Predicting the microbial cause of community-acquired pneumonia: can physicians or a data-driven method differentiate viral from bacterial pneumonia at patient presentation?

التفاصيل البيبلوغرافية
العنوان:	Predicting the microbial cause of community-acquired pneumonia: can physicians or a data-driven method differentiate viral from bacterial pneumonia at patient presentation?
المؤلفون:	Claire Lhommet, Denis Garot, Leslie Grammatico-Guillon, Cassandra Jourdannaud, Pierre Asfar, Christophe Faisy, Grégoire Muller, Kimberly A. Barker, Emmanuelle Mercier, Sylvie Robert, Philippe Lanotte, Alain Goudeau, Helene Blasco, Antoine Guillon
المصدر:	BMC Pulmonary Medicine, Vol 20, Iss 1, Pp 1-9 (2020)
بيانات النشر:	BMC, 2020.
سنة النشر:	2020
المجموعة:	LCC:Diseases of the respiratory system
مصطلحات موضوعية:	Community-acquired pneumonia, Diagnosis, Artificial intelligence, Diseases of the respiratory system, RC705-779
الوصف:	Abstract Background 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? Methods 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
نوع الوثيقة:	article
وصف الملف:	electronic resource
اللغة:	English
تدمد:	1471-2466 08873631
Relation:	http://link.springer.com/article/10.1186/s12890-020-1089-y; https://doaj.org/toc/1471-2466
DOI:	10.1186/s12890-020-1089-y
URL الوصول:	https://doaj.org/article/c08873631d0a48d1b310b8883299c14d
رقم الانضمام:	edsdoj.08873631d0a48d1b310b8883299c14d
قاعدة البيانات:	Directory of Open Access Journals

View record in DOAJ

Full Text Finder

الوصف
تدمد:	14712466 08873631
DOI:	10.1186/s12890-020-1089-y