Lan Dao

BACKGROUND We aimed to evaluate the feasibility of implementing Chester, a novel web-based chest X-ray (CXR) interpretation artificial intelligence (AI) tool, in the medical education curriculum and explore its effect on the diagnostic performance of undergraduate medical students. METHODS Third-year trainees were randomized in experimental (N=16) and control (N=16) groups and stratified for age, gender, confidence in CXR interpretation, and prior experience. Participants filled a pre-intervention survey, a test exam (Exam1), a final exam (Exam2), and a post-intervention survey. The experimental group was allowed to use Chester during Exam1 while the control group could not. All participants were forbidden from using any resources during Exam2. The diagnostic interpretation of a fellowship-trained chest radiologist was used as the standard of reference. Chester’s performance on Exam1 was 60%. A five-point Likert scale was used to assess students’ perceived confidence before/after the exams as well as Chester’s perceived usefulness. RESULTS Using a mixed model for repeated measures (MMRM), it was found that Chester did not have a statistically significant impact on the experimental group’s diagnostic performance nor confidence level when compared to the control group. The experimental group rated Chester’s usefulness at 3.7/5, its convenience at 4.25/5, and their likelihood to reuse it at 4.1/5. CONCLUSION Our experience highlights the interest of medical students in using AI tools as educational resources. While the results of the pilot project are inconclusive for now, they demonstrate proof of concept for a repeat experiment with a larger sample and establish a robust methodology to evaluate AI tools in radiological education. Finally, we believe that additional research should be focused on the applications of AI in medical education so students understand this new technology for themselves and given the growing trend of remote learning.

Across the world's coronavirus disease 2019 (COVID-19) hot spots, the need to streamline patient diagnosis and management has become more pressing than ever. As one of the main imaging tools, chest X-rays (CXRs) are common, fast, non-invasive, relatively cheap, and potentially bedside to monitor the progression of the disease. This paper describes the first public COVID-19 image data collection as well as a preliminary exploration of possible use cases for the data. This dataset currently contains hundreds of frontal view X-rays and is the largest public resource for COVID-19 image and prognostic data, making it a necessary resource to develop and evaluate tools to aid in the treatment of COVID-19. It was manually aggregated from publication figures as well as various web based repositories into a machine learning (ML) friendly format with accompanying dataloader code. We collected frontal and lateral view imagery and metadata such as the time since first symptoms, intensive care unit (ICU) status, survival status, intubation status, or hospital location. We present multiple possible use cases for the data such as predicting the need for the ICU, predicting patient survival, and understanding a patient's trajectory during treatment. Data can be accessed here: https://github.com/ieee8023/covid-chestxray-dataset

Across the world’s coronavirus disease 2019 (COVID-19) hot spots, the need to streamline patient diagnosis and management has become more pressing than ever. As one of the main imaging tools, chest X-rays (CXRs) are common, fast, non-invasive, relatively cheap, and potentially bedside to monitor the progression of the disease. This paper describes the first public COVID-19 image data collection as well as a preliminary exploration of possible use cases for the data. This dataset currently contains hundreds of frontal view X-rays and is the largest public resource for COVID-19 image and prognostic data, making it a necessary resource to develop and evaluate tools to aid in the treatment of COVID-19. It was manually aggregated from publication figures as well as various web based repositories into a machine learning (ML) friendly format with accompanying dataloader code. We collected frontal and lateral view imagery and metadata such as the time since first symptoms, intensive care unit (ICU) status, survival status, intubation status, or hospital location. We present multiple possible use cases for the data such as predicting the need for the ICU, predicting patient survival, and understanding a patient’s trajectory during treatment. Data can be accessed here: https://github.com/ieee8023/covid-chestxray-dataset

Summary: Acellular dermal matrices have become a mandatory tool in reconstructive breast surgery. Since their introduction, they have been considered to be nonreactive and nonimmunogenic scaffolds. However, some patients who undergo implant-based breast reconstruction with acellular dermal matrices develop postoperative cutaneous erythema overlying their matrices, a condition commonly referred to as red breast syndrome. The aim of this study was to gain a better understanding of this phenomenon. An analysis was conducted on consecutive patients who underwent acellular dermal matrix– and implant-based breast reconstructions and developed red breast syndrome that was treated surgically between April of 2017 and June of 2018 at the authors’ institution. During surgery, 1-cm² specimens of acellular dermal matrix were sampled and analyzed by scanning electron microscopy. Observations were charted to score and record the presence and thickness of biofilm, and for identification of bacteria. These measurements were performed using Adobe Photoshop CS6 Extended software. Six postmastectomy breast reconstruction patients were included, all with AlloDerm Ready-to-Use–based reconstructions. All specimens were colonized by various bacteria ranging from Gram-negative bacilli to Gram-positive microorganisms. Biofilm was present in all studied specimens. The cause of skin erythema overlying acellular dermal matrix grafts, and the so-called red breast syndrome, may be related to contamination with various bacteria. Although contamination was omnipresent in analyzed samples, its clinical significance is variable. Even if acellular dermal matrix–based reconstructions are salvaged, this could come at the price of chronic local inflammation.