Deep learning-based prediction of coronary artery calcium scoring in hemodialysis patients using radial artery calcification.

OBJECTIVE: This study used random forest model to explore the feasibility of radial artery calcification in prediction of coronary artery calcification in hemodialysis patients. MATERIAL AND METHODS: We enrolled hemodialysis patients and performed ultrasound examinations on their radial arteries to evaluate the calcification status using a calcification index. All involved patients received coronary artery computed tomography scans to generate coronary artery calcification scores (CACS). Clinical variables were collected from all patients. We constructed both a random forest model and a logistic regression model to predict CACS. Logistic regression model was used to identify the risk factors of radial artery calcification. RESULTS: One hundred eighteen patients were included in our analysis. In random forest model, the radial artery calcification index, age, serum C-reactive protein, body mass index (BMI), diabetes, and hypertension history were related to CACS based on the average decrease of the Gini coefficient. The random forest model achieved a sensitivity of 76.9%, specificity of 75.0%, and area under receiver operating characteristic of 0.869, while the logistic regression model achieved a sensitivity of 75.2%, specificity of 68.7%, and area under receiver operating characteristic of 0.742 in prediction of CACS. Sex, BMI index, smoking history, hypertension history, diabetes history, and serum total calcium were all the risk factors related to radial artery calcification. CONCLUSIONS: A random forest model based on radial artery calcification could be used to predict CACS in hemodialysis patients, providing a potential method for rapid screening and prediction of coronary artery calcification.

Inhibition of periderm removal in all-trans retinoic acid-induced cleft palate in mice.

Cleft palate is a common craniofacial birth defect. The aim of the present study was to investigate the effect of excess all-trans retinoic acid (atRA) on periderm removal and the disappearance of basal medial edge epithelial (MEE) cells during palatogenesis, particularly during the stage prior to contact. atRA (200 mg/kg) was administered to C57BL/6N mice at embryonic day (E) 12.0 by gavage. Fetal palates were processed and analyzed by histology and electron microscopy. Single palate shelf peridermal cells were removed and cultured in the presence of atRA (3 µM) only or in the presence of or the caspase inhibitor, Z-VAD (100 µM) only, for 48 h. Once cultured, morphological changes were analyzed by histological staining and electron microscopy. A TUNEL assay was used to detect apoptotic neurons. Paired palatal shelves with periderm removal were cultured in the presence of atRA (3 µM) only or in the presence of Z-VAD (100 µM) only for 48 h and analyzed by hematoxylin and eosin staining. At E14.5, medial edge epithelium periderm was retained in the atRA-treated palates but had been shed prior to contact in the control groups. In addition, atRA was revealed to disrupt the cell cycle in the periderm by downregulating p21. Furthermore, atRA inhibited apoptosis in the periderm and basal MEE cells; however, atRA exhibited no effect on basement membrane degradation in single palatal organ culture. Additionally, once paired palates were cultured for 48 h, all of the groups in which the periderm had been removed exhibited confluence of the embryonic palatal mesenchyme. The present results suggest that periderm removal is inhibited in atRA-induced cleft palate in mice and that removal of the periderm contributes to EPM confluence in vitro.

Involvement of RBP4 in all­trans retinoic acid induced cleft palate.

The current study was designed to elucidate the mechanism of retinol binding protein 4 (RBP4) in cleft palate induced by all­trans retinoic acid (atRA). To establish a cleft palate model in C57BL/6J mice, pregnant mice were administered atRA (100 mg/kg) by gavage at the tenth embryonic stage (E10.0). Control groups were given the equivalent volume of corn oil. Pregnant mice were dissected at E12.5, E13.5 and E14.5 to obtain the embryonic palates. The expression levels of RBP4 in the embryonic palatal mesenchyme (EPM) were determined by immunohistochemistry, reverse transcription­quantitative polymerase chain reaction (RT­qPCR) and western blotting. Human embryonic palatal mesenchymal cells were exposed to atRA to detect the variation in RBP4 induced by atRA in vitro. Small interfering RNA was used to suppress the expression of RBP4, and a plasmid overexpressing RBP4 was used to examine upregulated expression. The cell counting kit­8 assay was used to evaluate the effect of RBP4 on cell proliferation. The expression levels of p27 and cyclin D1 were determined by RT­qPCR and western blotting, while the expression levels of extracellular signal­related kinase (ERK) 1/2 and protein kinase B (AKT) were assessed by western blotting. At E14.5, RBP4 was strongly expressed in the EPM, while it was downregulated following atRA treatment, which induced cleft palate in vivo. In vitro experiments indicated that atRA suppressed the expression of RBP4 and altered the expression of p27 and cyclin D1 to cause growth inhibition. Knockdown of RBP4 resulted in decreased expression of cyclin D1 and increased p27, and suppressed proliferation. Overexpression of RBP4 reversed the inhibitory effect of atRA and promoted proliferation via the ERK1/2 and AKT signaling pathways. These results suggested that RBP4 was involved in cleft palate induced by atRA and it can be suppressed by atRA to cause growth inhibition in the embryonic palate.

Involvement of Notch2 in all­trans retinoic acid­induced inhibition of mouse embryonic palate mesenchymal cell proliferation.

Cleft palate is among the most common congenital disorders, and can be induced by exposure to all­trans retinoic acid (atRA) during mice and human embryogenesis. However, the mechanism underlying the implication of atRA in the development of cleft palate has yet to be elucidated. In the present study, atRA administered by gavage resulted in formation of a cleft palate in 99% of treated C57BL/6 mice. Notch2 was revealed to be upregulated in mouse embryonic palate mesenchymal (MEPM) cells in the atRA­treated group compared with untreated control mice between embryonic day (E)12.5 and E14.5. In addition, atRA was demonstrated to mediate Notch2 expression via the activation of RA receptors (RARs). Since Notch2 activation has previously been reported to inhibit the proliferation of MEPM cells, the expression levels of extracellular signal­regulated kinase (ERK), p21, cyclin D1 and Ki­67 were assessed in samples from atRA­treated and control mouse embryos between E12.5 and E14.5. It was demonstrated that Notch2 silencing partially reversed the atRA­induced inhibition of ERK phosphorylation in MEPM cells. In addition, the atRA­induced cyclin D1 downregulation and p21 upregulation were partially reversed following Notch2 silencing, whereas the atRA­induced inhibition of cellular proliferation was also attenuated. Furthermore, it was revealed that Notch2 expression was upregulated, whereas Ki­67 expression was downregulated following atRA exposure, as assessed using resin bead­released atRA in MEPM cells. The present findings suggested that during embryonic development, atRA may enhance the expression of Notch2, which may inhibit cellular proliferation, possibly through ERK signaling.

Activation of Notch1 inhibits medial edge epithelium apoptosis in all-trans retinoic acid-induced cleft palate in mice.

Administration of all-trans retinoic acid (atRA) on E12.0 (embryonic day 12.0) leads to failure of medial edge epithelium (MEE) disappearance and cleft palate. However, the molecular mechanism underlying the relationship between atRA and MEE remains to be identified. In this study, atRA (200 mg/kg) administered by gavage induced a 75% incidence of cleft palate in C57BL/6 mice. Notch1 was up-regulated in MEE cells in the atRA-treated group compared with the controls at E15.0, together with reduced apoptosis and elevated proliferation. Next, we investigated the mechanisms underlying atRA, Notch1 and MEE degradation in palate organ culture. Our results revealed that down-regulation of Notch1 partially rescued the inhibition of atRA-induced palate fusion. Molecular analysis indicated that atRA increased the expression of Notch1 and Rbpj and decreased the expression of P21. In addition, depletion of Notch1 expression decreased the expression of Rbpj and increased the expression of P21. Moreover, inhibition of Rbpj expression partially reversed atRA-induced MEE persistence and increased P21 expression. These findings demonstrate that atRA inhibits MEE degradation, which in turn induces a cleft palate, possibly through the Notch1/RBPjk/P21 signaling pathway.