Background: Whether the sensitivity of Deep Learning (DL) models to screen chest radiographs (CXR) for CoVID-19 can approximate that of radiologists, so that they can be adopted and used if real-time review of CXRs by radiologists is not possible, has not been explored before. Objective: To evaluate the diagnostic performance of a doctor-trained DL model (Svita_DL8) to screen for COVID-19 on CXR, and to compare the performance of the DL model with that of expert radiologists. Materials and Methods: We used a pre-trained convolutional neural network to develop a publicly available online DL model to evaluate CXR examinations saved in .jpeg or .png format. The initial model was subsequently curated and trained by an internist and a radiologist using 1062 chest radiographs to classify a submitted CXR as either normal, COVID-19, or a non-COVID-19 abnormal. For validation, we collected a separate set of 430 CXR examinations from numerous publicly available datasets from 10 different countries, case presentations, and two hospital repositories. These examinations were assessed for COVID-19 by the DL model and by two independent radiologists. Diagnostic performance was compared between the model and the radiologists and the correlation coefficient calculated. Results: For detecting COVID-19 on CXR, our DL model demonstrated sensitivity of 91.5%, specificity of 55.3%, PPV 60.9%, NPV 77.9%, accuracy 70.1%, and AUC 0.73 (95% CI: 0.86, 0.95). There was a significant correlation (r = 0.617, P = 0.000) between the results of the DL model and the radiologists’ interpretations. The sensitivity of the radiologists is 96% and their overall diagnostic accuracy is 90% in this study. Conclusions: The DL model demonstrated high sensitivity for detecting COVID-19 on CXR. Clinical Impact: The doctor trained DL tool Svita_DL8 can be used in resource-constrained settings to quickly triage patients with suspected COVID-19 for further in-depth review and testing.
Chronic obstructive pulmonary disease (COPD) is a chronic illness that is widely prevalent within the United States and has been frequently associated with heart failure (HF). COPD is associated with progressive damage and inflammation of the airways leading to airflow obstruction and inadequate gas exchange. HF represents a decline in the normal functioning of the heart resulting in insufficient pumping of blood through the circulatory system. COPD and HF present with similar signs and symptoms with some variation. There are many specific diagnostic tests and treatment modalities which we use to diagnose COPD and HF, but it becomes an issue when you come across a patient who has both conditions simultaneously. For example, attempting to use an X-ray to diagnose HF in a COPD patient is next to impossible because the results are manipulated by the COPD disease process. This is the case with many other diagnostic tests such as an electrocardiogram (ECG), chest radiography (X-ray), B-type natriuretic peptide (BNP), echocardiogram, cardiac magnetic resonance imaging (CMR), pulmonary function test (PFT), arterial blood gas (ABG), and exercise stress testing. When a patient has both COPD and HF, it becomes more difficult to treat. Many treatments for HF have negative impacts on COPD patients and vice-versa, whereas some have also shown positive clinical outcomes in both diseases. It is agreeable that treatment has to be patient-centered and it can vary from case to case depending on the severity of the disease. Ultimately, in this review, we discuss COPD and HF and how they interplay in their diagnostic and treatment modalities to gain a better understanding of how to effectively manage patients who have been diagnosed with both conditions.
Background: Cerebrovascular accident (also known as stroke) is a leading cause of mortality and morbidity in India. Renal dysfunction may be associated with increased recurrence of stroke and poorer long-term outcomes. Aims and Objectives: a) To find the relationship between CKD and occurrence of acute stroke b) To estimate the incidence of AKI in patients admitted with acute ischemic and hemorrhagic stroke. Materials and Methods: This is a retrospective analysis of renal function in patients admitted in K.V.G. Medical College Hospital with the diagnosis of “Acute stroke.” All patients admitted in Medical Intensive Care Unit (M-ICU) and general wards from 1st November 2018 to 31st March 2020 were included in the study. Results: In this study, we included 80 patients who were admitted with the diagnosis of acute stroke. Sixty-four patients (80%) had ischemic stroke and remaining sixteen (20%) had haemorrhagic stroke. Twenty-eight patients (35%) had renal dysfunction. The distribution of different types of renal dysfunction among different types of stroke was statistically insignificant (p value = 0.529). Incidence of acute kidney injury (AKI) in our study is 25%. 12 patients (15%) were found to have chronic kidney disease (CKD). The prevalence of CKD varies from 20 to 35% in ischemic stroke and 20 to 46% in haemorrhagic stroke. Conclusion: Renal dysfunction occurs frequently in patients with stroke. There was a significant proportion of patients with renal dysfunction. However, further prospective cohort studies are needed to find out the effect of renal dysfunction on stroke recovery and mortality.
Spontaneous pneumomediastinum (SPM) is a relatively rare presentation that often follows a benign clinical course. It is mainly triggered by underlying bronchial asthma, respiratory tract infections, strenuous activities, or illicit drug use. We present a case of an isolated primary pneumomediastinum where the patient was a 24-year-old man with underlying bronchial asthma who presented with acute onset of shortness of breath and pleuritic chest pain following snorting of an opioid-heroin. Although the clinical exam and chest radiograph were both unremarkable, the multi-detector computed tomography of the chest revealed an isolated pneumomediastinum. The patient was managed conservatively in accordance with existing evidence as SPM is known for its spontaneous recovery.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.