EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Human AI Teaming for Coronary CT Angiography Assessment: Impact on Imaging Workflow and Diagnostic Accuracy

Florian Andre iD, Philipp Fortner, Matthias Aurich iD, Sebastian Seitz, Ann-Kathrin Jatsch iD, Max Schöbinger, Michael Wels iD, Martin Kraus, Mehmet Akif Gülsün, Norbert Frey, Andre Sommer, Johannes Görich und 1 weitere

Diagnostics · 30.11.2023 · 13 (23) · 3574

DOI: 10.3390/diagnostics13233574 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 30.11.2023. Verfasst von Florian Andre und 12 weiteren Autor:innen. Beteiligte Einrichtung: Department of Cardiology, Angiology and Pneumology, University of Heidelberg, 69120 Heidelberg, Germany. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Siemens Healthcare (Germany), Siemens Healthcare, Forchheim, Germany.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As the number of coronary computed tomography angiography (CTA) examinations is expected to increase, technologies to optimize the imaging workflow are of great interest. The aim of this study was to investigate the potential of artificial intelligence (AI) to improve clinical workflow and diagnostic accuracy in high-volume cardiac imaging centers. A total of 120 patients (79 men; 62.4 (55.0–72.7) years; 26.7 (24.9–30.3) kg/m2) undergoing coronary CTA were randomly assigned to a standard or an AI-based (human AI) coronary analysis group. Severity of coronary artery disease was graded according to CAD-RADS. Initial reports were reviewed and changes were classified. Both groups were similar with regard to age, sex, body mass index, heart rate, Agatston score, and CAD-RADS. The time for coronary CTA assessment (142.5 (106.5–215.0) s vs. 195.0 (146.0–265.5) s; p < 0.002) and the total reporting time (274.0 (208.0–377.0) s vs. 350 (264.0–445.5) s; p < 0.02) were lower in the human AI than in the standard group. The number of cases with no, minor, or CAD-RADS relevant changes did not differ significantly between groups (52, 7, 1 vs. 50, 8, 2; p = 0.80). AI-based analysis significantly improves clinical workflow, even in a specialized high-volume setting, by reducing CTA analysis and overall reporting time without compromising diagnostic accuracy.

Schlagwörter

Stichwörter der Autor:innen

artificial intelligencecomputed tomographycoronary CT angiographycoronary artery diseasehuman AI teamingworkflow

Autor:innen und Institutionen

  • Department of Cardiology, Angiology and Pneumology, University of Heidelberg, 69120 Heidelberg, Germany.
  • MVZ DRZ Heidelberg, 69126 Heidelberg, Germany.
  • Siemens Healthineers, 91301 Forchheim, Germany.
  • Siemens Healthineers, Princeton, NJ 08540, USA.

ORCID-Profile: Florian Andre, Matthias Aurich, Ann-Kathrin Jatsch, Michael Wels

Förderung

  • Siemens Healthcare (Germany)
  • Siemens Healthcare, Forchheim, Germany

Zitieren

APA

Andre, F., Fortner, P., Aurich, M., Seitz, S., Jatsch, A. K., Schöbinger, M., Wels, M., Kraus, M., Gülsün, M. A., Frey, N., Sommer, A., Görich, J., & Buss, S. J. (2023). Human AI Teaming for Coronary CT Angiography Assessment: Impact on Imaging Workflow and Diagnostic Accuracy. Diagnostics, 13(23), 3574. https://doi.org/10.3390/diagnostics13233574

Vancouver

Andre F, Fortner P, Aurich M, Seitz S, Jatsch AK, Schöbinger M, et al. Human AI Teaming for Coronary CT Angiography Assessment: Impact on Imaging Workflow and Diagnostic Accuracy. Diagnostics. 2023;13(23):3574. doi:10.3390/diagnostics13233574

BibTeX
@article{Andre2023,
  author = {Andre, Florian and Fortner, Philipp and Aurich, Matthias and Seitz, Sebastian and Jatsch, Ann-Kathrin and Schöbinger, Max and Wels, Michael and Kraus, Martin and Gülsün, Mehmet Akif and Frey, Norbert and Sommer, Andre and Görich, Johannes and Buss, Sebastian J},
  title = {Human AI Teaming for Coronary CT Angiography Assessment: Impact on Imaging Workflow and Diagnostic Accuracy},
  journal = {Diagnostics},
  year = {2023},
  volume = {13},
  number = {23},
  pages = {3574},
  doi = {10.3390/diagnostics13233574}
}
Kostenlos starten →