Assuntos
Linfoma Difuso de Grandes Células B , Neoplasias do Mediastino , Neoplasias do Timo , Adulto , Humanos , Linfoma Difuso de Grandes Células B/diagnóstico por imagem , Linfoma Difuso de Grandes Células B/patologia , Neoplasias do Mediastino/diagnóstico por imagem , Neoplasias do Mediastino/patologiaRESUMO
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), 30-day mortality, and 3-day inpatient re-admission 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 with patients with sepsis but without shock (p < 0.0001). Scores for patients with infection and organ dysfunction were higher compared with 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 LOS (p < 0.0001), 30-day mortality (p < 0.0001), and 30-day inpatient readmission (p < 0.0001). In conclusion, a machine-learning algorithm based on electronic medical record (EMR) data and three nonroutinely measured biomarkers demonstrated good diagnostic and prognostic capability at the time of initial blood culture.
Assuntos
Diagnóstico Precoce , Registros Eletrônicos de Saúde/estatística & dados numéricos , Aprendizado de Máquina , Sepse/diagnóstico , Idoso , Área Sob a Curva , Biomarcadores/sangue , Serviço Hospitalar de Emergência/estatística & dados numéricos , Feminino , Mortalidade Hospitalar , Humanos , Tempo de Internação/estatística & dados numéricos , Masculino , Pessoa de Meia-Idade , Readmissão do Paciente/estatística & dados numéricos , Prognóstico , Estudos Prospectivos , Curva ROC , Sepse/sangue , Sepse/microbiologia , Sepse/mortalidadeRESUMO
We report a case of a 68-year-old woman who presented with atypical chest pain and fluctuating neurological symptoms 4 weeks after cryoballoon ablation procedure for atrial fibrillation. Brain imaging showed multiple embolic infarcts, while the chest imaging revealed an abnormal connection between the posterior wall of the left atrium and the oesophagus. Based on her clinical presentation and the imaging findings, a diagnosis of left atrio-oesophageal fistula (AOF) was established. AOF carries a high mortality rate unless an urgent surgical repair is performed. Oesophageal instrumentation for an echocardiogram or endoscopy should be avoided as it can result in massive air embolus, causing stroke or death.
