Agastache Species (Lamiaceae) as a Valuable Source of Volatile Compounds: GC-MS Profiling and Investigation of In Vitro Antibacterial and Cytotoxic Activities.

Nowadays, there is an increasing interest in the study of medicinal and aromatic plants, due to their therapeutic properties that correlate with the presence of different active compounds. Agastache species (sp.) are aromatic plants that belong to the Lamiaceae family, originating from North America and East Asia. The present study aimed to evaluate the composition of essential oils (EOs) obtained from different Romanian cultivated Agastache sp. and to investigate their antibacterial and cytotoxic activities. The gas chromatography-mass spectrometry (GC-MS) screening revealed that menthone was the dominant constituent of A. foeniculum (31.58%), A. rugosa (39.60%) and A. rugosa 'After Eight' (39.76%) EOs, while estragole was the major constituent of A. foeniculum "Aromat de Buzau" (63.27%) and A. mexicana (41.66%) EOs. The investigation of the antiproliferative effect showed that A. rugosa and A. foeniculum "Aromat de Buzau" EOs had significant cytotoxic activity on MDA-MB-231 and HEPG2 tumour cell lines, with the most promising effect on the MDA-MB-231 breast cancer cell line for A. foeniculum "Aromat de Buzau" EO (IC50 = 203.70 ± 0.24 µg/mL). Regarding the antibacterial activity, A. rugosa EO was most active against E. coli (8.91 ± 3.27 µL/mL) and S. aureus (10.80 ± 0.00 µL/mL). To the best of our knowledge, this is the first report on the cytotoxic effect of Agastache sp. EOs on MDA-MB-231, HCT116 and HEPG2 tumour cell lines. The results of our study provide new and promising information for the subsequent in vivo study of the pharmacological properties of Agastache sp. essential oils.

The Study of Clinical and Biochemical Parameters in Assessing the Response to the Antiviral Therapy in the Chronic Viral Hepatitis B.

Background and Objectives: Hepatitis B virus infection remains a major public health concern. The interaction between hepatitis B virus (HBV) hepatitis B virus and the host inflammatory response is an important contributing factor driving liver damage and diseases outcomes. The management of chronic hepatitis B virus infection is an area of massive unmet clinical need worldwide. Our primary aim for this study was to evaluate biological response rates and sustained virological response in patients with chronic hepatitis B treated with Peg-IFN α-2a/b. The second aim of the study was the identification of metabolic changes and insulin resistance. Materials and Methods: We enrolled in this study 166 patients who fulfilled all inclusion and exclusion criteria. These treatment-naive patients with chronic HBV were treated with Pegylated Interferon α-2a/b. HBV infection was defined by the presence of HBV serological markers (HBsAg, anti-HBsAb, anti-HBcAb, HBeAg, anti HBeAb) by Enzyme-Linked Immuno Sorbent Assay (ELISA) and serum HBV-DNA levels were estimated by a commercially available quantitative polymerase chain reaction (PCR) assay. Results: Patients' recovery progress has been evaluated by determining the following: age, gender; biochemical tests; alanine aminotransferase, aspartate aminotransferase; serological assays for HBV serological markers (HBsAg, anti-HBsAc/Ab, anti-HBcAc/Ab, HBeAg, anti HBeAc/Ab); molecular tests to detect viral particles, testing for HBV DNA (PCR) to confirm the diagnosis and quantify the number of viral copies in the blood (viremia); liver ultrasound-performed through epigastric and intercostal approach (transversal and longitudinal sections). Conclusions: Our results indicated that only HOMA index values, that of fasting insulin, together with baseline HBV DNA, alanine aminotransferase values, mean blood glucose at the beginning of treatment may be predictive of the early viral response in chronic hepatitis B.

Intelligent Diagnosis of Thyroid Ultrasound Imaging Using an Ensemble of Deep Learning Methods.

Background and Objectives: At present, thyroid disorders have a great incidence in the worldwide population, so the development of alternative methods for improving the diagnosis process is necessary. Materials and Methods: For this purpose, we developed an ensemble method that fused two deep learning models, one based on convolutional neural network and the other based on transfer learning. For the first model, called 5-CNN, we developed an efficient end-to-end trained model with five convolutional layers, while for the second model, the pre-trained VGG-19 architecture was repurposed, optimized and trained. We trained and validated our models using a dataset of ultrasound images consisting of four types of thyroidal images: autoimmune, nodular, micro-nodular, and normal. Results: Excellent results were obtained by the ensemble CNN-VGG method, which outperformed the 5-CNN and VGG-19 models: 97.35% for the overall test accuracy with an overall specificity of 98.43%, sensitivity of 95.75%, positive and negative predictive value of 95.41%, and 98.05%. The micro average areas under each receiver operating characteristic curves was 0.96. The results were also validated by two physicians: an endocrinologist and a pediatrician. Conclusions: We proposed a new deep learning study for classifying ultrasound thyroidal images to assist physicians in the diagnosis process.

Solidago graminifolia L. Salisb. (Asteraceae) as a Valuable Source of Bioactive Polyphenols: HPLC Profile, In Vitro Antioxidant and Antimicrobial Potential.

Solidago species are often used in traditional medicine as anti-inflammatory, diuretic, wound-healing and antimicrobial agents. Still, the bioactive compounds and biological activities of some species have not been studied. The present work aimed to investigate the polyphenolic profile and the biological properties of Solidago graminifolia L. Salisb., a poorly explored medicinal plant. The hydroalcoholic extracts from aerial parts were evaluated for total phenolic content (TPC), total flavonoid content (TFC) and the polyphenolic compounds were investigated by HPLC-MS. The antioxidant potential in vitro was determined using DPPH and FRAP assays. Antibacterial and antifungal effects were evaluated by dilution assays and MIC, MBC and MFC were calculated. The results showed that Solidago graminifolia aerial parts contain an important amount of total phenolics (192.69 mg GAE/g) and flavonoids (151.41 mg RE/g), with chlorogenic acid and quercitrin as major constituents. The hydroalcoholic extracts showed promising antioxidant and antimicrobial potential, with potent antibacterial activity against Staphylococcus aureus and important antifungal effect against Candida albicans and C. parapsilosis. The obtained results indicated that the aerial parts of Solidago graminifolia could be used as novel resource of phytochemicals in herbal preparations with antioxidant and antimicrobial activities.

Comparative Phytochemical Profile, Antioxidant, Antimicrobial and In Vivo Anti-Inflammatory Activity of Different Extracts of Traditionally Used Romanian Ajuga genevensis L. and A. reptans L. (Lamiaceae).

Several Ajuga species are used in Romanian folk medicine for their antioxidant, antimicrobial and anti-inflammatory properties, to treat pain, fever or arthritis. Still, the active compounds responsible for these effects and their mechanism of action are scarcely known. This research was designed to investigate the phytochemical profile (e.g. iridoids, polyphenolic compounds, phytosterols), as well as the biological potential (antioxidant, antibacterial, antifungal, anti-inflammatory properties) of two selected Ajuga species collected from different regions of Romanian spontaneous flora. The main compounds identified in A. reptans aerial parts extracts were 8-O-acetylharpagide, isoquercitrin and ß-sitosterol, whilst in A. genevensis were 8-O-acetylharpagide, luteolin and campesterol. The extracts were screened for their antioxidant potential using different methods (DPPH, TEAC, EPR) and the results showed a good activity, in accordance with the polyphenol content (18-26 mg GAE/g dw). The antifungal activity on the tested strains was good. The determination of few parameters linked with the inflammatory mechanism allowed the assessment of in vivo anti-inflammatory potential. Ajuga reptans and A. genevensis ethanol extracts had anti-inflammatory activity through lowering the oxidative stress, phagocytosis, PMN and total leukocytes. The best anti-oxidative and anti-inflammatory activity was observed for the Ajuga reptans 100 mg dw/mL extract when compared with diclofenac, thus the dose could be correlated with the pharmacological effect. These findings provide substantial evidence that both selected Ajuga species have the potential to be valued as sources of phytochemicals in effective anti-inflammatory herbal preparations.

Development of a NIR Method for the In-Line Quantification of the Total Polyphenolic Content: A Study Applied on Ajuga genevensis L. Dry Extract Obtained in a Fluid Bed Process.

This study describes an innovative in-line near-infrared (NIR) process monitoring method for the quantification of the total polyphenolic content (TPC) of Ajuga genevensis dry extracts. The dry extract was obtained in a fluidized bed processor, by spraying and adsorbing a liquid extract onto an inert powder support. NIR spectra were recorded continuously during the extract's spraying process. For the calibration of the in-line TPC quantification method, samples were collected during the entire process. The TPC of each sample was assessed spectroscopically, by applying a UV-Vis reference method. The obtained values were further used in order to develop a quality OPLS prediction model by correlating them with the corresponding NIR spectra. The final dry extract registered good flowability and compressibility properties, a concentration in active principles three times higher than the one of the liquid extract and an overall process yield of 85%. The average TPC's recovery of the NIR in-line prediction method, compared with the reference UV-Vis one, was 98.7%, indicating a reliable monitoring method which provided accurate predictions of the TPC during the process, permitting a good process overview and enabling us to establish the process's end point at the exact moment when the product reaches the desired TPC concentration.

Comparative studies on polyphenolic composition, antioxidant and antimicrobial activities of Schisandra chinensis leaves and fruits.

The aim of this paper was to evaluate the antioxidant and antimicrobial activities and the polyphenolic content of Schisandra chinensis (Turcz.) Baill. leaves and fruits. The leaves are an important source of flavonoids (35.10 ± 1.23 mg RE/g plant material). Qualitative and quantitative analyses of the polyphenolic compounds were achieved using a HPLC-UV-MS method. The main flavonoid from the leaves was isoquercitrin (2486.18 ± 5.72 µg/g plant material), followed by quercitrin (1645.14 ± 2.12 µg/g plant material). Regarding the fruit composition, the dominant compound there was rutin (13.02 ± 0.21 µg/g plant material), but comparing with the leaves, fruits can be considered a poor source of phenolic compounds. The antioxidant activity was evaluated by DPPH, TEAC, hemoglobin ascorbate peroxidase activity inhibition (HAPX), inhibition of lipid peroxidation catalyzed by cytochrome c and EPR spectroscopic assays, revealing a better antioxidant activity for the S. chinensis leaves extract. In the antimicrobial assay, S. chinensis leaves extract showed efficient activities against the targeted bacteria, being more active than the fruits extract. The results suggest the leaves of S. chinensis as a valuable source of antioxidant compounds with significant antioxidant activity.

Investigation of Epilobium hirsutum L. Optimized Extract's Anti-Inflammatory and Antitumor Potential.

Epilobium hirsutum L., commonly known as hairy willowherb, is a perennial herbaceous plant native to Europe and Asia. In Romania, the Epilobium genus includes 17 species that are used in folk medicine for various purposes. This study aimed to investigate the anti-inflammatory and antitumor potential of the optimized extract of Epilobium hirsutum (EH) in animal models. The first study investigated the anti-inflammatory properties of EH optimized extract and the model used was carrageenan-induced paw inflammation. Wistar rats were divided into three groups: negative control, positive control treated with indomethacin, and a group treated with the extract. Oxidative stress markers, cytokine levels, and protein expressions were assessed. The extract demonstrated anti-inflammatory properties comparable to those of the control group. In the second study, the antitumor effects of the extract were assessed using the tumor model of Ehrlich ascites carcinoma. Swiss albino mice with Ehrlich ascites were divided into four groups: negative, positive treated with cyclophosphamide (Cph), Group 3 treated with Cph and EH optimized extract, and Group 4 treated with extract alone. Samples from the ascites fluid, liver, and heart were analyzed to evaluate oxidative stress, inflammation, and cancer markers. The extract showed a reduction in tumor-associated inflammation and oxidative stress. Overall, the EH optimized extract exhibited promising anti-inflammatory and antitumor effects in the animal models studied. These findings suggest its potential as a natural adjuvant therapeutic agent for addressing inflammation and oxidative stress induced by different pathologies.

Agastache Species: A Comprehensive Review on Phytochemical Composition and Therapeutic Properties.

The Agastache genus is part of the Lamiaceae family and is native to North America, while one species, Agastache rugosa (A. rugosa), is native to East Asia. A review on the phytochemistry and bioactivity of Agastache genus was last performed in 2014. Since then, a lot of progress has been made on the characterization of the phytochemical and pharmacological profiles of Agastache species. Thus, the purpose of this paper is to present a summary of the findings on the phytochemistry and biological effects of several Agastache species, including both extracts and essential oil characterization. We performed a comprehensive search using PubMed and Scopus databases, following PRISMA criteria regarding the study selection process. The available data is focused mainly on the description of the chemical composition and bioactivity of A. rugosa, with fewer reports referring to Agastache mexicana (A. mexicana) and Agastache foeniculum (A. foeniculum). Agastache species are characterized by the dominance of flavonoids and phenolic acids, as well as volatile compounds, particularly phenylpropanoids and monoterpenes. Moreover, a series of pharmacological effects, including antioxidant, cytotoxic, antimicrobial, anti-atherosclerotic, and cardioprotective properties, have been reported for species from the Agastache genus.

New Approaches on the Anti-Inflammatory and Cardioprotective Properties of Taraxacum officinale Tincture.

The present research investigated the in vivo anti-inflammatory and cardioprotective activities, as well as the antioxidant potential of Taraxacum officinale tincture (TOT), in relation to the polyphenolic composition. Chromatographic and spectrophotometric techniques were used to determine the polyphenolic profile of TOT and the antioxidant activity was preliminarily assessed in vitro by DPPH• and FRAP spectrophotometric methods. The in vivo anti-inflammatory and cardioprotective activities were studied in rat turpentine-induced inflammation and in rat isoprenaline-induced myocardial infarction (MI) models. The main polyphenolic compound identified in TOT was cichoric acid. The oxidative stress determinations showed the capacity of the dandelion tincture not only to decrease the total oxidative stress (TOS), the oxidative stress index (OSI), and the total antioxidant capacity (TAC), but also the malondialdehide (MDA), thiols (SH), and nitrites/nitrates (NOx) levels both in inflammation and MI models. In addition, aspartate aminotransferase (AST), alanine aminotransferase (ALT), creatin kinase-MB (CK-MB), and nuclear factor kappa B (NF-κB) parameters were decreased by the administration of the tincture. The results show that T. officinale could be considered a valuable source of natural compounds with important benefits in pathologies linked to oxidative stress.

Chemical constituents of three Allium species from Romania.

The aim of this work was to study the chemical composition of Allium obliquum L., A. senescens L. subsp. montanum (Fries) Holub, and A. schoenoprasum L. subsp. schoenoprasum. Sulphur-containing compounds analysis was performed by an LC-MS method, the identification and quantification of polyphenolic compounds through a HPLC-UV-MS method, and the presence of five sterols was simultaneously assessed by HPLC-MS-MS. Alliin was identified only in A. obliquum and A. senescens subsp. montanum extracts, whilst allicin was present in all extracts, with higher amounts in A. schoenoprasum and A. obliquum. The pattern of phenol carboxylic acids shows the presence of p-coumaric and ferulic acids in all species. Isoquercitrin was identified in A. obliquum and A. schoenoprasum, and rutin in A. senescens subsp. montanum and A. schoenoprasum. Luteolin and apigenin were identified only in A. obliquum. All three species contain glycosides of kaempferol and quercetol. ß-Sitosterol and campesterol were identified in all species. The results obtained showed significant differences in the composition of the three Allium species.

Feasibility of a lung airway navigation system using fiber-Bragg shape sensing and artificial intelligence for early diagnosis of lung cancer.

Currently early diagnosis of malignant lesions at the periphery of lung parenchyma requires guidance of the biopsy needle catheter from the bronchoscope into the smaller peripheral airways via harmful X-ray radiation. Previously, we developed an image-guided system, iMTECH which uses electromagnetic tracking and although it increases the precision of biopsy collection and minimizes the use of harmful X-ray radiation during the interventional procedures, it only traces the tip of the biopsy catheter leaving the remaining catheter untraceable in real time and therefore increasing image registration error. To address this issue, we developed a shape sensing guidance system containing a fiber-Bragg grating (FBG) catheter and an artificial intelligence (AI) software, AIrShape to track and guide the entire biopsy instrument inside the lung airways, without radiation or electromagnetic navigation. We used a FBG fiber with one central and three peripheral cores positioned at 120° from each other, an array of 25 draw tower gratings with 1cm/3nm spacing, 2 mm grating length, Ormocer-T coating, and a total outer diameter of 0.2 mm. The FBG fiber was placed in the working channel of a custom made three-lumen catheter with a tip bending mechanism (FBG catheter). The AIrShape software determines the position of the FBG catheter by superimposing its position to the lung airway center lines using an AI algorithm. The feasibility of the FBG system was tested in an anatomically accurate lung airway model and validated visually and with the iMTECH platform. The results prove a viable shape-sensing hardware and software navigation solution for flexible medical instruments to reach the peripheral airways. During future studies, the feasibility of FBG catheter will be tested in pre-clinical animal models.

Epilobium Species: From Optimization of the Extraction Process to Evaluation of Biological Properties.

Epilobium species are used in Romanian folk medicine as tinctures, tea, or tablets for ameliorating the symptoms of benign prostate hyperplasia (BPH), but scientific-based evidence is scarce for this species or other endemic plants of the same genus. Therefore, the aims of this research were to evaluate the phytochemical profile of five endemic Epilobium species (E. hirsutum L., E. parviflorum Schreb., E. palustre L. E. dodonaei Vill., and E. angustifolium L.) and to assess their in vitro biological activity. For enhanced recovery of polyphenols, a D-optimal experimental plan was developed using Modde software and the optimal working conditions were ultra-turrax-assisted extraction, for 8 min, with 30% ethanol in water. The optimized extracts were obtained from various plant parts and were further characterized by LC-MS analysis, with the major compound being oenothein B. All extracts demonstrated good antioxidant activity, evaluated by DPPH and TEAC assays. The most prominent antimicrobial potency of optimized extracts was displayed against Bacillus cereus, while against Gram-(+) bacteria, a moderate efficacy was observed. Furthermore, anti-cancer, anti-inflammatory, and antioxidant potential were assessed on normal fibroblasts and prostate carcinoma cell lines. From the evaluated optimized extracts, E. angustifolium aerial parts had the highest selectivity toward killing cancerous cells, followed by E. hirsutum aerial parts extract. For the antioxidant effect, E. hirsutum leaves and E. hirstum aerial parts extracts displayed the highest potency, decreasing ROS at the level observed for the positive control. The highest anti-inflammatory potential, based on the IL-6 and IL-8 levels, was displayed by E. dodonaei aerial parts and E. angustifolium leaves extracts. In conclusion, all five endemic species of Epilobium harvested from Romanian flora possess a diverse phytochemical composition, which supports complex biological activities.

A Rare Case of Endophthalmitis with Rhizobium radiobacter, Soon after a Resolved Keratitis: Case Report.

BACKGROUND: Rhizobium (Agrobacterium) species are plant aerobic bacteria, which in some cases can produce endophthalmitis in humans after corneal trauma. CASE PRESENTATION: A 42-year-old female patient presented in the Emergency Department of the Emergency County Hospital of Craiova, Romania, reporting pain, epiphora, and blurry vision in her right eye for about five days. This initial infectious keratitis episode was successfully resolved, but after 20 days she presented again after trauma with a leaf with corneal abscess. In the conjunctival secretion, R. radiobacter was identified. Despite antibiotherapy, the patient's state did not improve, and ultimately the eye was eviscerated. METHODS: A search was performed in the ProQuest, PubMed, and ScienceDirect databases for the terms Agrobacterium, Rhizobium, radiobacter, and eye. We eliminated non-human studies, editorials and commentaries, and non-relevant content, and excluded the duplicates. RESULTS: In total, 138 studies were initially obtained, and then we selected 26 studies for retrieval. After the selection process, we ended up including 17 studies in our analysis. Most studies reported R. radiobacter endophthalmitis after ocular surgical procedures or outdoor activities that involve exposure to soil. CONCLUSION: R. radiobacter is a rare cause of endophthalmitis after eye trauma that generally responds well to usual antibiotherapy, but occasionally can evolve to severe, leading to the loss of the eye.

TEM,CTX-M,SHV Genes in ESBL-Producing Escherichia coli and Klebsiella pneumoniae Isolated from Clinical Samples in a County Clinical Emergency Hospital Romania-Predominance of CTX-M-15.

BACKGROUND: CTX-M betalactamases have shown a rapid spread in the recent years among Enterobacteriaceae and have become the most prevalent Extended Spectrum Beta-Lactamases (ESBLs) in many parts of the world. The introduction and dissemination of antibiotic-resistant genes limits options for treatment, increases mortality and morbidity in patients, and leads to longer hospitalization and expensive costs. We aimed to identify the beta-lactamases circulating encoded by the genes blaCTX-M-15, blaSHV-1 and blaTEM-1 in Escherichia coli (E. coli) and Klebsiella pneumoniae (K. pneumoniae) strains. Furthermore, we established the associated resistance phenotypes among patients hospitalized in the Intensive Care Unit (ICU) from County Clinical Emergency Hospital of Craiova, Romania. METHODS: A total of 46 non-duplicated bacterial strains (14 strains of E. coli and 32 strains of K. pneumoniae), which were resistant to ceftazidime (CAZ) and cefotaxime (CTX) by Kirby-Bauer disk diffusion method, were identified using the automated VITEK2 system. Detection of ESBL-encoding genes and other resistance genes was carried out by PCR. RESULTS: E. coli strains were resistant to 3rd generation cephalosporins and moderately resistant to quinolones, whereas K. pneumoniae strains were resistant to penicillins, cephalosporins, and sulfamides, and moderately resistant to quinolones and carbapenems. Most E. coli strains harbored blaCTX-M-15 gene (13/14 strains), a single strain had the blaSHV-1 gene, but 11 strains harbored blaTEM-1 gene. The mcr-1 gene was not detected. We detected tet(A) gene in six strains and tet(B) in one strain. In K. pneumoniae strains we detected blaCTX-M-15 in 23 strains, blaSHV-1 in all strains and blaTEM-1 in 14 strains. The colistin resistance gene mcr-1 was not detected. The tetracycline gene tet(A) was detected in 11 strains, but the gene tet(B) was not detected in any strains. CONCLUSIONS: The development in antibiotic resistance highlights the importance of establishing policies to reduce antibiotic use and improving the national resistance surveillance system in order to create local antibiotic therapy guidelines.

Transfer learning with pre-trained deep convolutional neural networks for the automatic assessment of liver steatosis in ultrasound images.

AIM: In this paper we proposed different architectures of convolutional neural network (CNN) to classify fatty liver disease in images using only pixels and diagnosis labels as input. We trained and validated our models using a dataset of 629 images consisting of 2 types of liver images, normal and liver steatosis. MATERIAL AND METHODS: We assessed two pre-trained models of convolutional neural networks, Inception-v3 and VGG-16 using fine-tuning. Both models were pre-trained on ImageNet dataset to extract features from B-mode ultrasound liver images. The results obtained through these methods were compared for selecting the predictive model with the best performance metrics. We trained the two models using a dataset of 262 images of liver steatosis and 234 images of normal liver. We assessed the models using a dataset of 70 liver steatosis im-ages and 63 normal liver images. RESULTS: The proposed model that used Inception v3 obtained a 93.23% test accuracy with a sensitivity of 89.9%% and a precision of 96.6%, and areas under each receiver operating characteristic curves (ROC AUC) of 0.93. The other proposed model that used VGG-16, obtained a 90.77% test accuracy with a sensitivity of 88.9% and a precision of 92.85%, and areas under each receiver operating characteristic curves (ROC AUC) of 0.91. CONCLUSION: The deep learning algorithms that we proposed to detect steatosis and classify the images in normal and fatty liver images, yields an excellent test performance of over 90%. However, future larger studies are required in order to establish how these algorithms can be implemented in a clinical setting.

Real-time computer-aided diagnosis of focal pancreatic masses from endoscopic ultrasound imaging based on a hybrid convolutional and long short-term memory neural network model.

Differential diagnosis of focal pancreatic masses is based on endoscopic ultrasound (EUS) guided fine needle aspiration biopsy (EUS-FNA/FNB). Several imaging techniques (i.e. gray-scale, color Doppler, contrast-enhancement and elastography) are used for differential diagnosis. However, diagnosis remains highly operator dependent. To address this problem, machine learning algorithms (MLA) can generate an automatic computer-aided diagnosis (CAD) by analyzing a large number of clinical images in real-time. We aimed to develop a MLA to characterize focal pancreatic masses during the EUS procedure. The study included 65 patients with focal pancreatic masses, with 20 EUS images selected from each patient (grayscale, color Doppler, arterial and venous phase contrast-enhancement and elastography). Images were classified based on cytopathology exam as: chronic pseudotumoral pancreatitis (CPP), neuroendocrine tumor (PNET) and ductal adenocarcinoma (PDAC). The MLA is based on a deep learning method which combines convolutional (CNN) and long short-term memory (LSTM) neural networks. 2688 images were used for training and 672 images for testing the deep learning models. The CNN was developed to identify the discriminative features of images, while a LSTM neural network was used to extract the dependencies between images. The model predicted the clinical diagnosis with an area under curve index of 0.98 and an overall accuracy of 98.26%. The negative (NPV) and positive (PPV) predictive values and the corresponding 95% confidential intervals (CI) are 96.7%, [94.5, 98.9] and 98.1%, [96.81, 99.4] for PDAC, 96.5%, [94.1, 98.8], and 99.7%, [99.3, 100] for CPP, and 98.9%, [97.5, 100] and 98.3%, [97.1, 99.4] for PNET. Following further validation on a independent test cohort, this method could become an efficient CAD tool to differentiate focal pancreatic masses in real-time.

COVID-19 and Artificial Intelligence: An Approach to Forecast the Severity of Diagnosis.

(1) Background: The new SARS-COV-2 pandemic overwhelmed intensive care units, clinicians, and radiologists, so the development of methods to forecast the diagnosis' severity became a necessity and a helpful tool. (2) Methods: In this paper, we proposed an artificial intelligence-based multimodal approach to forecast the future diagnosis' severity of patients with laboratory-confirmed cases of SARS-CoV-2 infection. At hospital admission, we collected 46 clinical and biological variables with chest X-ray scans from 475 COVID-19 positively tested patients. An ensemble of machine learning algorithms (AI-Score) was developed to predict the future severity score as mild, moderate, and severe for COVID-19-infected patients. Additionally, a deep learning module (CXR-Score) was developed to automatically classify the chest X-ray images and integrate them into AI-Score. (3) Results: The AI-Score predicted the COVID-19 diagnosis' severity on the testing/control dataset (95 patients) with an average accuracy of 98.59%, average specificity of 98.97%, and average sensitivity of 97.93%. The CXR-Score module graded the severity of chest X-ray images with an average accuracy of 99.08% on the testing/control dataset (95 chest X-ray images). (4) Conclusions: Our study demonstrated that the deep learning methods based on the integration of clinical and biological data with chest X-ray images accurately predicted the COVID-19 severity score of positive-tested patients.

Prevalence and Antimicrobial Resistance of Klebsiella Strains Isolated from a County Hospital in Romania.

The study evaluated the evolution of the incidence of infections with Klebsiella in the County Clinical Emergency Hospital of Craiova (SCJUC), Romania. Also, we monitored antibiotic resistance over more than two years and detected changes in resistance to various antimicrobial agents. Our study included 2062 patients (823 women and 1239 men) hospitalised in SCJUC during the period 1st of September 2017 to 30 June 2019. In 458 patients (22.21%) from the 2062 total patients, the collected samples (1116) were positive and from those, we isolated 251 strains of Klebsiella spp. We conducted a longitudinal analysis of the prevalence of Klebsiella spp. over calendar months, which showed a prevalence in surgical wards that ranged between 5.25% and 19.49% in June 2018, while in medical wards the variation was much wider, between 5.15% and 17.36% in April 2018. Klebsiella spp. strains showed significant resistance to Amoxicillin/Clavulanate, Aztreonam and Cephalosporins such as Ceftriaxone, Ceftazidime and Cefepime. We examined the possible link with the consumption of antibiotics in the same month by performing a multiple linear regression analysis. The evolution of antibiotic resistance in Klebsiella was correlated with the variation of resistance in other bacteria, which suggests common resistance mechanisms in the hospital environment. By performing the regression for dependency between antibiotic resistance and antibiotic consumption, we observed some correlations between antibiotic consumption and the development of antibiotic resistance after 1, 2 and even 3 months (e.g., resistance to meropenem was influenced by the consumption in the hospital ward of imipenem 1 month and two months before, but only 1 month before by the consumption of meropenem). The clustering of strains showed filiation between multiresistant Klebsiella spp. strains isolated from specific patients from the ICU. The evolution of prevalence and antibiotic resistance in Klebsiella correlated with the resistance in other bacteria, which suggest common resistance mechanisms in the hospital environment, and also with the consumption of antibiotics.

Skin Diseases Classification Using Deep Leaning Methods.

Due to the high incidence of skin tumors, the development of computer aided-diagnosis methods will become a very powerful diagnosis tool for dermatologists. The skin diseases are initially diagnosed visually, through clinical screening and followed in some cases by dermoscopic analysis, biopsy and histopathological examination. Automatic classification of dermatoscopic images is a challenge due to fine-grained variations in lesions. The convolutional neural network (CNN), one of the most powerful deep learning techniques proved to be superior to traditional algorithms. These networks provide the flexibility of extracting discriminatory features from images that preserve the spatial structure and could be developed for region recognition and medical image classification. In this paper we proposed an architecture of CNN to classify skin lesions using only image pixels and diagnosis labels as inputs. We trained and validated the CNN model using a public dataset of 10015 images consisting of 7 types of skin lesions: actinic keratoses and intraepithelial carcinoma/Bowen disease (akiec), basal cell carcinoma (bcc), benign lesions of the keratosis type (solar lentigine/seborrheic keratoses and lichen-planus like keratosis, bkl), dermatofibroma (df), melanoma (mel), melanocytic nevi (nv) and vascular lesions (angiomas, angiokeratomas, pyogenic granulomas and hemorrhages, vasc).