Creating a text classifier to detect radiology reports describing mediastinal findings associated with inhalational anthrax and other disorders
Chapman WW, Cooper GF, Hanbury P, Chapman BE, Harrison LH, Wagner MM. Creating a text classifier to detect radiology reports describing mediastinal findings associated with inhalational anthrax and other disorders. Journal of the American Medical Informatics Association 10 (2003) 494-503. PMID: 12807805 PMC212787
Objective: The aim of this study was to create a classiﬁer for automatic detection of chest radiograph reports consistent with the mediastinal ﬁndings of inhalational anthrax.
Design: The authors used the Identify Patient Sets (IPS) system to create a key word classiﬁer for detecting reports describing mediastinal ﬁndings consistent with anthrax and compared their performances on a test set of 79,032 chest radiograph reports.
Measurements: Area under the ROC curve was the main outcome measure of the IPS classiﬁer. Sensitivity and speciﬁcity of an initial IPS model were calculated based on an existing key word search and were compared against a Boolean version of the IPS classiﬁer. Results: The IPS classiﬁer received an area under the ROC curve of 0.677 (90% CI = 0.628 to 0.772) with a speciﬁcity of 0.99 and maximum sensitivity of 0.35. The initial IPS model attained a speciﬁcity of 1.0 and a sensitivity of 0.04.
Conclusion: The IPS system is a useful tool for helping domain experts create a statistical key word classiﬁer for textual reports that is a potentially useful component in surveillance of radiographic ﬁndings suspicious for anthrax.