Diagnostic performance of an artificial intelligence-driven cardiac-structured reporting system for myocardial perfusion
- PDF / 2,039,751 Bytes
- 13 Pages / 593.972 x 792 pts Page_size
- 39 Downloads / 193 Views
c
Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA Division of Cardiology, Department of Medicine, UNC School of Medicine, University of North Carolina, Chapel Hill, NC Syntermed, Inc., Atlanta, GA
Received Jun 5, 2018; accepted Aug 27, 2018 doi:10.1007/s12350-018-1432-3
Objectives. To describe and validate an artificial intelligence (AI)-driven structured reporting system by direct comparison of automatically generated reports to results from actual clinical reports generated by nuclear cardiology experts. Background. Quantitative parameters extracted from myocardial perfusion imaging (MPI) studies are used by our AI reporting system to generate automatically a guideline-compliant structured report (sR). Method. A new nonparametric approach generates distribution functions of rest and stress, perfusion, and thickening, for each of 17 left ventricle segments that are then transformed to certainty factors (CFs) that a segment is hypoperfused, ischemic. These CFs are then input to our set of heuristic rules used to reach diagnostic findings and impressions propagated into a sR referred as an AI-driven structured report (AIsR). The diagnostic accuracy of the AIsR for detecting coronary artery disease (CAD) and ischemia was tested in 1,000 patients who had undergone rest/stress SPECT MPI. Results. At the high-specificity (SP) level, in a subset of 100 patients, there were no statistical differences in the agreements between the AIsr, and nine experts’ impressions of CAD (P 5 .33) or ischemia (P 5 .37). This high-SP level also yielded the highest accuracy across global and regional results in the 1,000 patients. These accuracies were statistically significantly better than the other two levels [sensitivity (SN)/SP tradeoff, high SN] across all comparisons. Conclusions. This AI reporting system automatically generates a structured natural language report with a diagnostic performance comparable to those of experts. (J Nucl Cardiol 2018) Key Words: Expert systems Æ artificial intelligence Æ myocardial perfusion SPECT Æ quantitative analysis, structured reporting
Electronic supplementary material The online version of this article (https://doi.org/10.1007/s12350-018-1432-3) contains supplementary material, which is available to authorized users. The authors of this article have provided a PowerPoint file, available for download at SpringerLink, which summarises the contents of the paper and is free for re-use at meetings and presentations. Search for the article DOI on SpringerLink.com.
Reprint requests: Ernest V. Garcia, PhD, Department of Radiology and Imaging Sciences, Emory University, 101 Woodruff Circle, Room 1203, Atlanta, GA 30322; [email protected] 1071-3581/$34.00 Copyright Ó 2018 American Society of Nuclear Cardiology.
Garcia et al Diagnostic performance of an artificial intelligence-driven cardiac-structured reporting system
Abbreviations AI Artificial intelligence AIsR AI-driven structured report CAD Coronary artery disease CF Certainty factor CI Confidence interval ECTb
Data Loading...
