Combination of Machine Learning Techniques to Predict Overweight/Obesity in Adults.

(1) Background: Artificial intelligence using machine learning techniques may help us to predict and prevent obesity. The aim was to design an interpretable prediction algorithm for overweight/obesity risk based on a combination of different machine learning techniques. (2) Methods: 38 variables related to sociodemographic, lifestyle, and health aspects from 1179 residents in Madrid were collected and used to train predictive models. Accuracy, precision, and recall metrics were tested and compared between nine classical machine learning techniques and the predictive model based on a combination of those classical machine learning techniques. Statistical validation was performed. The shapely additive explanation technique was used to identify the variables with the greatest impact on weight gain. (3) Results: Cascade classifier model combining gradient boosting, random forest, and logistic regression models showed the best predictive results for overweight/obesity compared to all machine learning techniques tested, reaching an accuracy of 79%, precision of 84%, and recall of 89% for predictions for weight gain. Age, sex, academic level, profession, smoking habits, wine consumption, and Mediterranean diet adherence had the highest impact on predicting obesity. (4) Conclusions: A combination of machine learning techniques showed a significant improvement in accuracy to predict risk of overweight/obesity than machine learning techniques separately.

Phosphodiesterase-5 Expression in Buccal Mucosa of Patients with Erectile Dysfunction One Year after Radical Prostatectomy.

(1) Background: Radical prostatectomy has a high incidence of erectile dysfunction (ED). The aim was to determine if the expression of the nitric oxide synthase-3/soluble guanylate cyclase/phosphodiesterase 5 axis could be detected in buccal mucosa and if it could be differently expressed in patients with and without ED; (2) Methods: Erectile function from 38 subjects subjected to prostatectomy was evaluated using the International Index of Erectile Function-Erectile Function Domain before and one year after surgery. Nitric oxide synthase (NOS3), ß1-subunit of soluble guanylate cyclase (sGC), phosphodiesterase-5 (PDE-5) expressions, and interleukin-6 and interleukin-10 content were measured in the buccal mucosa. PDE5A rs3806808 gene polymorphism was genotyped; (3) Results: One year after prostatectomy, 15 patients had recovered functional erection, and 23 showed ED. NOS3, ß1-sGC, interleukin-6, and interleukin-10 expressions were not different between patients with and without ED after radical prostatectomy. Buccal mucosa levels of PDE-5 were higher in patients with ED compared to those who recovered erectile functionality. There were no differences found in the genotype of PDE5A polymorphism; (4) Conclusions: One year after prostatectomy, patients with ED had higher PDE5 levels in their buccal mucosa than patients who had recovered erectile function. Rs3806808 PDE5A gene polymorphism was not associated with increased PDE5 expression in buccal mucosa.

Spike Protein Subunits of SARS-CoV-2 Alter Mitochondrial Metabolism in Human Pulmonary Microvascular Endothelial Cells: Involvement of Factor Xa.

Background: Mitochondria have been involved in host defense upon viral infections. Factor Xa (FXa), a coagulating factor, may also have influence on mitochondrial functionalities. The aim was to analyze if in human pulmonary microvascular endothelial cells (HPMEC), the SARS-CoV-2 (COVID-19) spike protein subunits, S1 and S2 (S1+S2), could alter mitochondrial metabolism and what is the role of FXA. Methods: HPMEC were incubated with and without recombinants S1+S2 (10 nmol/L each). Results: In control conditions, S1+S2 failed to modify FXa expression. However, in LPS (1 µg/mL)-incubated HPMEC, S1+S2 significantly increased FXa production. LPS tended to reduce mitochondrial membrane potential with respect to control, but in higher and significant degree, it was reduced when S1+S2 were present. LPS did not significantly modify cytochrome c oxidase activity as compared with control. Addition of S1+S2 spike subunits to LPS-incubated HPMEC significantly increased cytochrome c oxidase activity with respect to control. Lactate dehydrogenase activity was also increased by S1+S2 with respect to control and LPS alone. Protein expression level of uncoupled protein-2 (UCP-2) was markedly expressed when S1+S2 were added together to LPS. Rivaroxaban (50 nmol/L), a specific FXa inhibitor, significantly reduced all the above-mentioned alterations induced by S1+S2 including UCP-2 expression. Conclusions: In HPMEC undergoing to preinflammatory condition, COVID-19 S1+S2 spike subunits promoted alterations in mitochondria metabolism suggesting a shift from aerobic towards anaerobic metabolism that was accompanied of high FXa production. Rivaroxaban prevented all the mitochondrial metabolic changes mediated by the present COVID-19 S1 and S2 spike subunits suggesting the involvement of endogenous FXa.

Are Panoramic Images a Good Tool to Detect Calcified Carotid Atheroma? A Systematic Review.

To investigate the reliability of panoramic dental images to detect calcified carotid atheroma, electronic databases (PubMed, IEEE/Xplore and Embase) were searched. Outcomes included cerebrovascular disease events, cardiovascular disease events, patient previous diseases, and combined endpoints. Risk of bias was evaluated using the Newcastle-Ottawa Scale. Hence, 15 studies were selected from 507 potential manuscripts. Five studies had a low risk of bias, while the remaining nine studies were found to have a moderate risk. Heterogeneous results were obtained but showed that patients with risk factors, such as obesity, diabetes mellitus, hypertension, and smoking, and with calcified carotid atheroma on panoramic images, have a higher prevalence than healthy patients. The evidence in the literature was found to be equivocal. However, the findings of this systematic review exhibit that panoramic radiographs can be used for dental diagnosis and treatment planning, as well as to detect calcified carotid artery atheroma.

Mitochondrial mitophagy protection combining rivaroxaban and aspirin in high glucose-exposed human coronary artery endothelial cell. An in vitro study.

PURPOSE: Combination of Rivaroxaban plus Aspirin improved cardiovascular outcome in patients with stable cardiovascular disease. The aim was to determine if Rivaroxaban and acetylsalicylic acid alone or in combination may protect mitochondrial mitophagy in human coronary artery endothelial cells (HCAEC) exposed to D-glucose. METHODS: HCAEC were incubated under different conditions: 5 mmol/L glucose D-glucose (control), 30 mmol/L D-Glucose with and without 50 nmol/L Rivaroxaban (Rivaroxaban), 0.33 mmol/L ASA (ASA) or Rivaroxaban (12.5 nmol/L)+ASA (0.33 mmol/L; (Riva+ASA). RESULTS: HCAEC incubated with D-glucose showed an increased Factor Xa expression. The mitochondrial content of Pink-1 and Parkin were significantly reduced in high glucose-incubated HCAEC compared to control. Rivaroxaban+ASA significantly increased the mitochondrial content of Pink-1 and Parkin, and the mitochondrial membrane potential compared to D-Glucose group. Both ASA alone and Riva+ASA reduced reactive oxygen species (ROS) and tissue factor production induced by high glucose exposure. CONCLUSION: Under high glucose condition combining Rivaroxaban+ASA increased the mitochondrial content of Pink-1 and Parkin, restored mitochondria membrane potential and reduced ROS and tissue factor expression in HCAEC. It suggests potential effects induced by dual use of Rivaroxaban and ASA on the coronary endothelium subjected to high glucose condition.

A Convolutional Neural Network for Automatic Tooth Numbering in Panoramic Images.

Analysis of dental radiographs and images is an important and common part of the diagnostic process in daily clinical practice. During the diagnostic process, the dentist must interpret, among others, tooth numbering. This study is aimed at proposing a convolutional neural network (CNN) that performs this task automatically for panoramic radiographs. A total of 8,000 panoramic images were categorized by two experts with more than three years of experience in general dentistry. The neural network consists of two main layers: object detection and classification, which is the support of the previous one and a transfer learning to improve computing time and precision. A Matterport Mask RCNN was employed in the object detection. A ResNet101 was employed in the classification layer. The neural model achieved a total loss of 6.17% (accuracy of 93.83%). The architecture of the model achieved an accuracy of 99.24% in tooth detection and 93.83% in numbering teeth with different oral health conditions.

A Validation Employing Convolutional Neural Network for the Radiographic Detection of Absence or Presence of Teeth.

Dental radiography plays an important role in clinical diagnosis, treatment and making decisions. In recent years, efforts have been made on developing techniques to detect objects in images. The aim of this study was to detect the absence or presence of teeth using an effective convolutional neural network, which reduces calculation times and has success rates greater than 95%. A total of 8000 dental panoramic images were collected. Each image and each tooth was categorized, independently and manually, by two experts with more than three years of experience in general dentistry. The neural network used consists of two main layers: object detection and classification, which is the support of the previous one. A Matterport Mask RCNN was employed in the object detection. A ResNet (Atrous Convolution) was employed in the classification layer. The neural model achieved a total loss of 0.76% (accuracy of 99.24%). The architecture used in the present study returned an almost perfect accuracy in detecting teeth on images from different devices and different pathologies and ages.

Dental Caries Diagnosis and Detection Using Neural Networks: A Systematic Review.

Dental caries is the most prevalent dental disease worldwide, and neural networks and artificial intelligence are increasingly being used in the field of dentistry. This systematic review aims to identify the state of the art of neural networks in caries detection and diagnosis. A search was conducted in PubMed, Institute of Electrical and Electronics Engineers (IEEE) Xplore, and ScienceDirect. Data extraction was performed independently by two reviewers. The quality of the selected studies was assessed using the Cochrane Handbook tool. Thirteen studies were included. Most of the included studies employed periapical, near-infrared light transillumination, and bitewing radiography. The image databases ranged from 87 to 3000 images, with a mean of 669 images. Seven of the included studies labeled the dental caries in each image by experienced dentists. Not all of the studies detailed how caries was defined, and not all detailed the type of carious lesion detected. Each study included in this review used a different neural network and different outcome metrics. All this variability complicates the conclusions that can be made about the reliability or not of a neural network to detect and diagnose caries. A comparison between neural network and dentist results is also necessary.