Reading TB screening chest radiographs may be more efficient with the use of custom software, from SIIM 2016.
Computer-aided reporting increases efficiency of reporting tuberculosis (TB) screening chest radiographs, according to a study presented at the annual meeting of the Society for Imaging Informatics in Medicine in Portland, OR.
Researchers from the University of Maryland Medical Center in Baltimore evaluated the efficiency of reporting with custom software, and its ability to maintain high quality results when screening for TB. Using EzRad, a custom software package developed specifically for interpreting chest screening radiographs for TB, one resident provided complete preliminary interpretations of the studies performed off hours (evening and night) from 2007 to 2015, which were then stored in a relational database. Residents accessed the interpretations to compare them with initial readings.
The researchers performed a retrospective evaluation to determine percentage of studies initially interpreted incorrectly for TB screening by the resident’s preliminary report when compared with the attending’s final report, or the miss rate.
The results showed that of 838,465 TB screening chest radiographs, there were 964 false negatives and 97 false positives for TB, for an overall miss rate of 0.1% when using the EzRad computer-aided reporting software.
“Computer-aided reporting through the custom EzRad software provided an efficient method for residents to interpret TB screening chest radiographs in a high risk patient population without sacrificing the quality of reporting,” the researchers said. The researchers compared this approach with the tailored approach of mammography. “The study suggests that computer-aided reporting of structured reports through a user interface with natural language generation can help to provide an efficient and accurate method for interpretation of TB screening chest radiographs.”
Study: AI Bolsters Sensitivity for Pneumothorax on CXR and Significantly Reduces Reporting Time
October 30th 2024For clinically actionable pneumothorax, an artificial intelligence algorithm demonstrated a 93 percent AUC and a 96 percent specificity rate in a study involving chest X-rays from over 27,000 adults.
Comparative Study Evaluates AI Products for Detecting Tuberculosis on Chest X-Rays
August 9th 2024At a 90 percent threshold for sensitivity, Lunit’s Insight CXR and the Nexus CXR software from Nexus demonstrated the highest specificity rates for tuberculosis (TB) detection in a patient population with a high prevalence of TB and HIV.