Jesper Møller Jensen

Integrated prediction of lesion-specific ischaemia from quantitative coronary CT angiography using machine learning: a multicentre study

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

  • Damini Dey, Cedars-Sinai Medical Center
  • ,
  • Sara Gaur
  • ,
  • Kristian A Ovrehus
  • ,
  • Piotr J Slomka, Cedars-Sinai Medical Center
  • ,
  • Julian Betancur, Cedars-Sinai Medical Center
  • ,
  • Markus Goeller, Department of Cardiology, Friedrich-Alexander Universitat Erlangen-Nurnberg, Erlangen, Germany.
  • ,
  • Michaela M Hell, Department of Cardiology, Friedrich-Alexander Universitat Erlangen-Nurnberg, Erlangen, Germany.
  • ,
  • Heidi Gransar, Cedars-Sinai Medical Center
  • ,
  • Daniel S Berman, Cedars-Sinai Medical Center
  • ,
  • Stephan Achenbach, Department of Cardiology, Friedrich-Alexander Universitat Erlangen-Nurnberg, Erlangen, Germany.
  • ,
  • Hans Erik Botker
  • Jesper Moller Jensen
  • Jens Flensted Lassen
  • ,
  • Bjarne Linde Norgaard

OBJECTIVES: We aimed to investigate if lesion-specific ischaemia by invasive fractional flow reserve (FFR) can be predicted by an integrated machine learning (ML) ischaemia risk score from quantitative plaque measures from coronary computed tomography angiography (CTA).

METHODS: In a multicentre trial of 254 patients, CTA and invasive coronary angiography were performed, with FFR in 484 vessels. CTA data sets were analysed by semi-automated software to quantify stenosis and non-calcified (NCP), low-density NCP (LD-NCP, < 30 HU), calcified and total plaque volumes, contrast density difference (CDD, maximum difference in luminal attenuation per unit area) and plaque length. ML integration included automated feature selection and model building from quantitative CTA with a boosted ensemble algorithm, and tenfold stratified cross-validation.

RESULTS: Eighty patients had ischaemia by FFR (FFR ≤ 0.80) in 100 vessels. Information gain for predicting ischaemia was highest for CDD (0.172), followed by LD-NCP (0.125), NCP (0.097), and total plaque volumes (0.092). ML exhibited higher area-under-the-curve (0.84) than individual CTA measures, including stenosis (0.76), LD-NCP volume (0.77), total plaque volume (0.74) and pre-test likelihood of coronary artery disease (CAD) (0.63); p < 0.006.

CONCLUSIONS: Integrated ML ischaemia risk score improved the prediction of lesion-specific ischaemia by invasive FFR, over stenosis, plaque measures and pre-test likelihood of CAD.

KEY POINTS: • Integrated ischaemia risk score improved prediction of ischaemia over quantitative plaque measures • Integrated ischaemia risk score showed higher prediction of ischaemia than standard approach • Contrast density difference had the highest information gain to identify lesion-specific ischaemia.

Original languageEnglish
JournalEuropean Radiology
Pages (from-to)2655-2664
Number of pages10
Publication statusPublished - 1 Jun 2018

    Research areas

  • Journal Article

See relations at Aarhus University Citationformats

ID: 120719744