Optimal Ensemble learning model for COVID-19 detection using chest X-ray images.

COVID-19 pandemic is the main outbreak in the world, which has shown a bad impact on people's lives in more than 150 countries. The major steps in fighting COVID-19 are identifying the affected patients as early as possible and locating them with special care. Images from radiology and radiography are among the most effective tools for determining a patient's ailment. Recent studies have shown detailed abnormalities of affected patients with COVID-19 in the chest radiograms. The purpose of this work is to present a COVID-19 detection system with three key steps: "(i) preprocessing, (ii) Feature extraction, (iii) Classification." Originally, the input image is given to the preprocessing step as its input, extracting the deep features and texture features from the preprocessed image. Particularly, it extracts the deep features by inceptionv3. Then, the features like proposed Local Vector Patterns (LVP) and Local Binary Pattern (LBP) are extracted from the preprocessed image. Moreover, the extracted features are subjected to the proposed ensemble model based classification phase, including Support Vector Machine (SVM), Convolutional Neural Network (CNN), Optimized Neural Network (NN), and Random Forest (RF). A novel Self Adaptive Kill Herd Optimization (SAKHO) approach is used to properly tune the weight of NN to improve classification accuracy and precision. The performance of the proposed method is then compared to the performance of the conventional approaches using a variety of metrics, including recall, FNR, MCC, FDR, Thread score, FPR, precision, FOR, accuracy, specificity, NPV, FMS, and sensitivity, accordingly.

Feature Selection and Dwarf Mongoose Optimization Enabled Deep Learning for Heart Disease Detection.

Heart disease causes major death across the entire globe. Hence, heart disease prediction is a vital part of medical data analysis. Recently, various data mining and machine learning practices have been utilized to detect heart disease. However, these techniques are inadequate for effectual heart disease prediction due to the deficient test data. In order to progress the efficacy of detection performance, this research introduces the hybrid feature selection method for selecting the best features. Moreover, the missed value from the input data is filled with the quantile normalization and missing data imputation method. In addition, the best features relevant to disease detection are selected through the proposed hybrid Congruence coefficient Kumar-Hassebrook similarity. In addition, heart disease is predicted using SqueezeNet, which is tuned by the dwarf mongoose optimization algorithm (DMOA) that adapts the feeding aspects of dwarf mongoose. Moreover, the experimental result reveals that the DMOA-SqueezeNet method attained a maximum accuracy of 0.925, sensitivity of 0.926, and specificity of 0.918.

Using deep learning to detect digitally encoded DNA trigger for Trojan malware in Bio-Cyber attacks.

This article uses Deep Learning technologies to safeguard DNA sequencing against Bio-Cyber attacks. We consider a hybrid attack scenario where the payload is encoded into a DNA sequence to activate a Trojan malware implanted in a software tool used in the sequencing pipeline in order to allow the perpetrators to gain control over the resources used in that pipeline during sequence analysis. The scenario considered in the paper is based on perpetrators submitting synthetically engineered DNA samples that contain digitally encoded IP address and port number of the perpetrator's machine in the DNA. Genetic analysis of the sample's DNA will decode the address that is used by the software Trojan malware to activate and trigger a remote connection. This approach can open up to multiple perpetrators to create connections to hijack the DNA sequencing pipeline. As a way of hiding the data, the perpetrators can avoid detection by encoding the address to maximise similarity with genuine DNAs, which we showed previously. However, in this paper we show how Deep Learning can be used to successfully detect and identify the trigger encoded data, in order to protect a DNA sequencing pipeline from Trojan attacks. The result shows nearly up to 100% accuracy in detection in such a novel Trojan attack scenario even after applying fragmentation encryption and steganography on the encoded trigger data. In addition, feasibility of designing and synthesizing encoded DNA for such Trojan payloads is validated by a wet lab experiment.

Collagenofibrotic glomerulopathy: A case of glomerular deposition disease in the Indian subcontinent and review of the literature.

Collagenofibrotic glomerulopathy (CG) is a rare renal disease with unknown etiology, defined by deposition of Type III collagen fibers in the subendothelial space and mesangium seen on supported by electron microscopy. There are merely 19 cases reported in the literature from the Indian subcontinent. Herein, we present a case report of CG from the Indian subcontinent and review its literature mainly focusing on histopathological findings.

Fumarase Deficiency: A Safe and Potentially Disease Modifying Effect of High Fat/Low Carbohydrate Diet.

Fumarate hydratase deficiency (FHD) caused by biallelic alterations of the FH (fumarate hydratase) gene is a rare disorder of the tricarboxylic acid cycle, classically characterized by encephalopathy, profound psychomotor retardation, seizures, a spectrum of brain abnormalities and early death in childhood. Less common milder phenotypes with moderate cognitive impairment and long-term survival have been reported. In addition, heterozygous mutations of the FH gene are responsible for hereditary leiomyomatosis and renal cell cancer (HLRCC). There is currently no recommended disease modifying treatment for FHD and only isolated reports of unsuccessful dietary modifications. Herein, we describe the safe and possibly disease modifying effect of a high fat, low carbohydrate diet in a 14-year-old female with severe FHD.

Unique presentation of cutis laxa with Leigh-like syndrome due to ECHS1 deficiency.

Clinical finding of cutis laxa, characterized by wrinkled, redundant, sagging, nonelastic skin, is of growing significance due to its occurrence in several different inborn errors of metabolism (IEM). Metabolic cutis laxa results from Menkes syndrome, caused by a defect in the ATPase copper transporting alpha (ATP7A) gene; congenital disorders of glycosylation due to mutations in subunit 7 of the component of oligomeric Golgi (COG7)-congenital disorders of glycosylation (CDG) complex; combined disorder of N- and O-linked glycosylation, due to mutations in ATPase H+ transporting V0 subunit a2 (ATP6VOA2) gene; pyrroline-5-carboxylate reductase 1 deficiency; pyrroline-5-carboxylate synthase deficiency; macrocephaly, alopecia, cutis laxa, and scoliosis (MACS) syndrome, due to Ras and Rab interactor 2 (RIN2) mutations; transaldolase deficiency caused by mutations in the transaldolase 1 (TALDO1) gene; Gerodermia osteodysplastica due to mutations in the golgin, RAB6-interacting (GORAB or SCYL1BP1) gene; and mitogen-activated pathway (MAP) kinase defects, caused by mutations in several genes [protein tyrosine phosphatase, non-receptor-type 11 (PTPN11), RAF, NF, HRas proto-oncogene, GTPase (HRAS), B-Raf proto-oncogene, serine/threonine kinase (BRAF), MEK1/2, KRAS proto-oncogene, GTPase (KRAS), SOS Ras/Rho guanine nucleotide exchange factor 2 (SOS2), leucine rich repeat scaffold protein (SHOC2), NRAS proto-oncogene, GTPase (NRAS), and Raf-1 proto-oncogene, serine/threonine kinase (RAF1)], which regulate the Ras-MAPK cascade. Here, we further expand the list of inborn errors of metabolism associated with cutis laxa by describing the clinical presentation of a 17-month-old girl with Leigh-like syndrome due to enoyl coenzyme A hydratase, short chain, 1, mitochondria (ECHS1) deficiency, a mitochondrial matrix enzyme that catalyzes the second step of the beta-oxidation spiral of fatty acids and plays an important role in amino acid catabolism, particularly valine.

ANG1005 for breast cancer brain metastases: correlation between 18F-FLT-PET after first cycle and MRI in response assessment.

PURPOSE: Improved therapies and imaging modalities are needed for the treatment of breast cancer brain metastases (BCBM). ANG1005 is a drug conjugate consisting of paclitaxel covalently linked to Angiopep-2, designed to cross the blood-brain barrier. We conducted a biomarker substudy to evaluate 18F-FLT-PET for response assessment. METHODS: Ten patients with measurable BCBM received ANG1005 at a dose of 550 mg/m2 IV every 21 days. Before and after cycle 1, patients underwent PET imaging with 18F-FLT, a thymidine analog, retention of which reflects cellular proliferation, for comparison with gadolinium-contrast magnetic resonance imaging (Gd-MRI) in brain metastases detection and response assessment. A 20 % change in uptake after one cycle of ANG1005 was deemed significant. RESULTS: Thirty-two target and twenty non-target metastatic brain lesions were analyzed. The median tumor reduction by MRI after cycle 1 was -17.5 % (n = 10 patients, lower, upper quartiles: -25.5, -4.8 %) in target lesion size compared with baseline. Fifteen of twenty-nine target lesions (52 %) and 12/20 nontarget lesions (60 %) showed a ≥20 % decrease post-therapy in FLT-PET SUV change (odds ratio 0.71, 95 % CI: 0.19, 2.61). The median percentage change in SUVmax was -20.9 % (n = 29 lesions; lower, upper quartiles: -42.4, 2.0 %), and the median percentage change in SUV80 was also -20.9 % (n = 29; lower, upper quartiles: -49.0, 0.0 %). Two patients had confirmed partial responses by PET and MRI lasting 6 and 18 cycles, respectively. Seven patients had stable disease, receiving a median of six cycles. CONCLUSIONS: ANG1005 warrants further study in BCBM. Results demonstrated a moderately strong association between MRI and 18F-FLT-PET imaging.

Geometric data perturbation-based personal health record transactions in cloud computing.

Cloud computing is a new delivery model for information technology services and it typically involves the provision of dynamically scalable and often virtualized resources over the Internet. However, cloud computing raises concerns on how cloud service providers, user organizations, and governments should handle such information and interactions. Personal health records represent an emerging patient-centric model for health information exchange, and they are outsourced for storage by third parties, such as cloud providers. With these records, it is necessary for each patient to encrypt their own personal health data before uploading them to cloud servers. Current techniques for encryption primarily rely on conventional cryptographic approaches. However, key management issues remain largely unsolved with these cryptographic-based encryption techniques. We propose that personal health record transactions be managed using geometric data perturbation in cloud computing. In our proposed scheme, the personal health record database is perturbed using geometric data perturbation and outsourced to the Amazon EC2 cloud.

Intraparenchymal pericatheter cyst following disconnection of ventriculoperitoneal shunt system.

Ventriculoperitoneal (VP) shunt is one of the most commonly performed procedures in neurosurgery, but it is also the procedure, which is most prone to complications. Spread of cerebrospinal fluid (CSF) into the brain parenchyma is a rare complication of VP shunt and can take the form of CSF edema or a porencephalic cyst. We describe a case of a 1½-year-old child who presented to us with seizures. Computed tomography scan revealed pericatheter porencephalic cyst. Surgical exploration revealed a disconnected VP shunt system. Patient was neurologically observed after shunt extraction. He was seizure free and radiological follow-up showed resolution of cyst. Ours is the first case to document the presence of pericatheter cyst following complete disconnection of shunt system. Though shunt revision is the accepted treatment modality, careful neurological observation can be done after shunt removal especially in asymptomatic cases with compensated hydrocephalus.

Evaluation of PCR-based approach for serotype determination of Streptococcus pneumoniae.

Determination of Streptococcus pneumoniae serotypes is essential for epidemiological surveillance. Therefore accurate, reliable and cost effective serotyping method is crucial. In this study, we determined the serotypes of 41 pneumococcal isolates recovered from human anterior nares by multiplex Polymerase Chain Reaction (PCR) utilizing published primers. The data was then compared with conventional serology using latex agglutination (LA) and the Quellung reaction. Based on the PCR-approach, 8 different serogroups/serotypes were detected with one isolate classified as non-typeable (cpsA-negative). In reference to the serology-based data, the results were in agreement except for one isolate. For the latter isolate, the LA and Quellung tests failed to show a reaction but the PCR-approach and sequencing identified the isolate as serogroup 15B/C. Based on this experimental setting, we found that the PCR-approach for pneumococcal serotypes determination is reliable to serve as the alternative for determining the pneumococcal serotyping.

Risk factors of female breast carcinoma: a case control study at Puducherry.

OBJECTIVE: To identify and quantify various demographic, reproductive, socio-economic and dietary risk factors among women with breast cancer. STUDY DESIGN: Case control study. STUDY PERIOD: February 2004 to May 2005. STUDY SETTING: Departments of Surgery, Medicine and Radiotherapy of Jawaharlal Institute of Postgraduate Medical Sciences and Research (JIPMER), Pondicherry. MATERIALS AND METHODS: Cases were women with pathologically confirmed breast cancer. Controls were age-matched women from medicine and surgery wards without any current breast problem or previous breast cancer. A total of 152 cases and 152 controls were enrolled. They were interviewed for parity, breast feeding, past history of benign breast lesion, family history and dietary history with a pre-tested interview schedule after obtaining informed written consent. RESULTS: The significant risk factors were (odds ratios with 95% CI) previous history of biopsy for benign breast lesion 10.4 (1.3-86.3), nulliparity 2.4 (1.14-5.08), consumption of fats more than 30 g/day 2.4 (1.14-5.45) and consumption of oils containing more of saturated fat 2.0 (1.03-4.52). CONCLUSIONS: Nulliparity, past history of benign breast lesion, high fat diet and consumption of oils with more saturated fats were the risk factors.

Infantile Progressive Hepatoencephalomyopathy with Combined OXPHOS Deficiency due to Mutations in the Mitochondrial Translation Elongation Factor Gene GFM1.

Mitochondrial disorders are a heterogeneous group of often multisystemic and early fatal diseases caused by defects in the oxidative phosphorylation (OXPHOS) system. Given the complexity and intricacy of the OXPHOS system, it is not surprising that the underlying molecular defect remains unidentified in many patients with a mitochondrial disorder. Here, we report the clinical features and diagnostic workup leading to the elucidation of the genetic basis for a combined complex I and IV OXPHOS deficiency secondary to a mitochondrial translational defect in an infant who presented with rapidly progressive liver failure, encephalomyopathy, and severe refractory lactic acidemia. Sequencing of the GFM1 gene revealed two inherited novel, heterozygous mutations: a.539delG (p.Gly180AlafsX11) in exon 4 which resulted in a frameshift mutation, and a second c.688G > A (p.Gly230Ser) mutation in exon 5. This missense mutation is likely to be pathogenic since it affects an amino acid residue that is highly conserved across species and is absent from the dbSNP and 1,000 genomes databases. Review of literature and comparison were made with previously reported cases of this recently identified mitochondrial disorder encoded by a nuclear gene. Although limited in number, nuclear gene defects causing mitochondrial translation abnormalities represent a new, rapidly expanding field of mitochondrial medicine and should potentially be considered in the diagnostic investigation of infants with progressive hepatoencephalomyopathy and combined OXPHOS disorders.

Tay-Sach disease with "cherry-red spot"--first reported case in Malaysia.

We present a rare case of Tay-Sachs disease with retinal 'cherry-red spots' in a 19-month-old Malay child. Molecular genetic studies confirmed the diagnosis. The case highlights that 'cherry-red spot' is a useful clinical clue in Tay-Sachs disease and several other lysosomal storage disorders. It serves as an ideal illustration of the eye as a window to inborn error of metabolism.

Massive benign osteoblastoma of the suboccipital bone and foramen magnum region.

Benign osteoblastoma is an uncommon primary bone tumor frequently found in the vertebral column and long tubular bones, and rarely occurring in the calvarium. A case of a massive benign osteoblastoma of the suboccipital bone and foramen magnum region in a 9-year-old boy is reported. He presented with progressively worsening nuchal pain and headaches secondary to a bony lesion in the suboccipital and foramen magnum region. Computed tomography (CT) of the brain showed a large midline occipital/suboccipital bony lesion extending to either side (R > L) and extending from the torcula till the foramen magnum region, causing moderate obstructive hydrocephalus. The atlas was uninvolved by the tumor. In addition, the cerebellum was pushed anteriorly squashing the fourth ventricle. The tumor was completely resected with wide margins via a suboccipital route. At follow-up after 7 years, the patient was asymptomatic, and CT imaging demonstrated no recurrence. The occurrence of benign osteoblastoma in the suboccipital bone and foramen magnum region has not been reported earlier in the pediatric population. Surgical extirpation of the lesion with wide margins is advocated and can produce an excellent long-term outcome. Serial vigilant follow-up along with sequential imaging is advocated even in cases with complete resection to detect early recurrence and possible malignant transformation.

Mowat-Wilson syndrome: the first two Malaysian cases.

Mowat-Wilson syndrome (MWS) is a recently delineated mental retardation; a multiple congenital anomaly syndrome characterised by a typical facial gestalt, Hirschsprung disease or severe constipation, genitourinary anomaly, congenital heart defects, agenesis of corpus callosum and eye defects. Some cases also present with epilepsy, growth retardation with microcephaly and speech impairment. MWS was first described in 1998 by Mowat et al, and approximately 180 cases have been reported as of August 2008. The syndrome occurs as a result of heterozygous mutations or deletions in the zinc finger E-box-binding homeobox 2 gene, ZEB2, previously called ZFHX1B (SIP1). Most cases reported so far were sporadic occurrences; however, rare cases of sibling recurrence have been cited. The facial phenotype is particularly important for the initial clinical diagnosis and provides the hallmark, warranting ZEB2 mutational analysis even in the absence of Hirschsprung disease. We present the first two molecularly confirmed Malaysian MWS patients, one of whom has a novel mutation.

The 14-item Paediatric Throat Disorders Outcome Test: a valid, sensitive, reliable, parent-reported outcome measure for paediatric throat disorders.

OBJECTIVES: We modified and abbreviated a pre-existing research questionnaire, the Tonsil and Adenoid Health Status Instrument, to make it suitable for rapid completion as a disease-specific, health-related quality of life research tool for children with tonsil and adenoid disease in the UK. We determined the main psychometric properties of the resulting 14-item Paediatric Throat Disorders Outcome Test. DESIGN, SETTING AND PARTICIPANTS: Pre- and post-operative questionnaires were completed by the parents of children with throat disorders referred to two large hospitals. We included children with recurrent tonsillitis and with obstructive sleep apnoea. A separate cohort of healthy children of comparable age range was also studied. MAIN OUTCOME MEASURES: The test's internal consistency and responsiveness were analysed and its construct validity documented via known-group differences. RESULTS: A total of 126 completed questionnaires were received from the hospital referral group. The children's mean age was 6.5 years (range one to 16). The 40 unaffected children were well matched in age to the study population (mean 6.1 years, range two to 15). Cronbach's alpha coefficient for the pre-operative assessment total score was 0.84. The test-retest reliability coefficient for the total score was 0.98, indicating very high reproducibility. The 14-item Paediatric Throat Disorders Outcome Test discriminated well between children known to suffer with throat problems and a group of healthy controls (p < 0.0001; t = 24.016). Six months after surgical intervention, parentally reported questionnaire scores had improved (i.e. were lower) (p < 0.0001; t = 7.01). The standard effect size (i.e. change in mean divided by baseline standard deviation) for children for whom post-operative questionnaires were completed was 1.53; this is very large. CONCLUSIONS: The 14-item Paediatric Throat Disorders Outcome Test is an appropriate, disease-specific, parent-reported outcome measure for children with throat disorders, for which we have demonstrated internal consistency, reliability, responsiveness to change and two forms of construct validity.

Contiguous gene deletion syndrome in a female with ornithine transcarbamylase deficiency.

OTC deficiency, a partially dominant X-linked trait, is the most frequent inborn error of the urea cycle. We describe a female patient with a contiguous gene deletion syndrome encompassing the OTC, DMD, RPGR, CYBB and XK genes, amongst others, only manifesting features of OTC deficiency. Molecular characterization was ascertained by MLPA and confirmed by CGH microarray, which revealed an 8.7 Mb deletion of the X-chromosome. Complete de novo deletion of the OTC gene led to a severe clinical phenotype in the proband. The application of high resolution molecular genetic techniques such as MLPA and array CGH, in mutation negative OTC cases allows the identification of chromosomal rearrangements, such as large deletions and provides information for accurate genetic counseling and prenatal diagnosis.

Tuberculous temporal brain abscess mimicking otogenic pyogenic abscess.

Tuberculous brain abscess is a rare manifestation of central nervous system tuberculosis. We report the case of a tuberculous temporal lobe abscess in a 14-year-old female child that mimicked an otogenic pyogenic brain abscess. The patient had no prior history of tuberculosis. She had chronic otitis media and presented with signs of raised intracranial tension. Radiological imaging was suggestive of an acute pyogenic left temporal lobe abscess. A left temporal craniotomy was performed and the abscess was completely excised. Histological examination was consistent with a chronic abscess, and bacterial cultures were negative. A left radical mastoidectomy was also carried out. However, she presented with repeated abscess formation at the same site over the next 8 weeks, which was refractory to surgical therapy and broad-spectrum antibiotic administration. Furthermore, the purulent exudate showed strong positivity in the PCR test for tubercular bacilli. After administration of antituberculous treatment, she showed gradual clinical and radiological improvement. At follow-up after 2 years, she is asymptomatic. CT imaging at 2 years showed total resolution of abscess. Tuberculous abscess in the temporal lobe following otogenic infection has not been reported in the pediatric population. Although rare, the possibility of tuberculous etiology should be borne in mind as a differential diagnosis of acute abscess of otogenic origin, especially in endemic areas where the incidence of chronic otitis media as well as tuberculosis is high. The pathogenesis and treatment of tuberculous brain abscess in children is reviewed in light of the current literature on the subject.

Comparative genomic sequence analysis and isolation of human and mouse alternative EGFR transcripts encoding truncated receptor isoforms.

This study presents the annotated genomic sequence and exon-intron organization of the human and mouse epidermal growth factor receptor (EGFR) genes located on chromosomes 7p11.2 and 11, respectively. We report that the EGFR gene spans nearly 200 kb and that the full-length 170-kDa EGFR is encoded by 28 exons. In addition, we have identified two human and two mouse alternative EGFR transcripts of 2.4-3.0 kb using both computational and experimental methods. The human 3.0-kb and mouse 2.8-kb EGFR mRNAs are predominantly expressed in placenta and liver, respectively, and both transcripts encode 110-kDa truncated receptor isoforms containing only the extracellular ligand-binding domain. We also have demonstrated that the aberrant 2.8-kb EGFR transcript produced by the human A431 carcinoma cell line is generated by splicing to a recombinant 3'-terminal exon located in EGFR intron 16, which apparently was formed as a result of a chromosomal translocation. Finally, we have shown that the human, mouse, rat, and chicken 1.8- to 3.0-kb alternative EGFR transcripts are generated by distinct splicing mechanisms and that each of these mRNAs contains unique 3' sequences that are not evolutionarily conserved. The presence of truncated receptor isoforms in diverse species suggests that these proteins may have important functional roles in regulating EGFR activity.