Displaying results 1 - 6 of 6
-
Optimizing Performance of an Ngram Method for Classifying Emergency Department Visits into the Respiratory Syndrome
Content Type: Abstract
A number of different methods are currently used to classify patients into syndromic groups based on the patient’s chief complaint (CC). We previously reported results using an “Ngram” text processing program for building classifiers… read more… AT&T Labs). The method applies the ICD9 classifier to a training set of ED visits for which both the CC and ICD9 … Ngrams), with associated probabilities, from the training data. We then generate a CC classifier from the … AT&T Labs). The method applies the ICD9 classifier to a training set of ED visits for which both the CC and ICD9 … -
Talking Turkish: Using N-Grams for Syndromic Surveillance in a Turkish Emergency Department without the Need for English Translation
Content Type: Abstract
Previously we used an “N-Gram” classifier for syndromic surveillance of emergency department (ED) chief complaints (CC) in English for bioterrorism. The classifier is trained on a set of ED visits for which both the ICD diagnosis code and CC are… read more… Our objective was to apply the N-Gram method to a training set of Turkish ED data to create a Turkish CC … Our objective was to apply the N-Gram method to a training set of Turkish ED data to create a Turkish CC … technologies applied to the first 10 months of data as a training set to create a Turkish CC RESP classifier. We next … -
Improvement in Performance of Ngram Classifiers with Frequent Updates
Content Type: Abstract
Syndromic surveillance of emergency department(ED) visit data is often based on computerized classifiers which assign patient chief complaints (CC) tosyndromes. These classifiers may need to be updatedperiodically to account for changes… read more… creates a CC classifier automatically based on a training set of patient visits for which both the CC and … creates a CC classifier automatically based on a training set of patient visits for which both the CC and … for lower GI. The N-Gram CC classifiers were built from training sets chosen in three different and pro- gressively … -
The NGram CC Classifier: A Novel Method of Automatically Creating CC Classifiers Based on ICD9 Groupings
Content Type: Abstract
Syndromic surveillance of emergency department (ED) visit data is often based on computer algorithms which assign patient chief complaints (CC) to syndromes. ICD9 code data may also be used to develop visit classifiers for syndromic surveillance but… read more… (AT&T Labs). The method applies the ICD9 classifier to a training set of ED visits for which both the CC and ICD9 … (AT&T Labs). The method applies the ICD9 classifier to a training set of ED visits for which both the CC and ICD9 … abdominal pain. The ICD9 classifier was applied to a training set of visits for the year 2000 to create the ngram … -
The Performance of a NGram Classifier for Patients' Chief Complaint Based on a Computerized Pick List Entry and Free Text in an Italian Emergency Department
Content Type: Abstract
Syndromic surveillance of emergency department (ED) visit data is often based on computer algorithms which assign patient chief complaints (CC) and ICD code data to syndromes. The triage nurse note (NN) has also been used for… read more… the 23 CC pick list categories. We used the 2005 data for training the classifiers and the 2006 data for testing the … ESSENCE classifier for RESP as the criterion standard for training and testing. To test the probabilistic methods, we … -
Sensitivity and Specificity of an Ngram Method for Classifying Emergency Department Visits into the Respiratory Syndrome in the Turkish Language
Content Type: Abstract
Previously we developed an “Ngram” classifier for syndromic surveillance of emergency department (ED) chief complaints (CC) in Turkish for bioterrorism. The classifier is developed from a set of ED visits for which both the ICD… read more… AT&T Labs applied to the first 10 months of data as a training set to create a Turkish CC RESP classifier. We next …