Predicting the microbial cause of community-acquired pneumonia: can physicians or a data-driven method differentiate viral from bacterial pneumonia at patient presentation?
Open Access
- 6 March 2020
- journal article
- research article
- Published by Springer Science and Business Media LLC in BMC Pulmonary Medicine
- Vol. 20 (1), 1-9
- https://doi.org/10.1186/s12890-020-1089-y
Abstract
Community-acquired pneumonia (CAP) requires urgent and specific antimicrobial therapy. However, the causal pathogen is typically unknown at the point when anti-infective therapeutics must be initiated. Physicians synthesize information from diverse data streams to make appropriate decisions. Artificial intelligence (AI) excels at finding complex relationships in large volumes of data. We aimed to evaluate the abilities of experienced physicians and AI to answer this question at patient admission: is it a viral or a bacterial pneumonia? We included patients hospitalized for CAP and recorded all data available in the first 3-h period of care (clinical, biological and radiological information). For this proof-of-concept investigation, we decided to study only CAP caused by a singular and identified pathogen. We built a machine learning model prediction using all collected data. Finally, an independent validation set of samples was used to test the pathogen prediction performance of: (i) a panel of three experts and (ii) the AI algorithm. Both were blinded regarding the final microbial diagnosis. Positive likelihood ratio (LR) values > 10 and negative LR values < 0.1 were considered clinically relevant. We included 153 patients with CAP (70.6% men; 62 [51–73] years old; mean SAPSII, 37 [27–47]), 37% had viral pneumonia, 24% had bacterial pneumonia, 20% had a co-infection and 19% had no identified respiratory pathogen. We performed the analysis on 93 patients as co-pathogen and no-pathogen cases were excluded. The discriminant abilities of the AI approach were low to moderate (LR+ = 2.12 for viral and 6.29 for bacterial pneumonia), and the discriminant abilities of the experts were very low to low (LR+ = 3.81 for viral and 1.89 for bacterial pneumonia). Neither experts nor an AI algorithm can predict the microbial etiology of CAP within the first hours of hospitalization when there is an urgent need to define the anti-infective therapeutic strategy.Keywords
Other Versions
This publication has 28 references indexed in Scilit:
- Viral infection in community-acquired pneumonia: a systematic review and meta-analysisEuropean Respiratory Review, 2016
- Use of Tracheal Aspirate Culture in Newly Intubated Patients with Community-Onset PneumoniaAnnals of the American Thoracic Society, 2016
- Multicenter Comparison of Machine Learning Methods and Conventional Regression for Predicting Clinical Deterioration on the WardsCritical Care Medicine, 2016
- Impact of a Rapid Respiratory Panel Test on Patient OutcomesArchives of Pathology & Laboratory Medicine, 2014
- Long-term prognosis in community-acquired pneumoniaCurrent Opinion in Infectious Diseases, 2013
- Acute respiratory distress syndrome secondary to human metapneumovirus infection in a young healthy adultIntensive Care Medicine, 2013
- Years lived with disability (YLDs) for 1160 sequelae of 289 diseases and injuries 1990–2010: a systematic analysis for the Global Burden of Disease Study 2010The Lancet, 2013
- Implementation of FilmArray Respiratory Viral Panel in a Core Laboratory Improves Testing Turnaround Time and Patient CareAmerican Journal of Clinical Pathology, 2013
- Respiratory Infection and the Impact of Pulmonary Immunity on Lung Health and DiseaseAmerican Journal of Respiratory and Critical Care Medicine, 2012
- Clinical Impact of RT-PCR for Pediatric Acute Respiratory Infections: A Controlled Clinical TrialPEDIATRICS, 2011