Artificial Intelligence Based COVID-19 Detection and Classification Model on Chest X-ray Images.

Diagnostic and predictive models of disease have been growing rapidly due to developments in the field of healthcare. Accurate and early diagnosis of COVID-19 is an underlying process for controlling the spread of this deadly disease and its death rates. The chest radiology (CT) scan is an effective device for the diagnosis and earlier management of COVID-19, meanwhile, the virus mainly targets the respiratory system. Chest X-ray (CXR) images are extremely helpful in the effective diagnosis of COVID-19 due to their rapid outcomes, cost-effectiveness, and availability. Although the radiological image-based diagnosis method seems faster and accomplishes a better recognition rate in the early phase of the epidemic, it requires healthcare experts to interpret the images. Thus, Artificial Intelligence (AI) technologies, such as the deep learning (DL) model, play an integral part in developing automated diagnosis process using CXR images. Therefore, this study designs a sine cosine optimization with DL-based disease detection and classification (SCODL-DDC) for COVID-19 on CXR images. The proposed SCODL-DDC technique examines the CXR images to identify and classify the occurrence of COVID-19. In particular, the SCODL-DDC technique uses the EfficientNet model for feature vector generation, and its hyperparameters can be adjusted by the SCO algorithm. Furthermore, the quantum neural network (QNN) model can be employed for an accurate COVID-19 classification process. Finally, the equilibrium optimizer (EO) is exploited for optimum parameter selection of the QNN model, showing the novelty of the work. The experimental results of the SCODL-DDC method exhibit the superior performance of the SCODL-DDC technique over other approaches.

A Machine Learning Approach for Monitoring and Classifying Healthcare Data-A Case of Emergency Department of KSA Hospitals.

The Emergency Departments (EDs), in hospitals located in a few important areas in Saudi Arabia, experience a heavy inflow of patients due to viral illnesses, pandemics, and even on a few special occasions events such as Hajj or Umrah, when pilgrims travel from one region to another with severe disease conditions. Apart from the EDs, it is critical to monitor the movements of patients from EDs to other wards inside the hospital or in the region. This is to track the spread of viral illnesses that require more attention. In this scenario, Machine Learning (ML) algorithms can be used to classify the data into many classes and track the target audience. The current research article presents a Machine Learning-based Medical Data Monitoring and Classification Model for the EDs of the KSA hospitals and is named MLMDMC-ED technique. The most important aim of the proposed MLMDMC-ED technique is to monitor and track the patient's visits to the EDs, the treatment given to them based on the Canadian Emergency Department Triage and Acuity Scale (CTAS), and their Length Of Stay (LOS) in the hospital, based on their treatment requirements. A patient's clinical history is crucial in terms of making decisions during health emergencies or pandemics. So, the data should be processed so that it can be classified and visualized in different formats using the ML technique. The current research work aims at extracting the textual features from the patients' data using the metaheuristic Non-Defeatable Genetic Algorithm II (NSGA II). The data, collected from the hospitals, are classified using the Graph Convolutional Network (GCN) model. Grey Wolf Optimizer (GWO) is exploited for fine-tuning the parameters to optimize the performance of the GCN model. The proposed MLMDMC-ED technique was experimentally validated on the healthcare data and the outcomes indicated the improvements of the MLMDMC-ED technique over other models with a maximum accuracy of 91.87%.

Prediction of Diabetes through Retinal Images Using Deep Neural Network.

Microvascular problems of diabetes, such as diabetic retinopathy and macular edema, can be seen in the eye's retina, and the retinal images are being used to screen for and diagnose the illness manually. Using deep learning to automate this time-consuming process might be quite beneficial. In this paper, a deep neural network, i.e., convolutional neural network, has been proposed for predicting diabetes through retinal images. Before applying the deep neural network, the dataset is preprocessed and normalised for classification. Deep neural network is constructed by using 7 layers, 5 kernels, and ReLU activation function, and MaxPooling is implemented to combine important features. Finally, the model is implemented to classify whether the retinal image belongs to a diabetic or nondiabetic class. The parameters used for evaluating the model are accuracy, precision, recall, and F1 score. The implemented model has achieved a training accuracy of more than 95%, which is much better than the other states of the art algorithms.

Optimal Deep Stacked Sparse Autoencoder Based Osteosarcoma Detection and Classification Model.

Osteosarcoma is a kind of bone cancer which generally starts to develop in the lengthy bones in the legs and arms. Because of an increase in occurrence of cancer and patient-specific treatment options, the detection and classification of cancer becomes a difficult process. The manual recognition of osteosarcoma necessitates expert knowledge and is time consuming. An earlier identification of osteosarcoma can reduce the death rate. With the development of new technologies, automated detection models can be exploited for medical image classification, thereby decreasing the expert's reliance and resulting in timely identification. In recent times, an amount of Computer-Aided Detection (CAD) systems are available in the literature for the segmentation and detection of osteosarcoma using medicinal images. In this view, this research work develops a wind driven optimization with deep transfer learning enabled osteosarcoma detection and classification (WDODTL-ODC) method. The presented WDODTL-ODC model intends to determine the presence of osteosarcoma in the biomedical images. To accomplish this, the osteosarcoma model involves Gaussian filtering (GF) based on pre-processing and contrast enhancement techniques. In addition, deep transfer learning using a SqueezNet model is utilized as a featured extractor. At last, the Wind Driven Optimization (WDO) algorithm with a deep-stacked sparse auto-encoder (DSSAE) is employed for the classification process. The simulation outcome demonstrated that the WDODTL-ODC technique outperformed the existing models in the detection of osteosarcoma on biomedical images.

Detection of Dental Diseases through X-Ray Images Using Neural Search Architecture Network.

An important aspect of the diagnosis procedure in daily clinical practice is the analysis of dental radiographs. This is because the dentist must interpret different types of problems related to teeth, including the tooth numbers and related diseases during the diagnostic process. For panoramic radiographs, this paper proposes a convolutional neural network (CNN) that can do multitask classification by classifying the X-ray images into three classes: cavity, filling, and implant. In this paper, convolutional neural networks are taken in the form of a NASNet model consisting of different numbers of max-pooling layers, dropout layers, and activation functions. Initially, the data will be augmented and preprocessed, and then, the construction of a multioutput model will be done. Finally, the model will compile and train the model; the evaluation parameters used for the analysis of the model are loss and the accuracy curves. The model has achieved an accuracy of greater than 96% such that it has outperformed other existing algorithms.

Legionella confirmation in cooling tower water. Comparison of culture, real-time PCR and next generation sequencing.

OBJECTIVES: To investigate the presence of Legionella spp in cooling tower water. Legionella proliferation in cooling tower water has serious public health implications as it can be transmitted to humans via aerosols and cause Legionnaires' disease. METHODS: Samples of cooling tower water were collected from King Fahd Hospital of the University (KFHU) (Imam Abdulrahman Bin Faisal University, 2015/2016). The water samples were analyzed by a standard Legionella culture method, real-time polymerase chain reaction (RT-PCR), and 16S rRNA next-generation sequencing. In addition, the bacterial community composition was evaluated. RESULTS: All samples were negative by conventional Legionella culture. In contrast, all water samples yielded positive results by real-time PCR (105 to 106 GU/L). The results of 16S rRNA next generation sequencing showed high similarity and reproducibility among the water samples. The majority of sequences were Alpha-, Beta-, and Gamma-proteobacteria, and Legionella was the predominant genus. The hydrogen-oxidizing gram-negative bacterium Hydrogenophaga was present at high abundance, indicating high metabolic activity. Sphingopyxis, which is known for its resistance to antimicrobials and as a pioneer in biofilm formation, was also detected. CONCLUSION: Our findings indicate that monitoring of Legionella in cooling tower water would be enhanced by use of both conventional culturing and molecular methods.

Fibroscan: a noninvasive test of liver fibrosis assessment.

Determination of the extent of progress of hepatic fibrosis is important in clinical practice, where it may reflect the severity of liver disease and predict response to treatment. Percutaneous liver biopsy is the gold standard for grading and staging of liver disease. However, liver biopsy is an invasive procedure with certain unavoidable risks and complications. Several methods have been studied in an attempt to reach a diagnosis of cirrhosis by noninvasive means. Fibroscan has been designed to quantify liver fibrosis by means of elastography and found to have reasonably good sensitivity and specificity patterns, especially in patients with advanced fibrosis and can be used as an alternative to liver biopsy.

Epidemiology and outcome of Crohn's disease in a teaching hospital in Riyadh.

AIM: To know the epidemiology and outcome of Crohn's disease at King Khalid University Hospital, Riyadh, Saudi Arabia and to compare the results from other world institutions. METHODS: A retrospective analysis of patients seen for 20 years (between 1983 and 2002). Individual case records were reviewed with regard to history, clinical, findings from colonoscopy, biopsies, small bowel enema, computerized tomography scan, treatment and outcome. RESULTS: Seventy-seven patients with Crohn's disease were revisited, 13% presented the disease in the first 10 years and 87% over the last 10 years. Thirty-three patients (42.9%) were males and 44 (57.1%) were females. Age ranged from 11-70 years (mean of 25.3+/-11.3 years). Ninety-two (92%) were Saudi. The mean duration of symptoms was 26+/-34.7 mo. The mean annual incidence of the disease over the first 10 years was 0.32:100,000 and 1.66:100,000 over the last 10 years with a total mean annual incidence of 0.94:100,000 over the last 20 years. The chief clinical features included abdominal pain, diarrhea, weight loss, anorexia, rectal bleeding and palpable mass. Colonoscopic findings were abnormal in 58 patients (76%) showing mostly ulcerations and inflammation of the colon. Eighty nine percent of patients showed nonspecific inflammation with chronic inflammatory cells and half of these patients revealed the presence of granulomas and granulations on bowel biopsies. Similarly, 69 (89%) of small bowel enema results revealed ulcerations (49%), narrowing of the bowel lumen (42%), mucosal thickening (35%) and cobblestone appearance (35%). CT scan showed abnormality in 68 (88%) of patients with features of thickened loops (66%) and lymphadenopathy (37%). Seventy-eight percent of patients had small and large bowel disease, 16% had small bowel involvement and only 6% had colitis alone. Of the total 55 (71%) patients treated with steroids at some point in their disease history, a satisfactory response to therapy was seen in 28 patients (51%) while 27 (49%) showed recurrences of the condition with mild to moderate symptoms of abdominal pain and diarrhea most of which were due to poor compliance to medication. Seven patients (33%) remained with active Crohn's disease. Nine (12%) patients underwent surgery with resections of some parts of bowel, 2 (2.5%) had steroid side effects, 6 (8%) with perianal Crohn's disease and five (6.5%) with fistulae. CONCLUSION: The epidemiological characteristics of Crohn's disease among Saudi patients are comparable to those reported from other parts of the world. However the incidence of Crohn's disease in our hospital increased over the last 10 years. The anatomic distribution of the disease is different from other world institutions with less isolated colonic affection.

Malignant biliary strictures. Diagnosis and management.

OBJECTIVE: To identify the cause, methods of diagnosis and management of malignant biliary strictures in our institution and compare with studies from other communities. METHODS: From March 1998 through to August 2002, we reviewed 1000 files of patients who underwent endoscopic retrograde cholangiopancreatography (ERCP) at the Gastroenterology unit, King Khalid University Hospital in Riyadh, Kingdom of Saudi Arabia for malignant biliary strictures (MBS). Clinical, laboratory data, method of diagnosis and management were recorded. RESULTS: Seventy-two patients (72/1000) with MBS were encountered. Forty one (57%) were males and 31 (43%) were females and the majority were Saudi nationals (82%). Jaundice and right upper quadrant pain were the most frequent symptoms in 84.7% and 52.8% of patients. Cholangiocarcinoma was present in 31 (43%) and pancreatic adenocarcinoma in 23 (31.9%) patients. Other malignancies found included gallbladder carcinoma in 5 patients (6.9%), ampullary carcinoma in 5 (6.9%), metastatic liver carcinoma in 4 patients (5.6%), hepatocellular carcinoma in 2 (2.8%) and lymphoma in 2 (2.8%). The diagnosis was entertained mainly by ERCP (93%). Endoscopic palliation was carried out in 77.8% of patients, percutaneous transhepatic drainage in 13.9% and surgery in 6 (8.3%). The mean survival was higher for the endoscopic compared to the percutaneous transhepatic and surgery groups (6.9 +/- 4.13, 4.27 +/- 4.29 and 3.67 +/- 2.65 months). CONCLUSION: In non-resectable tumors, ERCP is the optimal method of diagnosis and palliation of MBS.

Lack of association of coronary artery disease with H.pylori infection.

OBJECTIVE: It has been suggested from previous studies that there is an associated increased risk of coronary artery disease (CAD) in patients with Helicobacter pylori (H.pylori). However, others dispute this. We therefore evaluated this hypothesis in a group of patients with confirmed H.pylori infection. METHODS: A total of 158 patients with dyspeptic symptoms were evaluated by esophago-gastro-duodenoscopy (EGD) in King Khalid University Hospital in Riyadh, Kingdom of Saudi Arabia from May through to June 1997. Endoscopic biopsies and histology as well as culture and serology for H.pylori were obtained. In patients with confirmed H.pylori a further analysis was performed looking at associated (CAD) or known risk factors for CAD. RESULTS: Among the 158 patients who underwent EGD, 143 patients (90.5%) were found to have H.pylori either by culture, histology or serology, or both in a percentage of (31.5%) (77.6%) and (60.8%). There was no evidence of CAD in this group of patients based on history, electrocardiogram (ECG), echocardiography, ECG stress test, dypiridamole thallium scan or coronary angiography. Other known risk factors for CAD were cigarette smoking (12.6%), diabetes mellitus (10.5%), hypertension (1.4%) and hyperlipidemia (2.8%). CONCLUSION: Helicobacter pylori infection does not increase the risk of CAD, and should not be considered as an independent risk factor for CAD. Further, prospective large trial is needed to confirm our finding.