Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Study design.

(A) Development—Two BCDs were developed at IH and UPMC, respectively. At each site, a rule-based parser was manually built by a knowledge engineer based on expert-annotated sample notes. A Bayesian network classifier was machine-learned from a local training set. (B) Test—Test datasets were created using local encounters (continuous arrows) or non-local encounters (dashed arrows) to evaluate both local performance and transferability. Bayesian network classifier’s abilities to discriminate a case of (1) influenza from non-influenza and (2) influenza from non-influenza influenza-like illness (NI-ILI) were evaluated. Not shown—an algorithm limited encounter data included in the test dataset based on time since registration.

More »

Fig 1 Expand

Table 1.

Summary of training and test datasets.

More »

Table 1 Expand

Table 2.

Transferability studies.

More »

Table 2 Expand

Table 3.

Seven factors affecting the performance of a Bayesian case detection system.

More »

Table 3 Expand

Table 4.

Clinical findings included in the four Bayesian network classifiers.

More »

Table 4 Expand

Fig 2.

Four Bayesian network classifiers developed using datasets distinguished by data resources and NLP parsers.

GeNIe visualization [62].

More »

Fig 2 Expand

Table 5.

Performance and transferability of the influenza detection systems.

More »

Table 5 Expand

Table 6.

Information delay of all ED encounters between June 1, 2010 and May 31, 2011 at UPMC and IH.

More »

Table 6 Expand

Fig 3.

AUCs of BCDIH and BCDUPMC for discriminating between influenza and non-influenza over different time delays.

More »

Fig 3 Expand

Fig 4.

AUCs of BCDIH and BCDUPMC for discriminating between influenza and NI-ILI over different time delays.

More »

Fig 4 Expand