IntroductionAlthough pneumonia has been identified as the single most common risk factor for acute lung injury (ALI), we have a limited knowledge as to why ALI develops in some patients with pneumonia and not in others. The objective of this study was to determine frequency, risk factors, and outcome of ALI in patients with infectious pneumonia.MethodsA retrospective cohort study of adult patients with microbiologically positive pneumonia, hospitalized at two Mayo Clinic Rochester hospitals between January 1, 2005, and December 31, 2007. In a subsequent nested case-control analysis, we evaluated the differences in prehospital and intrahospital exposures between patients with and without ALI/acute respiratory distress syndrome (ARDS) matched by specific pathogen, isolation site, gender, and closest age in a 1:1 manner.ResultsThe study included 596 patients; 365 (61.2%) were men. The median age was 65 (IQR, 53 to 75) years. In total, 171 patients (28.7%) were diagnosed with ALI. The occurrence of ALI was less frequent in bacterial (n = 99 of 412, 24%) compared with viral (n = 19 of 55, 35%), fungal (n = 39 of 95, 41%), and mixed isolates pneumonias (n = 14 of 34, 41%; P = 0.002). After adjusting for baseline severity of illness and comorbidities, patients in whom ALI developed had a markedly increased risk of hospital death (ORadj 9.7; 95% CI, 6.0 to 15.9). In a nested case-control study, presence of shock (OR, 8.9; 95% CI, 2.8 to 45.9), inappropriate initial antimicrobial treatment (OR, 3.2; 95% CI, 1.3 to 8.5), and transfusions (OR, 4.8; 95% CI, 1.5 to 19.6) independently predicted ALI development.ConclusionsThe development of ALI among patients hospitalized with infectious pneumonia varied among pulmonary pathogens and was associated with increased mortality. Inappropriate initial antimicrobial treatment and transfusion predict the development of ALI independent of pathogen.

No abstract

This retrospective population-based study evaluated the effects of alcohol consumption on the development of acute respiratory distress syndrome (ARDS). Alcohol consumption was quantified based on patient and/or family provided information at the time of hospital admission. ARDS was defined according to American-European consensus conference (AECC). From 1,422 critically ill Olmsted county residents, 1,357 had information about alcohol use in their medical records, 77 (6%) of whom developed ARDS. A history of significant alcohol consumption (more than two drinks per day) was reported in 97 (7%) of patients. When adjusted for underlying ARDS risk factors (aspiration, chemotherapy, high-risk surgery, pancreatitis, sepsis, shock), smoking, cirrhosis and gender, history of significant alcohol consumption was associated with increased risk of ARDS development (odds ratio 2.9, 95% CI 1.3-6.2). This population-based study confirmed that excessive alcohol consumption is associated with higher risk of ARDS.

Background: International Classification of Disease (ICD) coding for pneumonia classification is based on causal organism or use of general pneumonia codes, creating challenges for epidemiological evaluations, where pneumonia is standardly subtyped by settings, exposures and time of emergence. Pneumonia subtype classification requires data available in electronic health records (EHR), frequently in non-structured formats including radiological interpretation or clinical notes that complicate electronic classification. Objective: The current study undertook development of a rule-based pneumonia subtyping algorithm for stratifying pneumonia by the setting in which it emerged using information documented in the EHR. Methods: Pneumonia subtype classification was developed by interrogating patient information within the EHR of a large private Health System. ICD coding was mined in the EHR applying requirements for ‘rule of two’ pneumonia-related codes or one ICD code and radiologically-confirmed pneumonia validated by natural language processing and/or documented antibiotic prescriptions. A rule-based algorithm flow chart was created to support sub-classification based on features including symptomatic patient point of entry into the healthcare system timing of pneumonia emergence and identification of clinical, laboratory or medication orders that informed definition of the pneumonia sub-classification algorithm. Results: Data from 65,904 study-eligible patients with 91,998 episodes of pneumonia diagnoses documented by 380,509 encounters were analyzed, while 8,611 episodes were excluded following NLP classification of pneumonia status as ‘negative’ or ‘unknown’. Subtyping of 83,387 episodes identified: community acquired (54.5%), hospital-acquired (20%), aspiration-related (10.7%), healthcare-acquired (5%), ventilator-associated (0.4%) cases, and 9.4% were not classifiable by the algorithm. Conclusion: Study outcome indicated capacity to achieve electronic pneumonia subtype classification based on interrogation of big data available in the EHR. Examination of portability of the algorithm to achieve rule-based pneumonia classification in other health systems remains to be explored.

Introduction: Pneumonia is caused by microbes that establish an infectious process in the lungs. The gold standard for pneumonia diagnosis is radiologist-documented pneumonia-related features in radiology notes that are captured in electronic health records in an unstructured format. Objective: The study objective was to develop a methodological approach for assessing validity of a pneumonia diagnosis based on identifying presence or absence of key radiographic features in radiology reports with subsequent rendering of diagnostic decisions into a structured format. Methods: A pneumonia-specific Natural Language Processing (NLP) pipeline was strategically developed applying cTAKES to validate pneumonia diagnoses following development of a pneumonia feature-specific lexicon. Radiographic reports of study-eligible subjects identified by International Classification of Diseases (ICD) codes were parsed through the NLP pipeline. Classification rules were developed to assign each pneumonia episode into one of three categories: “positive”, “negative” or “not classified: requires manual review” based on tagged concepts that support or refute diagnostic codes. Results: A total of 91,998 pneumonia episodes diagnosed in 65,904 patients were retrieved retrospectively. Approximately 89% (81,707/91,998) of the total pneumonia episodes were documented by 225,893 chest x-ray reports. NLP classified and validated 33% (26,800/81,707) of pneumonia episodes classified as ‘Pneumonia-positive’, 19% as (15401/81,707) as ‘Pneumonia-negative’ and 48% (39,209/81,707) as ‘‘episode classification pending further manual review’. NLP pipeline performance metrics included accuracy (76.3%), sensitivity (88%), and specificity (75%). Conclusion: The pneumonia-specific NLP pipeline exhibited good performance comparable to other pneumonia-specific NLP systems developed to date.