Search

PURPOSE: Patients with pneumonia often present to the emergency department and require prompt diagnosis and treatment. Clinical decision support systems for the diagnosis and management of pneumonia are commonly utilized in emergency departments to improve patient care. The purpose of this study is to investigate whether a deep learning model for detecting radiographic pneumonia and pleural effusions can improve functionality of a clinical decision support system for pneumonia management (ePNa) operating in 20 emergency departments. MATERIALS AND METHODS: In this retrospective cohort study, a dataset of 7,434 prior chest radiographic studies from 6,551 emergency department patients was used to develop and validate a deep learning model to identify radiographic pneumonia, pleural effusions, and evidence of multilobar pneumonia. Model performance was evaluated against three radiologists’ adjudicated interpretation and compared to performance of the natural language processing of radiology reports used by ePNa. RESULTS: The deep learning model achieved an area under the receiver operating characteristic curve of 0.833 (95% CI 0.795, 0.868) for detecting radiographic pneumonia, 0.939 (95% CI 0.911, 0.962) for detecting pleural effusions, and 0.847 (95% CI 0.800, 0.890) for identifying multilobar pneumonia. On all three tasks, the model achieved higher agreement with the adjudicated radiologist interpretation compared to ePNa. CONCLUSIONS: A deep learning model demonstrated higher agreement with radiologists than the ePNa clinical decision support system in detecting radiographic pneumonia and related findings. Incorporating deep learning models into pneumonia clinical decision support systems could enhance diagnostic performance and improve pneumonia management.

Our purpose is to describe aspiration pneumonia/pneumonitis as a spectrum of infectious/noninfectious diseases affecting the lung. We summarize diagnosis, risk factors, treatment, and strategies for prevention of aspiration.Aspiration is present in normal individuals, and disease manifestation depends on the chemical characteristics, frequency, and volume of inoculum. Anaerobes, though present, are no longer the predominant microbes isolated in aspiration pneumonia. Targets for preventing aspiration including improved oral hygiene and positional feeding have had mixed results. Patients diagnosed by clinicians with aspiration pneumonia experience greater morbidity and mortality than patients with community-acquired pneumonia.Aspiration pneumonia and pneumonitis are part of the pneumonia continuum and share similarities in pathophysiology, microbiology, and treatment. Modern microbiology demonstrates that the lung is not sterile, and isolates in aspiration pneumonia frequently include aerobes or mixed cultures. Treatment for aspiration pneumonia should include antibiotic coverage for oral anaerobes, aerobes associated with community-acquired pneumonia, and resistant organisms depending on appropriate clinical context. Additional studies targeting prevention of aspiration and investigating the increased morbidity and mortality associated with aspiration pneumonia are warranted.

The goal of this study was to determine the accuracy and the impact of 5 different claims-based pneumonia definitions. Three International Classification of Diseases, Version 9, (ICD-9), and 2 diagnosis-related group (DRG)-based case identification algorithms were compared against an independent, clinical pneumonia reference standard. Among 10748 patients, 272 (2.5%) had pneumonia verified by the reference standard. The sensitivity of claims-based algorithms ranged from 47.8% to 66.2%. The positive predictive values ranged from 72.6% to 80.8%. Patient-related variables were not significantly different from the reference standard among the 3 ICD-9-based algorithms. DRG-based algorithms had significantly lower hospital admission rates (57% and 65% vs 73.2%), lower 30-day mortality (5.0% and 5.8% vs 10.7%), shorter length of stay (3.9 and 4.1 days vs 5.6 days), and lower costs (USD $4543 and USD $5159 vs USD $8585). Claims-based identification algorithms for defining pneumonia in administrative databases are imprecise. ICD-9-based algorithms did not influence patient variables in our population. Identifying pneumonia patients with DRG codes is significantly less precise.

Ewig et al. proposed a new definition of severe community-acquired pneumonia in 1999, which was adopted by the American Thoracic Society in 2001. We evaluated this definition in an independent population of emergency department patients.We compared the 2001 American Thoracic Society definition of severe community-acquired pneumonia using emergency department data to intensive care unit (ICU) admission, use of mechanical ventilation, and administration of vasopressors.LDS Hospital, a tertiary care, university-affiliated hospital with 520 total beds and 68 ICU beds in Salt Lake City, UT.We studied 980 consecutive emergency department patients with a radiographically confirmed diagnosis of pneumonia between June 1995 and June 1999. Of these patients, 498 were admitted to the hospital, immunocompetent, and without a "do-not-resuscitate" order within 24 hrs of admission.Forty-seven patients met the criteria for severe community-acquired pneumonia in the emergency department and were admitted to the ICU. Three hundred eighty patients did not meet the criteria and were admitted to a hospital unit. Nineteen patients met the definition but were admitted to a hospital unit; only one required subsequent ICU admission. Two of the 19 died after a do-not-resuscitate order was entered24 hrs after admission; the remainder recovered. Fifty-two patients were triaged to the ICU but did not initially meet the definition of severe pneumonia. Sixteen of these 52 patients required mechanical ventilation, 13 of the 16 within 24 hrs of admission to the ICU. The sensitivity for the 2001 American Thoracic Society definition in our population was 44%, specificity was 95%, positive predictive value was 71%, and negative predictive value was 88%.The 2001 American Thoracic Society definition of severe community-acquired pneumonia had high specificity but lower sensitivity in our population compared with the derivation population. Additional factors not reflected in the definition may contribute to ICU admission and the need for mechanical ventilation.