Our lab is focused on defining the diagnosis, prevention and treatment strategies for respiratory syncytial virus (RSV), influenza, and other respiratory viruses. RSV is the most important cause of viral pneumonia in infants worldwide, for which no vaccine or effective treatment is currently available. The lab is also working to develop neutralizing antibody assays to analyze serum and breast milk and evaluate the role of humoral and cellular immunity in protection against respiratory viruses in pregnant women and infants. The lab has additionally developed sequencing techniques to identify patterns of viral transmission in nosocomial and community-based settings. Using these techniques, our group has described transmission patterns of RSV, rhinovirus, and human metapneumovirus, the epidemiology and adverse birth outcomes associated with respiratory viral pneumonia in pregnant women, and the kinetics of transplacental RSV antibody transfer and decay in infants.
Aside from protecting your pearly whites, here's more motivation to squeeze in that twice-a-year teeth cleaning: It could keep you from getting sick. A new study suggests that regular dental visits may protect against pneumonia by reducing levels of harmful bacteria in the mouth (ick). The study's findings--based on the health records of more than 26,000 people nationwide--suggest that people who never get dental checkups have a far greater risk of getting bacterial pneumonia than those who keep up with biannual visits. "There is a well-documented connection between oral health and pneumonia," said lead author Michelle Doll, MD, assistant professor of internal medicine at Virginia Commonwealth University, in a press release. "We can never rid the mouth of bacteria altogether, but good oral hygiene can limit the quantities of bacteria present."
A new antibiotic developed to fight'superbug' lung infections could be used to treat ventilator-associated pneumonia in COVID-19 patients, a study has suggested. Researchers have shown that the drug can successfully combat potentially fatal lung infections in both mice, as well as human cells grown in the laboratory. The medication could help to extend the lives of cystic fibrosis sufferers, who are vulnerable to infections that affect their breathing. It also offers the hope of potentially slashing deaths rates from the coronavirus by stopping secondary infections from colonising a patient's airways. This is a particular problem for critically ill patients on ventilators -- who are especially prone to developing pneumonia.
This article is to set up the framework with a simple model with a detailed walk through of each step. There are tons of improvements that can be made to boost model performance! In the world of healthcare, one of the major issues that medical professionals face is the correct diagnosis of conditions and diseases of patients. Not being able to correctly diagnose a condition is a problem for both the patient and the doctor. The doctor is not benefiting the patient in the appropriate way if the doctor misdiagnoses the patient.
We demonstrate use of iteratively pruned deep learning model ensembles for detecting pulmonary manifestation of COVID-19 with chest X-rays. This disease is caused by the novel Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) virus, also known as the novel Coronavirus (2019-nCoV). A custom convolutional neural network and a selection of ImageNet pretrained models are trained and evaluated at patient-level on publicly available CXR collections to learn modality-specific feature representations. The learned knowledge is transferred and fine-tuned to improve performance and generalization in the related task of classifying CXRs as normal, showing bacterial pneumonia, or COVID-19-viral abnormalities. The best performing models are iteratively pruned to reduce complexity and improve memory efficiency. The predictions of the best-performing pruned models are combined through different ensemble strategies to improve classification performance. Empirical evaluations demonstrate that the weighted average of the best-performing pruned models significantly improves performance resulting in an accuracy of 99.01% and area under the curve of 0.9972 in detecting COVID-19 findings on CXRs. The combined use of modality-specific knowledge transfer, iterative model pruning, and ensemble learning resulted in improved predictions. We expect that this model can be quickly adopted for COVID-19 screening using chest radiographs.