Cryptococcal Pneumonia in a Patient on Tyrosine Kinase Inhibitor Therapy: How Common Is It?

Cryptococcal pneumonia is identified as a fungal infection of the lungs, with Cryptococcus neoformans and Cryptococcus gattii as the most common culprits. Cryptococcus neoformans primarily affects immunocompromised individuals while Cryptococcus gattii infections occur mostly in immunocompetent hosts. We present a 76-year-old male on ibrutinib due to a history of chronic lymphocytic leukemia who had multiple hospitalizations for pneumonia and was later diagnosed with cryptococcal pneumonia through positive bronchoalveolar lavage fungal culture and lymph node biopsy.

Deep Learning Classification of Tuberculosis Chest X-rays.

Background Tuberculosis (TB) is an infectious disease caused by the bacterium Mycobacterium tuberculosis. It primarily affects the lungs but can also affect other organs, such as the kidneys, bones, and brain. TB is transmitted through the air when an infected individual coughs, sneezes, or speaks, releasing tiny droplets containing the bacteria. Despite significant efforts to combat TB, challenges such as drug resistance, co-infection with human immunodeficiency virus (HIV), and limited resources in high-burden settings continue to pose obstacles to its eradication. TB remains a significant global health challenge, necessitating accurate and timely detection for effective management.  Methods This study aimed to develop a TB detection model using chest X-ray images obtained from Kaggle.com, utilizing Google's Collaboration Platform. Over 1196 chest X-ray images, comprising both TB-positive and normal cases, were employed for model development. The model was trained to recognize patterns within the TB chest X-rays to efficiently recognize TB within patients in order to be treated in time. Results The model achieved an average precision of 0.934, with precision and recall values of 94.1% each, indicating its high accuracy in classifying TB-positive and normal cases. Sensitivity and specificity values were calculated as 96.85% and 91.49%, respectively. The F1 score was also calculated to be 0.941. The overall accuracy of the model was found to be 94%.  Conclusion These results highlight the potential of machine learning algorithms for TB detection using chest X-ray images. Further validation studies and research efforts are needed to assess the model's generalizability and integration into clinical practice, ultimately facilitating early detection and improved management of TB.

Pneumoperitoneum in a Patient With COVID-19 and Acute Respiratory Distress Syndrome Without Pneumothorax.

We present a case report of pneumoperitoneum, pneumomediastinum, and subcutaneous emphysema in a patient with COVID-19 pneumonia-causing acute respiratory distress syndrome (ARDS) without any pneumothorax occurring. Pneumothorax, pneumomediastinum, and subcutaneous emphysema are known complications of barotrauma due to positive pressure from mechanical ventilation which is necessary for patients suffering from a severe case of COVID-19. In our literature search, we could not find any reported case of pneumoperitoneum without pneumothorax occurring. Our case is an important addition to the literature presenting a rare complication of mechanical ventilation in patients with ARDS.

Incidence of Barotrauma in COVID-19 Patients Requiring Mechanical Ventilation: A Retrospective Study in a Community Hospital.

Background and aim Acute respiratory distress syndrome (ARDS) is a severe complication of COVID-19 and traditional ventilation strategies using ARDSNet protocol, including low tidal volumes, appear to cause barotrauma in COVID-19 patients at a higher rate than non-COVID-19 ARDS patients. The purpose of our study was to determine if COVID-19 patients with ARDS undergoing mechanical ventilation at St. Joseph's Medical Center (SJMC) developed barotrauma at a higher rate than non-COVID-19 ARDS patients. Methods and materials This study was a retrospective chart review of all patients admitted to critical care units at SJMC with COVID-19 infection and requiring mechanical ventilation from March 1, 2020 to September 30, 2020. The sample included adult patients (aged 18 and above) with the International Classification of Diseases (ICD) 10 code for COVID-19 (U07.1) and patients who were placed on mechanical ventilation for longer than 24 hours, from March 1, 2020 to September 30, 2020. Barotrauma was confirmed via radiographic imaging including chest X-ray, CT, or CT angiography (CTA).  Results One hundred and forty COVID-19 patients underwent mechanical ventilation for longer than 24 hours from March 1, 2020 to September 30, 2020 at our facility. Twenty-six COVID-19 patients (18.6%) met our inclusion criteria (development of barotrauma during hospital admission) of which 25 patients (17.9%) underwent mechanical (invasive and/or non-invasive) ventilation prior to the development of barotrauma. Around 80% of the patients were on non-invasive mechanical ventilation prior to intubation and invasive mechanical ventilation. The categorical breakdown of barotrauma was as follows: pneumothorax 65.4%, subcutaneous emphysema 61.5%, pneumomediastinum 34.6%, and pneumoperitoneum 7.7%. None of the included patients had any previous history of documented barotrauma. Prior to the time of barotrauma, 17 patients were on volume control, seven were on pressure control, and one was not on mechanical ventilation. Of the 17 patients on volume control, only one patient was above the ARDSNet guideline of 6-8 mL/kg ideal body weight (IBW). In comparison to ARDS patients at SJMC in 2019, only two out of 28 patients (7.14%) developed barotrauma during mechanical ventilation.  Conclusions Patients with COVID-19 who underwent mechanical ventilation developed barotrauma at a higher rate than traditional non-COVID-19 patients with ARDS.