Automated COVID-19 and Heart Failure Detection Using DNA Pattern Technique with Cough Sounds

COVID-19 and heart failure (HF) are common disorders and although they share some similar symptoms, they require different treatments. Accurate diagnosis of these disorders is crucial for disease management, including patient isolation to curb infection spread of COVID-19. In this work, we aim to develop a computer-aided diagnostic system that can accurately differentiate these three classes (normal, COVID-19 and HF) using cough sounds. A novel handcrafted model was used to classify COVID-19 vs. healthy (Case 1), HF vs. healthy (Case 2) and COVID-19 vs. HF vs. healthy (Case 3) automatically using deoxyribonucleic acid (DNA) patterns. The model was developed using the cough sounds collected from 241 COVID-19 patients, 244 HF patients, and 247 healthy subjects using a hand phone. To the best our knowledge, this is the first work to automatically classify healthy subjects, HF and COVID-19 patients using cough sounds signals. Our proposed model comprises a graph-based local feature generator (DNA pattern), an iterative maximum relevance minimum redundancy (ImRMR) iterative feature selector, with classification using the k-nearest neighbor classifier. Our proposed model attained an accuracy of 100.0%, 99.38%, and 99.49% for Case 1, Case 2, and Case 3, respectively. The developed system is completely automated and economical, and can be utilized to accurately detect COVID-19 versus HF using cough sounds.

A case report of synchronous bilateral tonsillar carcinoma associated with human papilloma virus

The case of a 69-year-old man with bilateral synchronous tonsillar carcinoma is reported. The patient complained of nasal closure, strange voice, and discomfort in his pharynx when he was admitted to the Department of Otolaryngology Head and Neck Surgery at Wakayama Medical University, Wakayama, Japan, in March 2017. The palatine tonsils were enlarged and the surface was irregular. Left cervical lymphadenopathy was also evident. Histological examination from both tonsils was performed and bilateral tonsillar squamous cell carcinoma was diagnosed. PCR analysis showed the same HPV-DNA pattern from bilateral tonsils. Concurrent chemoradiotherapy was performed. Total 70 Gy of irradiation (2Gy/day×35 day) was applied to bilateral tonsillar tumours and upper neck. Follow up was conducted every three months and the patient was free of recurrence for three years. Patient’s informed consent was taken to publish the case report. Keywords: bilateral synchronous tonsillar carcinoma, HPV, tonsil Continuous...

Identification and Differences in Antimicrobial Susceptibility of Lactococcus garvieae from Farmed Grey Mullet ( Mugil cephalus ) and Non-Grey Mullet in Southern Taiwan

Streptococcal infection is a main infectious diseases for farmed grey mullet (Mugil cephalus). This study were to identify spreptococcal species in diseased farmed grey mullet and to investigate differences in susceptibility to 13 antibiotics and in genotypes between the stains from the grey mullet and non-grey mullet. 170 samples from diseased farmed grey mullet were collected from three county in 2013 -2016. Multiplex PCR identified L. garviea (146) as the main pathogen, S. agalactia (9), S. dysgalactiae (19), and double infection (5), but no S. iniae. The prevalence changed annually and differed among three counties. Pulsed-field gel electrophoresis (PFGE) analysis demonstrated identical genotype with an ApaI-digested DNA pattern. Disc diffusion results demonstrated differences in antibiotic susceptibility between the strains from grey mullet (146) and non-grey mullet (30). Almost all strains resisted to clindamycin and all strains were susceptible to six antibiotic in grey mullet and 4 antibiotics in non-grey mullet. The reduced susceptible strains was more in non-grey mullet than grey mullet group. The reduced susceptible strains were observed the highest in 2014 and in Chiayi county and decreased from 2014 to 2016. However, the strains with reduced susceptibility to ceftriaxone, cirpofoxacin, moxifloxacin, tetracycline for human treatment were observed.

DNA Classification using Machine Learning for Detecting Genetic Disorders

Deoxyribonucleic acid is a double- helical molecule composed of two chains that contains genetic instructions. Genetic diseases are caused by changes in pre-existing genes. A genetic abnormality results from the alteration in chromosomes. DNA classification helps to identify genetic disorders in organisms. DNA pattern recognition is a major issue in bioinformatics. DNA is classified into several categories on the basis of Structure, Location, Number of base pairs etc. Traditionally the DNA Molecule is studied by extracting it from the blood sample and is then manually analysed to find out the abnormalities. To increase the accuracy, a machine learning based DNA classification is done which helps in studying the extracted DNA image using various techniques. This consumes minimal amount of time and is more efficient. The image is preprocessed using median filter and canny edge detection. DNA sequences can be recognized correctly and effectively without any uncertainties with the help of Neural Network.The network successfully classifies an image given as input when it is trained with patterns. Thus, we can analyse if a person has a genetic disorder.

Molecular analysis of genetic diversity in population of Silybum marianum (L.) Gaertn in Egypt

Background Silybum marianum L. Gaertn is a medicinal plant of unique pharmaceutical properties in the treatment of liver disorders and diabetic nephropathy. Biochemical (SDS-PAGE) and molecular markers such as randomly amplified polymorphic DNA (RAPD) and inter-simple sequence repeats (ISSR) technologies were used in this work to detect genetic diversity of 14 collections of Silybum marianum population in Egypt. Results The electrophoretic pattern of seed protein gave different molecular weight bands, ranging from 24 to 111 KDa with the presence of unique bands. RAPD results revealed a high level of polymorphism (73.2%) using 12 RAPD primers, but only eight of them gave reproducible polymorphic DNA pattern. Sixteen primers were used in the ISSR method; only ten of them yielded clearly identifiable bands. The percentage of polymorphism is about 80% of the studied samples. Conclusion The obtained data confirmed that SDS-protein, RAPD, and ISSR markers are important tools for genetic analysis for Silybum marianum and recommended to give accurate results.

Cell-Free DNA Pattern Identification and its Classification using Convolution Neural Network

Circulating cell DNA (cfDNA) design identification assumes a cardinal job in fetal drug, transplantation and oncology. Be that as it may, it has additionally demonstrated to be a biomarker for different maladies. There are numerous order strategies by which the acknowledgment and arrangement should be possible. So as to have a superior time unpredictability and improve the precision further, this strategy targets distinguishing and arranging the general DNA examples and ailments related with them utilizing cfDNA Images in a Convolution Neural Network. A probabilistic method is used for cfDNA image feature extraction, fragmentation and interpretation. Graphical User Interface is the platform where this method is employed since it uses visual indicators in place of text-based interface. The aftereffects of this test demonstrate that the Convolution Neural Network calculation can perceive cfDNA successions accurately and successfully with no dubiety. Prepared with examples, the CNN can effectively characterize the picture surrendered to coordinated and unparalleled examples with numerical highlights.

A New Method for Biostatistical miRNA Pattern Recognition with Topological Properties of Visibility Graphs in 3D Space

Visibility is a very important topic in computer graphics and especially in calculations of global illumination. Visibility determination, the process of deciding which surface can be seen from a certain point, has also problematic applications in biomedical engineering. The problem of visibility computation with mathematical tools can be presented as a visibility network. Instead of utilizing a 2D visibility network or graphs whose construction is well known, in this paper, a new method for the construction of 3D visibility graphs will be proposed. Drawing graphs as nodes connected by links in a 3D space is visually compelling but computationally difficult. Thus, the construction of 3D visibility graphs is highly complex and requires professional computers or supercomputers. A new method for optimizing the algorithm visibility network in a 3D space and a new method for quantifying the complexity of a network in DNA pattern recognition in biomedical engineering have been developed. Statistical methods have been used to calculate the topological properties of a visibility graph in pattern recognition. A new n-hyper hybrid method is also used for combining an intelligent neural network system for DNA pattern recognition with the topological properties of visibility networks of a 3D space and for evaluating its prospective use in the prediction of cancer.