allow the survival of the young embryo and its normal development inside the uterus. In order for these processes to function properly, the trophoblast has to undergo a series of characteristic changes that lead to its adhesion and invasion of the uterus. This is achieved, among other mechanisms, by inactivation of specific tumor suppressor genes, commonly by methylation of their promoters. Cell adhesion and tissue invasion are also characteristics of malignant tumors and patterns of methylation similar to that seen in trophoblast are found in various tumor types. Another important mechanism that aids trophoblast cells invasion is their transition from epithelial to mesenchymal phenotype. Such a transition is also a common characteristic of invading malignant cells. Thus, studying tissue invasion and its control mechanisms can benefit the understanding of both the trophoblast and malignant cells behavior.