Probabilistic Case Detection for Disease Surveillance Using Data in Electronic Medical Records

This paper describes a probabilistic case detection system (CDS) that uses a Bayesian network model of medical diagnosis and natural language processing to compute the posterior probability of influenza and influenza-like illness from emergency department dictated notes and laboratory results. The d...

Descripción completa

Detalles Bibliográficos
Autores principales: Tsui, Fuchiang, Wagner, Michael, Cooper, Gregory, Que, Jialan, Harkema, Hendrik, Dowling, John, Sriburadej, Thomsun, Li, Qi, Espino, Jeremy U., Voorhees, Ronald
Formato: Online Artículo Texto
Lenguaje:English
Publicado: University of Illinois at Chicago Library 2011
Materias:
Articles
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3615792/
https://www.ncbi.nlm.nih.gov/pubmed/23569615
http://dx.doi.org/10.5210/ojphi.v3i3.3793
Descripción
Sumario:This paper describes a probabilistic case detection system (CDS) that uses a Bayesian network model of medical diagnosis and natural language processing to compute the posterior probability of influenza and influenza-like illness from emergency department dictated notes and laboratory results. The diagnostic accuracy of CDS for these conditions, as measured by the area under the ROC curve, was 0.97, and the overall accuracy for NLP employed in CDS was 0.91.

Ejemplares similares