Based on a study recently published in the June issue of Academic Radiology, the assortment and prioritization of patients with severe chest pains may soon become a simpler process, as an introduction of a computer-aided simple triage (CAST) system for mechanical stenosis detection can correctly classify patients with major stenosis.
“Given the significance of coronary artery disease as the most important socioeconomic health care problem in the Western world, the application of CAD [computer aided detection] algorithms and diagnosis techniques to this disease is surprisingly rare,” said professor at University Medical Center Mannheim, Germany, Mathias Meyer.
“This study demonstrates that the cCTA [coronary CT angiography] CAST system evaluated in this study is a reliable tool to rule out significant stenotic coronary artery stenosis on a per-patient as well as on a per-vessel level and especially improves the diagnostic accuracy of an inexperienced reader in a consecutive cohort of patients with acute chest pain and an intermediate risk for ACS [acute coronary syndrome],” he added.
Evaluating patients who are admitted to an emergency room with undetermined chest pain is a difficult task, albeit cCTA can consistently rule out considerable coronary artery stenosis in patients with a low- to intermediate-risk profile for ACS, noted the study.
“However, a major limitation of cCTA for evaluation of chest pain patients in the ED is the lack of available experienced readers, especially during nighttime and weekend hours.Therefore, a CAD system with consistent performance for coronary artery stenosis detection appears desirable.”
Meyer and peers looked to evaluate a CAST system, which is a branch of CAD used to carry out preliminary triage, unlike standard CAD systems which operate solely as a second reader.
The study originally enrolled 93 patients with severe chest pain and intermediate risk of ACS, of which 74 had satisfactory cCTA image quality for automatic analysis by the CAST system.
The CAST system identified stenosis of 50 percent or more in 45 patients, as opposed to interpretations made by physicians, which recognized 37 patients with major stenosis. For every patient, the CAST system had a sensitivity and specificity of 100 and 78 percent, for every vessel, sensitivity and specificity was 79 and 89 percent.
The researchers also observed the influence of CAST guidance on an inexperienced reader and discovered the system boosted overall improvement. Sensitivity and positive predictive values for inexperienced readers in identifying major stenosis saw an increase from 69 and 41 percent respectively, without the use of CAST, to 91 and 74 percent, respectively, with CAST.
Meyer and peers also cited that motion artifacts lessened image quality in some instances, caused vessels to be inaccurately recognized and the presence of stenosis to be overcalled. Yet they also noticed sensitivity and negative predictive value remained constant.
“In addition, such CAST systems can be used to perform a reading order prioritization, example: by giving higher priority to cases deemed positive by the system or by assigning more experienced readers to positive or low quality cases and less experienced to simple negative cases.”