Deep Learning Framework for Integrating Multibatch Calibration, Classification, and Pathway Activities.

The amount of available biological data has exploded since the emergence of high-throughput technologies, which is not only revolting the way we recognize molecules and diseases but also bringing novel analytical challenges to bioinformatics analysis. In recent years, deep learning has become a dominant technique in data science. However, classification accuracy is plagued with domain discrepancy.

[Doppler echocardiographic assessment of CarboMedics prosthesis in patients with mitral valve replacement].

Objective: To evaluate the CarboMedics (CM) prosthesis function two years after mitral valve replacement, and to compare the effective orifice area (EOA) calculated by pressure half-time (PHT) method and continuity method (CON).

Methods: Forty nine patients who underwent isolated mitral valve replacement with a CM prosthesis were recruited in this study, which included 13 cases of 25 mm CM prosthesis and 36 cases of 27 mm CM prosthesis. Two years after the mitral valve replacement, transthoracic echocardiography (TTE) was performed, measuring left ventricular ejection fraction (LVEF), stroke volume mean gradient (SV), PHT, peak early mitral diastolic velocity (E velocity), mean gradient (MG), time-velocity integral of left ventricular outflow tract/time-velocity integral of mitral valve prosthesis (TVI(MVP)/TVI(LVOT)).

[Impact of tricuspid annuloplasty on changes of right atrioventricular diameter and annulus in patients with mitral valve replacement].

Objective: To observe changes of right atrioventricular diameter and annulus after mitral valve replacement (MVR) in patients with and without tricuspid annuloplasty.

Methods: A total of 112 patients who underwent MVR surgery from April 2005 to December 2006 were recruited in this study. The patients were divided into two groups.