Sepsis is a major cause of mortality among hospitalized patients worldwide. Shorter time to administration of broad-spectrum antibiotics is associated with improved outcomes, but early recognition of sepsis remains a major challenge. In a two-center cohort study with prospective sample collection from 1400 adult patients in emergency departments suspected of sepsis, we sought to determine the diagnostic and prognostic capabilities of a machine-learning algorithm based on clinical data and a set of uncommonly measured biomarkers. Specifically, we demonstrate that a machine-learning model developed using this dataset outputs a score with not only diagnostic capability but also prognostic power with respect to hospital length of stay (LOS), thirty-day mortality, and thirty-day inpatient readmission both in our entire testing cohort and various subpopulations. The area under the Receiver Operating Curve (AUROC) for diagnosis of sepsis was 0.83. Predicted risk scores for patients with septic shock were higher compared to patients with sepsis but without shock (p < 0.0001). Scores for patients with infection and organ dysfunction were higher compared to those without either condition (p < 0.0001). Stratification based on predicted scores of the patients into low, medium and high-risk groups showed significant differences in length of stay (p < 0.0001), thirty-day mortality (p < 0.0001), and thirty-day inpatient readmission (p < 0.0001). In conclusion, a machine-learning algorithm based on EMR data and three non-routinely measured biomarkers demonstrated good diagnostic and prognostic capability at the time of initial blood culture.
Introduction Lower respiratory tract anomalies are not commonly encountered in clinical practice, specifically with regards to adult medicine. Bronchogenic cysts, in particular, are rare anomalies that may present as a diagnostic challenge for most clinicians, especially if the patient is asymptomatic. Furthermore, presenting symptoms are often non-specific, and imaging may be misleading. Historically, gold standard for diagnosis requires surgical resection and pathological evaluation. However, there may be a role for bronchoscopy and endobronchial ultrasound (EBUS) with transbronchial needle aspiration (TBNA) in the diagnosis and, potentially, treatment of bronchogenic cysts. Case Description The patient was referred to pulmonary for abnormal imaging. A computed tomography scan of the chest revealed a mediastinal mass that was initially concerning for malignancy. After undergoing bronchoscopy with EBUS, it was determined based on ultrasound that the lesion in question was in fact cystic in nature. Furthermore, TBNA of the lesion yielded serous fluid and resulted in shrinkage of the lesion. Discussion There are several peer-reviewed, published case reports detailing the use of bronchoscopy with EBUS-TBNA to aid in diagnosis of bronchogenic cysts. The obvious advantage of this method is potentially avoiding unnecessary surgery. However, there are also case reports detailing potentially fatal adverse events from performing needle aspiration of bronchogenic cysts, the most devastating being mediastinitis. Further data is needed regarding the utility and safety of bronchoscopy with EBUS-TBNA in diagnosing and managing bronchogenic cysts.
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.