Developmental delay and failure to thrive associated with a loss-of-function variant in WHSC1 (NSD2).

Wolf-Hirschhorn syndrome (WHS) is a microdeletion syndrome characterized by distinctive facial features consisting of "Greek warrior helmet" appearance, prenatal and postnatal growth deficiency, developmental disability, and seizures. This disorder is caused by heterozygous deletions on chromosome 4p16.3 often identified by cytogenetic techniques. Many groups have attempted to identify the critical region within this deletion to establish which genes are responsible for WHS. Herein, clinical whole exome sequencing (WES) was performed on a child with developmental delays, mild facial dysmorphisms, short stature, failure to thrive, and microcephaly, and revealed a de novo frameshift variant, c.1676_1679del (p.Arg559Tfs*38), in WHSC1 (NSD2). While WHSC1 falls within the WHS critical region, individuals with only disruption of this gene have only recently been described in the literature. Loss-of-function de novo variations in WHSC1 were identified in large developmental delay, autism, diagnostic, and congenital cardiac cohorts, as well as recent case reports, suggesting that de novo loss-of-function WHSC1 variants may be related to disease. These findings, along with our patient suggest that loss-of-function variation in WHSC1 may lead to a mild form of Wolf-Hirschhorn syndrome, and also may suggest that the developmental delays, facial dysmorphisms, and short stature seen in WHS may be due to disruption of WHSC1 gene.

Mortality in Patients with Acute Coronary Syndrome-A Prospective 5-Year Follow-Up Study.

Our objective was to compare long-term outcomes in patients with non-ST-elevation myocardial infarction (NSTEMI) and ST-elevation myocardial infarction (STEMI) between two time periods in Southern Norway. There are limited contemporary data comparing long-term follow-up after revascularization in the last decades. This prospective follow-up study consecutively included both NSTEMI and STEMI patients during two time periods, 2014-2015 and 2004-2009. Patients were followed up for a period of 5 years. The primary outcome was all-cause mortality after 1 and 5 years. A total of 539 patients with acute myocardial infarction (AMI), 316 with NSTEMI (234 included in 2014 and 82 included in 2007) and 223 with STEMI (160 included in 2014 and 63 included in 2004). Mortality after NSTEMI was high and remained unchanged during the two time periods (mortality rate at 1 year: 3.5% versus 4.9%, p = 0.50; and 5 years: 11.4% versus 14.6%, p = 0.40). Among STEMI patients, all-cause mortality at 1 year was reduced in 2014 compared to 2004 (1.3% versus 11.1%, p < 0.001; and 5 years: 7.0% versus 22.2%, p = 0.004, respectively). Time to coronary angiography in NSTEMI patients remained unchanged between 2014 and 2007 (28.2 h [IQR 18.1-46.3] versus 30.3 h [IQR 18.0-48.3], p = 0.20), while time to coronary angiography in STEMI patients was improved in 2014 compared with 2004 (2.8 h [IQR 2.0-4.8] versus 21.7 h [IQR 5.4-27.1], p < 0.001), respectively. During one decade of AMI treatment, mortality in patients with NSTEMI remained unchanged while mortality in STEMI patients decreased, both at 1 and 5 years.

Myocardial Function Imaging in Echocardiography Using Deep Learning.

Deformation imaging in echocardiography has been shown to have better diagnostic and prognostic value than conventional anatomical measures such as ejection fraction. However, despite clinical availability and demonstrated efficacy, everyday clinical use remains limited at many hospitals. The reasons are complex, but practical robustness has been questioned, and a large inter-vendor variability has been demonstrated. In this work, we propose a novel deep learning based framework for motion estimation in echocardiography, and use this to fully automate myocardial function imaging. A motion estimator was developed based on a PWC-Net architecture, which achieved an average end point error of (0.06±0.04) mm per frame using simulated data from an open access database, on par or better compared to previously reported state of the art. We further demonstrate unique adaptability to image artifacts such as signal dropouts, made possible using trained models that incorporate relevant image augmentations. Further, a fully automatic pipeline consisting of cardiac view classification, event detection, myocardial segmentation and motion estimation was developed and used to estimate left ventricular longitudinal strain in vivo. The method showed promise by achieving a mean deviation of (-0.7±1.6)% compared to a semi-automatic commercial solution for N=30 patients with relevant disease, within the expected limits of agreement. We thus believe that learning-based motion estimation can facilitate extended use of strain imaging in clinical practice.

Artificial Intelligence for Automatic Measurement of Left Ventricular Strain in Echocardiography.

OBJECTIVES: This study sought to examine if fully automated measurements of global longitudinal strain (GLS) using a novel motion estimation technology based on deep learning and artificial intelligence (AI) are feasible and comparable with a conventional speckle-tracking application. BACKGROUND: GLS is an important parameter when evaluating left ventricular function. However, analyses of GLS are time consuming and demand expertise, and thus are underused in clinical practice. METHODS: In this study, 200 patients with a wide range of left ventricle (LV) function were included. Three standard apical cine-loops were analyzed using the AI pipeline. The AI method measured GLS and was compared with a commercially available semiautomatic speckle-tracking software (EchoPAC v202, GE Healthcare. RESULTS: The AI method succeeded to both correctly classify all 3 standard apical views and perform timing of cardiac events in 89% of patients. Furthermore, the method successfully performed automatic segmentation, motion estimates, and measurements of GLS in all examinations, across different cardiac pathologies and throughout the spectrum of LV function. GLS was -12.0 ± 4.1% for the AI method and -13.5 ± 5.3% for the reference method. Bias was -1.4 ± 0.3% (95% limits of agreement: 2.3 to -5.1), which is comparable with intervendor studies. The AI method eliminated measurement variability and a complete GLS analysis was processed within 15 s. CONCLUSIONS: Through the range of LV function this novel AI method succeeds, without any operator input, to automatically identify the 3 standard apical views, perform timing of cardiac events, trace the myocardium, perform motion estimation, and measure GLS. Fully automated measurements based on AI could facilitate the clinical implementation of GLS.

Real-Time Automatic Ejection Fraction and Foreshortening Detection Using Deep Learning.

Volume and ejection fraction (EF) measurements of the left ventricle (LV) in 2-D echocardiography are associated with a high uncertainty not only due to interobserver variability of the manual measurement, but also due to ultrasound acquisition errors such as apical foreshortening. In this work, a real-time and fully automated EF measurement and foreshortening detection method is proposed. The method uses several deep learning components, such as view classification, cardiac cycle timing, segmentation and landmark extraction, to measure the amount of foreshortening, LV volume, and EF. A data set of 500 patients from an outpatient clinic was used to train the deep neural networks, while a separate data set of 100 patients from another clinic was used for evaluation, where LV volume and EF were measured by an expert using clinical protocols and software. A quantitative analysis using 3-D ultrasound showed that EF is considerably affected by apical foreshortening, and that the proposed method can detect and quantify the amount of apical foreshortening. The bias and standard deviation of the automatic EF measurements were -3.6 ± 8.1%, while the mean absolute difference was measured at 7.2% which are all within the interobserver variability and comparable with related studies. The proposed real-time pipeline allows for a continuous acquisition and measurement workflow without user interaction, and has the potential to significantly reduce the time spent on the analysis and measurement error due to foreshortening, while providing quantitative volume measurements in the everyday echo lab.

The CELF1 RNA-Binding Protein Regulates Decay of Signal Recognition Particle mRNAs and Limits Secretion in Mouse Myoblasts.

We previously identified several mRNAs encoding components of the secretory pathway, including signal recognition particle (SRP) subunit mRNAs, among transcripts associated with the RNA-binding protein CELF1. Through immunoprecipitation of RNAs crosslinked to CELF1 in myoblasts and in vitro binding assays using recombinant CELF1, we now provide evidence that CELF1 directly binds the mRNAs encoding each of the subunits of the SRP. Furthermore, we determined the half-lives of the Srp transcripts in control and CELF1 knockdown myoblasts. Our results indicate CELF1 is a destabilizer of at least five of the six Srp transcripts and that the relative abundance of the SRP proteins is out of balance when CELF1 is depleted. CELF1 knockdown myoblasts exhibit altered secretion of a luciferase reporter protein and are impaired in their ability to migrate and close a wound, consistent with a defect in the secreted extracellular matrix. Importantly, similar defects in wound healing are observed when SRP subunit imbalance is induced by over-expression of SRP68. Our studies support the existence of an RNA regulon containing Srp mRNAs that is controlled by CELF1. One implication is that altered function of CELF1 in myotonic dystrophy may contribute to changes in the extracellular matrix of affected muscle through defects in secretion.