Explicable AI for surveillance and interpretation of Coronavirus using X-ray imaging

Explainable AI (XAI) is one of the disciplines being investigated, with the goal of improving the transparency of black-box systems. XAI is such a technology that could assist to alleviate the black-box system by providing new ways of understanding the core thinking process of AI systems. Conside ring the healthcare domain, doctors are still not able to explain why certain decisions or forecasts had been predicted by a particular system. As a result, it imposes limitations on how and where AI technology can be implemented. And to address this problem, a taxonomy of model interpretability is framed for conceptualizing the explainability. Also, an approach with the baseline system is created which could firstly differentiate in the Covid-19 positive and Covid-19 negative chest X-ray images and an automated explainable pipeline is designed using XAI technique. This technique shows that the model is interpretable, that is the achieved results are easy to understand and can encourage medicians and patients with transparent and reliable medical journey. This article aims to help people comprehend the necessity for Explainable AI, as well as the methodological approaches used in healthcare. © 2023 IEEE.

CX-R Classification Using DCNN Method

The virus SARS-CoV2 was identified in late 2019. Coronavirus Disease 2019 (COVID-19) is still a threat to global health and safety. Deep Learning (DL) is anticipated to be the most excellent strategy for reliably predicting COVID-19. Convolutional Neural Networks(CNNs) have achieved successful outcomes particularly in categorization and analyzing of medical image data. This work proposes a Deep CNN(DCNN) method for the classification of CX-R(Chest X-Ray) images in prediction of COVID-19. The dataset is preprocessed under many phases with different techniques for creating effective training dataset for the DCNN model to achieve best performance. This is done to deal various complexities like availability of very small sized imbalanced dataset with quality issues. In the first instance, model is trained using the train dataset. Then the model is tested for a separate validate X-ray image dataset and Confusion matrix is displayed. Up to 98.3% Accuracy is obtained, when proposed model was tested using the validate dataset. The Accuracy and Loss graph is plotted for the same. Later, random image prediction is made from prediction dataset which include both COVID and Normal X-rays. Other important performance metrics like F1 score, Recall, Precision for the model is displayed. © 2023 IEEE.

COVID-LiteNet: A lightweight CNN based network for COVID-19 detection using X-ray images

To restrict the virus's transmission in the pandemic and lessen the strain on the healthcare industry, computer-assisted diagnostics for the accurate and speedy diagnosis of coronavirus illness (COVID-19) has become a prerequisite. Compared to other types of imaging and detection, chest X-ray imaging (CXR) provides several advantages. Healthcare practitioners may profit from any technology instrument providing quick and accurate COVID-19 infection detection. COVID-LiteNet is a technique suggested in this paper that combines white balance with Contrast Limited Adaptive Histogram Equalization (CLAHE) and a convolutional neural network (CNN). White balance is employed as an image pre-processing step in this approach, followed by CLAHE, to improve the visibility of CXR images, and CNN is trained using sparse categorical cross-entropy for image classification tasks and gives the smaller parameters file size, i.e., 2.24 MB. The suggested COVID-LiteNet technique produced better results than vanilla CNN with no pre-processing. The proposed approach outperformed several state-of-the-art methods with a binary classification accuracy of 98.44 percent and a multi-class classification accuracy of 97.50 percent. COVID-LiteNet, the suggested technique, outperformed the competition on various performance parameters. COVID-LiteNet may help radiologists discover COVID-19 patients from CXR pictures by providing thorough model interpretations, cutting diagnostic time significantly. © 2023 IEEE.

Utility of the Brixia CXR score, C-Reactive Protein and Absolute Neutrophil Count in Predicting the Need for Invasive Mechanical Ventilation, Length of Hospital Stay, and Mortality in Moderate to Severe COVID-19 Patients

Background: The Brixia Chest X-ray (CXR) score, C-reactive protein (CRP), and the absolute neutrophil count (ANC) have been useful to predict outcomes in Coronavirus disease 2019 (COVID-19 patients). We studied the utility of the Brixia CXR score, CRP, and ANC in predicting the outcomes in terms of the need for invasive mechanical ventilation, length of stay, and mortality in moderate-severe COVID-19 patients. Material(s) and Method(s): This was a single-centre, retrospective, study on 122 COVID-19 patients. Brixia CXR score, CRP, and ANC on admission to the hospital and the fifth day of hospital stay were noted along with the need for invasive mechanical ventilation (IMV), prolonged length of stay (LOS) >= 14 days, and mortality. Result(s): 122 patients were included for analysis. The median and interquartile range (IQR) for baseline CRP was 81.50 (39-151) mg/L and 11.0 (4-30) mg/L (p < 0.001) on the fifth day. The median and IQR for baseline Brixia score was 10.0 (7-13), and on the fifth day was 7 (4-11) (p <0.001). The receiver operating characteristic curve (ROC) showed that the baseline CRP >= 52.5mg/L predicted both the need for IMV, with an area under the curve (AUC) of 0.628, and prolonged LOS with an AUC of 0.608. The ROC curve depicted that the baseline ANC >8500/muL predicted IMV requirement with an AUC of 0.657. The fifth day CRP >= 32 mg/L, ANC >= 11,000/ muL and Brixia CXR score >= 7 predicted a higher mortality in hospitalized patients. Conclusion(s): Baseline CRP (> 52.5mg/L) predicts the need for IMV and a prolonged LOS, but not mortality. Baseline ANC (> 8500/muL) predicted the need for IMV. CRP, Brixia CXR score, and ANC on the fifth day were not useful to predict LOS or mortality, though there was a significant reduction in CRP and Brixia CXR score on the fifth day compared to baseline after treatment. The fifth day CRP >= 32 mg/L, ANC >= 11,000/ muL and Brixia CXR score >= 7 predicted a higher mortality.Copyright © 2023, College of Anaesthesiologists of Sri Lanka. All rights reserved.

Deep learning model for binary classification of COVID-19 based on Chest X-Ray

COVID-19 is a novel virus infecting the upper respiratory tract and lungs. On a scale of the global pandemic, the number of cases and deaths had been increasing each day. Chest X-ray (CXR) images proved effective in monitoring a variety of lung illnesses, including the COVID-19 disease. In recent years, deep learning (DL) has become one of the most significant topics in the computing world and has been extensively applied in several medical applications. In terms of automatic diagnosis of COVID-19, those approaches had proven to be very effective. In this research, a DL technology based on convolution neural networks (CNN) models had been implemented with less number of layers with tuning parameters that will take less time for training for binary classification of COVID-19 based on CXR images. Experimental results had shown that the proposed model for training had achieved an accuracy of 96.68%, Recall of 94.12%, Precision of 93.49%, Specificity of 97.61%, and F1 Score of 93.8%. Those results had shown the high value of utilizing DL for early COVID-19 diagnosis, which can be utilized as a useful tool for COVID-19 screening. © 2023 IEEE.

Probiotic improves symptomatic and viral clearance in Covid19 outpatients: a randomized, quadruple-blinded, placebo-controlled trial.

Intestinal bacteria may influence lung homeostasis via the gut-lung axis. We conducted a single-center, quadruple-blinded, randomized trial in adult symptomatic Coronavirus Disease 2019 (Covid19) outpatients. Subjects were allocated 1:1 to probiotic formula (strains Lactiplantibacillus plantarum KABP022, KABP023, and KAPB033, plus strain Pediococcus acidilactici KABP021, totaling 2 × 109 colony-forming units (CFU)) or placebo, for 30 days. Co-primary endpoints included: i) proportion of patients in complete symptomatic and viral remission; ii) proportion progressing to moderate or severe disease with hospitalization, or death; and iii) days on Intensive Care Unit (ICU). Three hundred subjects were randomized (median age 37.0 years [range 18 to 60], 161 [53.7%] women, 126 [42.0%] having known metabolic risk factors), and 293 completed the study (97.7%). Complete remission was achieved by 78 of 147 (53.1%) in probiotic group compared to 41 of 146 (28.1%) in placebo (RR: 1.89 [95 CI 1.40-2.55]; P < .001), significant after multiplicity correction. No hospitalizations or deaths occurred during the study, precluding the assessment of remaining co-primary outcomes. Probiotic supplementation was well-tolerated and reduced nasopharyngeal viral load, lung infiltrates and duration of both digestive and non-digestive symptoms, compared to placebo. No significant compositional changes were detected in fecal microbiota between probiotic and placebo, but probiotic supplementation significantly increased specific IgM and IgG against Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV2) compared to placebo. It is thus hypothesized this probiotic primarily acts by interacting with the host's immune system rather than changing colonic microbiota composition. Future studies should replicate these findings and elucidate its mechanism of action (Registration: NCT04517422).Abbreviations: AE: Adverse Event; BMI: Body Mass Index; CONSORT: CONsolidated Standards of Reporting Trials; CFU: Colony-Forming Units; eDRF: Electronic Daily Report Form; GLA: Gut-Lung Axis; GSRS: Gastrointestinal Symptoms Rating Scale; hsCRP: High-sensitivity C-Reactive Protein; HR: Hazard Ratio; ICU: Intensive Care Unit; OR: Odds Ratio; PCoA: Principal Coordinate Analysis; RR: Relative Risk; RT-qPCR: Real-Time Quantitative Polymerase Chain Reaction; SARS-CoV2: Severe acute respiratory syndrome coronavirus 2; SpO2: Peripheral Oxygen Saturation; WHO: World Health Organization.

A Rare Manifestation of Unknown Hyperparathyroidism as a Perforated Peptic Ulcer.

Hypercalcemia is a common electrolyte abnormality with different causes. Hypercalcemia is most often associated with malignancy and primary hyperparathyroidism and malignancy together account for most cases. Primary hyperparathyroidism manifests as hypercalcemia owing to the overproduction of parathyroid hormone. In most cases, primary hyperparathyroidism manifests due to a solitary parathyroid adenoma. Based on calcium levels, hypercalcemia can be classified as mild, moderate, and severe. Hypercalcemia typically presents with non-specific clinical features. Here, we present the case of a 38-year-old male patient who presented to the emergency department (ED) with acute abdominal pain and a tender abdomen with absent bowel sounds. He had chest radiography and blood tests initially. Chest radiography showed left-sided pneumoperitoneum, and the patient was suspected to have a perforated peptic ulcer due to hypercalcemia secondary to a parathyroid adenoma during the second wave of the coronavirus disease 2019 (COVID-19) pandemic. The findings were confirmed by a computerized tomography scan of the abdomen, and the patient was treated with intravenous fluids for hypercalcemia and was managed conservatively for a sealed perforated peptic ulcer following discussion in the multi-disciplinary team meeting (MDT). The COVID-19 pandemic led to a long waiting list and delays in the timely management of patients requiring elective surgical intervention, such as parathyroidectomy. The patient made a complete recovery and had parathyroidectomy of the inferior right lobe two months later.

Deep learning approach for early prediction of COVID-19 mortality using chest X-ray and electronic health records.

BACKGROUND: An artificial-intelligence (AI) model for predicting the prognosis or mortality of coronavirus disease 2019 (COVID-19) patients will allow efficient allocation of limited medical resources. We developed an early mortality prediction ensemble model for COVID-19 using AI models with initial chest X-ray and electronic health record (EHR) data. RESULTS: We used convolutional neural network (CNN) models (Inception-ResNet-V2 and EfficientNet) for chest X-ray analysis and multilayer perceptron (MLP), Extreme Gradient Boosting (XGBoost), and random forest (RF) models for EHR data analysis. The Gradient-weighted Class Activation Mapping and Shapley Additive Explanations (SHAP) methods were used to determine the effects of these features on COVID-19. We developed an ensemble model (Area under the receiver operating characteristic curve of 0.8698) using a soft voting method with weight differences for CNN, XGBoost, MLP, and RF models. To resolve the data imbalance, we conducted F1-score optimization by adjusting the cutoff values to optimize the model performance (F1 score of 0.77). CONCLUSIONS: Our study is meaningful in that we developed an early mortality prediction model using only the initial chest X-ray and EHR data of COVID-19 patients. Early prediction of the clinical courses of patients is helpful for not only treatment but also bed management. Our results confirmed the performance improvement of the ensemble model achieved by combining AI models. Through the SHAP method, laboratory tests that indicate the factors affecting COVID-19 mortality were discovered, highlighting the importance of these tests in managing COVID-19 patients.

A Real Time Method for Distinguishing COVID-19 Utilizing 2D-CNN and Transfer Learning.

Rapid identification of COVID-19 can assist in making decisions for effective treatment and epidemic prevention. The PCR-based test is expert-dependent, is time-consuming, and has limited sensitivity. By inspecting Chest R-ray (CXR) images, COVID-19, pneumonia, and other lung infections can be detected in real time. The current, state-of-the-art literature suggests that deep learning (DL) is highly advantageous in automatic disease classification utilizing the CXR images. The goal of this study is to develop models by employing DL models for identifying COVID-19 and other lung disorders more efficiently. For this study, a dataset of 18,564 CXR images with seven disease categories was created from multiple publicly available sources. Four DL architectures including the proposed CNN model and pretrained VGG-16, VGG-19, and Inception-v3 models were applied to identify healthy and six lung diseases (fibrosis, lung opacity, viral pneumonia, bacterial pneumonia, COVID-19, and tuberculosis). Accuracy, precision, recall, f1 score, area under the curve (AUC), and testing time were used to evaluate the performance of these four models. The results demonstrated that the proposed CNN model outperformed all other DL models employed for a seven-class classification with an accuracy of 93.15% and average values for precision, recall, f1-score, and AUC of 0.9343, 0.9443, 0.9386, and 0.9939. The CNN model equally performed well when other multiclass classifications including normal and COVID-19 as the common classes were considered, yielding accuracy values of 98%, 97.49%, 97.81%, 96%, and 96.75% for two, three, four, five, and six classes, respectively. The proposed model can also identify COVID-19 with shorter training and testing times compared to other transfer learning models.