No abstract

Pneumonia is common in the intensive care unit (ICU), infecting 27% of all critically ill patients. Given the high prevalence of this disease state in the ICU, optimizing antimicrobial therapy while minimizing toxicities is of utmost importance. Inappropriate antimicrobial use can increase the risk of antimicrobial resistance, Clostridiodes difficile infection, allergic reaction, and other complications from antimicrobial use (e.g., QTc prolongation, thrombocytopenia). This review article aims to discuss methods to optimize antimicrobial treatment in patients with pneumonia, including the following: procalcitonin use, utilization of methicillin-resistant Staphylococcus aureus nares testing to determine need for vancomycin therapy, utilization of the Biofire® FilmArray® pneumonia polymerase chain reaction (PCR), and microbiology reporting techniques.

Patients diagnosed with acute pulmonary embolism (PE) are at an elevated risk for short-term mortality. An accurate prognostic model is important in guiding appropriate management. We aimed to use machine learning (ML) to predict 30-day all-cause mortality in patients diagnosed with acute PE. METHODS: 439 patients (48% men, 61AE15 years) diagnosed with acute PE at our institution were retrospectively analyzed. We included 101 variables from a range of domains including demographics, clinical, laboratory, echocardiographic, and CT imaging as candidate predictors. Machine learning algorithms including extreme gradient boosting (XGBoost), gradient boosting machine (GBM), random forest (RF), deep neural networks (DNN), and generalized linear models (GML) were evaluated on their classification performance and validated with 5-fold cross-validation. The PE severity index (PESI) and its simplified version (sPESI) were used as reference models. RESULTS: XGBoost was the best performing model in predicting 30-day all-cause mortality (AUC, 0.922 (95% confidence interval [

D-cycloserine (DCS) is an anti-tuberculosis medication that has been utilized for years for drug-resistant tuberculosis. DCS works via a centrally acting mechanism which can cause neurotoxic adverse effects which has limited its use. This centrally acting mechanism also allows for DCS to be utilized for various neuropsychiatric purposes. Our patient was on high-dose DCS for autism spectrum disorder and presented to the emergency department (ED) with a seizure. The seizure episode was managed with both anti-epileptics and pyridoxine. With increasing novel use of this older medication, it is imperative for ED clinicians to be aware of the different management strategies that may be required when a patient presents with a neurotoxic effect, specifically seizures, secondary to DCS.

No abstract