Performance of Prediction Models for Diagnosing Severe Aortic Stenosis Based on Aortic Valve Calcium on Cardiac Computed Tomography: Incorporation of Radiomics and Machine Learning

OBJECTIVE

We aimed to develop a prediction model for diagnosing severe aortic stenosis (AS) using computed tomography (CT) radiomics features of aortic valve calcium (AVC) and machine learning (ML) algorithms.

MATERIALS AND METHODS

We retrospectively enrolled 408 patients who underwent cardiac CT between March 2010 and August 2017 and had echocardiographic examinations (240 patients with severe AS on echocardiography [the severe AS group] and 168 patients without severe AS [the non-severe AS group]). Data were divided into a training set (312 patients) and a validation set (96 patients). Using non-contrast-enhanced cardiac CT scans, AVC was segmented, and 128 radiomics features for AVC were extracted. After feature selection was performed with three ML algorithms (least absolute shrinkage and selection operator [LASSO], random forests [RFs], and eXtreme Gradient Boosting [XGBoost]), model classifiers for diagnosing severe AS on echocardiography were developed in combination with three different model classifier methods (logistic regression, RF, and XGBoost). The performance (c-index) of each radiomics prediction model was compared with predictions based on AVC volume and score.

RESULTS

The radiomics scores derived from LASSO were significantly different between the severe AS and non-severe AS groups in the validation set (median, 1.563 vs. 0.197, respectively, p < 0.001). A radiomics prediction model based on feature selection by LASSO + model classifier by XGBoost showed the highest c-index of 0.921 (95% confidence interval [CI], 0.869-0.973) in the validation set. Compared to prediction models based on AVC volume and score (c-indexes of 0.894 [95% CI, 0.815-0.948] and 0.899 [95% CI, 0.820-0.951], respectively), eight and three of the nine radiomics prediction models showed higher discrimination abilities for severe AS. However, the differences were not statistically significant (p > 0.05 for all).

CONCLUSION

Models based on the radiomics features of AVC and ML algorithms may perform well for diagnosing severe AS, but the added value compared to AVC volume and score should be investigated further.

Stiffness of the Central Corpus Cavernosum on Shear-Wave Elastography Is Inversely Correlated with the Penile Rigidity Score in Patients with Erectile Dysfunction

Purpose

To perform real-time quantitative measurements of penile rigidity for patients with erectile dysfunction (ED) using shear-wave elastography (SWE).

Materials and Methods

A total of 92 patients with clinically diagnosed ED filled out an abridged five-item version of the International Index of Erectile Function (IIEF-5) questionnaire and underwent SWE as well as penile color Doppler ultrasound (CDUS) after intracavernosal injection for penile erection. Elasticity measurements were repeated on two sites of the corpus cavernosum (central and peripheral elasticity of corpus cavernosum [ECC]) and the glans penis during the erection phase. Correlations between penile elasticity and rigidity scores or IIEF-5 were evaluated statistically. Penile elasticity was also compared with the ED types based on CDUS.

Results

The mean age of all patients was 53.5±13.4 years, and the mean IIEF-5 score was 9.78±5.01. The rigidity score and central ECC value demonstrated a significant correlation (r=−0.272; 95% confidence interval: −0.464 to −0.056; p=0.015). The IIEF-5 score was not significantly correlated with penile elasticity. Vascular ED patients showed significantly higher central ECC values than nonvascular ED patients (p<0.001). At a cut-off value of 8.05 kPa, the central ECC had a specificity of 41.5%, a sensitivity of 84.6%, and an area under the ROC curve of 0.720 with a standard error of 0.059 (p=0.019) for predicting vascular ED.

Conclusions

Quantitatively measuring Young's modulus of the corpus cavernosum using SWE could be an objective technique for assessing penile erectile rigidity and the vascular subtype in patients with ED.

Effectiveness of auricular acupuncture combined with nicotine replacement therapy for smoking cessation

INTRODUCTION

The aim of this study was to establish if the auricular acupuncture treatment can play a complementary role in enhancing the smoking cessation rate of the smokers receiving conventional therapy, such as NRT and behavioral counseling.

METHODS

This was a retrospective cohort study. Republic of Korea Air Force soldiers who visited the clinic with the intention to quit smoking from September 2016 to March 2017 were reviewed. The smoking cessation program consisted of a 6-weeks treatment period with follow-up at 3 and 6 months from the baseline. Smokers who chose to receive nicotine replacement therapy (NRT) were compared with those who chose to receive auricular acupuncture combined with NRT. Both groups received behavioral counseling.

RESULTS

A total of 148 subjects were reviewed in the study. Of the 86 smokers who received combination therapy, 41 achieved continuous abstinence (47.7%), while 19 out of the 62 smokers stayed abstinent from the NRT group (30.6%). There was a significant difference between the two groups (p=0.037). Minnesota Nicotine Withdrawal Scale scores significantly decreased after the treatment in both groups, but there was no significant difference between the two groups (p=0.681). No serious adverse events were reported from both groups.

CONCLUSIONS

The results of this study indicate that conventional treatments, such as NRT and behavioral counseling, when combined with auricular acupuncture could be a safer and more effective smoking cessation treatment than conventional treatments alone.

Gianotti-Crosti syndrome following Japanese encephalitis vaccination

We report a three-year-old Korean boy who presented with itching symmetrical erythematous macules and papules on his face, trunk, and extremities for 1 week. Lymphadenopathies were detected on physical examination. He was vaccinated against Japanese B Encephalitis (JE) 1 day before developing skin rashes. The patient s serum JE antibody titer by hemagglutinin inhibition (HI) test was 1:40. Under the diagnosis of Gianotti-Crosti syndrome following JE vaccination, he was conservatively treated with an antihistamine agent, and his symptoms were all cleared 2 weeks after treatment.

Phospholipase C isozymes selectively couple to specific neurotransmitter receptors

A variety of extracellular signals are transduced across the cell membrane by the enzyme phosphoinositide-specific phospholipase C-beta (PLC-beta) coupled with guanine-nucleotide-binding G proteins. There are four isoenzymes of PLC-beta, beta1-beta4, but their functions in vivo are not known. Here we investigate the role of PLC-beta1 and PLC-beta4 in the brain by generating null mutations in mice: we found that PLCbeta1-/- mice developed epilepsy and PLCbeta4-/- mice showed ataxia. We determined the molecular basis of these phenotypes and show that PLC-beta1 is involved in signal transduction in the cerebral cortex and hippocampus by coupling predominantly to the muscarinic acetylcholine receptor, whereas PLC-beta4 works through the metabotropic glutamate receptor in the cerebellum, illustrating how PLC-beta isoenzymes are used to generate different functions in the brain.

Dicistronic tagging of genes active in embryonic stem cells of mice

A gene-trap vector, pWH14, has been developed to tag genes expressed in embryonic stem (ES) cells of the mouse. The approach relies on the ability of the endogenous promoter to drive promoterless neo-IRES-lacZ construct producing a dicistronic mRNA consisting of the neomycin-resistance (neo) gene and the beta-galactosidase gene sequence. The neo gene produces a chimeric protein with the truncated product of the tagged gene and serves as a selectable marker for an insertion into an expressed gene. The internal ribosome entry site (IRES) sequence from murine encephalomyocarditis virus allows the translation of the second cistron, lacZ, to produce beta-galactosidase that can be used as a reporter for the expression of the tagged gene. The pWH14 vector was introduced into ES cells by electroporation, and the cells were selected for G418-resistance. About 50% of the G418-resistant colonies were stained positive for the beta-galactosidase activity. Southern analysis showed that each clone had one or more vector sequences integrated. Northern blot analysis of the clones positive for beta-galactosidase indicated that the fused RNAs containing the neo and the beta-gal genes were derived from the endogenous promoters of the tagged genes. Seven clones were chosen and injected into blastocysts, and chimeras were obtained. Two of the gene-trap insertions (wh14.1 and wh14.3) were transmitted through germ-line. In these two lines, the pattern of lacZ expression was restricted to early stages of embryos. This gene-trap vector may provide a means for tagging and studying the active genes in vivo in early embryogenesis.