Lien-Hsin Hu1,2, Robert J H Miller1,3, Tali Sharir4,5, Frederic Commandeur1, Richard Rios1, Andrew J Einstein6,7, Mathews B Fish8, Terrence D Ruddy9, Philipp A Kaufmann10, Albert J Sinusas11, Edward J Miller11, Timothy M Bateman12, Sharmila Dorbala13, Marcelo Di Carli13, Joanna X Liang1, Evann Eisenberg1, Damini Dey1, Daniel S Berman1, Piotr J Slomka1. 1. Department of Imaging, Medicine, and Biomedical Sciences, Cedars-Sinai Medical Center, 8700 Beverly Blvd, Los Angeles, CA 90048, USA. 2. Department of Nuclear Medicine, Taipei Veterans General Hospital, 201, Sec. 2, Shipai Road, Beitou District, Taipei 112, Taiwan. 3. Department of Cardiac Sciences, University of Calgary, 24 Ave NW, Calgary, AB, Canada. 4. Department of Nuclear Cardiology, Assuta Medical Center, HaBarzel St 20, Tel Aviv, Israel. 5. Faculty of Health Sciences, Ben Gurion University of the Negev, Rager Blvd, 84105 Be'er Sheva,, Israel. 6. Division of Cardiology, Department of Medicine, Columbia University Medical Center, 622 W 168th St, New York, NY 10032, USA. 7. Department of Radiology and Herbert Irving Comprehensive Cancer Center, Columbia University Irving Medical Center, 622 W 168th St, New York, NY 10032, USA. 8. Department of Nuclear Medicine, Oregon Heart and Vascular Institute, Sacred Heart Medical Center, 3333 Riverbend Dr, Springfield, OR 97477, USA. 9. Division of Cardiology, University of Ottawa Heart Institute, 40 Ruskin St, Ottawa, ON K1Y 4W7, Canada. 10. Department of Nuclear Medicine, Cardiac Imaging, University Hospital Zurich, Rämistrasse 100, 8091 Zurich, Switzerland. 11. Department of Internal Medicine, Section of Cardiovascular Medicine, Yale University, 333 Cedar St, New Haven, CT 06510, USA. 12. Cardiovascular Imaging Technologies LLC, 4320 Wormhall Rd, Kansas City, 64111 MO, USA. 13. Division of Nuclear Medicine and Molecular Imaging, Department of Radiology, Brigham and Women's Hospital, 75 Francis St, Boston, MA 02115, USA.
Abstract
AIMS: Single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) stress-only protocols reduce radiation exposure and cost but require clinicians to make immediate decisions regarding rest scan cancellation. We developed a machine learning (ML) approach for automatic rest scan cancellation and evaluated its prognostic safety. METHODS AND RESULTS: In total, 20 414 patients from a solid-state SPECT MPI international multicentre registry with clinical data and follow-up for major adverse cardiac events (MACE) were used to train ML for MACE prediction as a continuous probability (ML score), using 10-fold repeated hold-out testing to separate test from training data. Three ML score thresholds (ML1, ML2, and ML3) were derived by matching the cancellation rates achieved by physician interpretation and two clinical selection rules. Annual MACE rates were compared in patients selected for rest scan cancellation between approaches. Patients selected for rest scan cancellation with ML had lower annualized MACE rates than those selected by physician interpretation or clinical selection rules (ML1 vs. physician interpretation: 1.4 ± 0.1% vs. 2.1 ± 0.1%; ML2 vs. clinical selection: 1.5 ± 0.1% vs. 2.0 ± 0.1%; ML3 vs. stringent clinical selection: 0.6 ± 0.1% vs. 1.7 ± 0.1%, all P < 0.0001) at matched cancellation rates (60 ± 0.7, 64 ± 0.7, and 30 ± 0.6%). Annualized all-cause mortality rates in populations recommended for rest cancellation by physician interpretation, clinical selection approaches were higher (1.3%, 1.2%, and 1.0%, respectively) compared with corresponding ML thresholds (0.6%, 0.6%, and 0.2%). CONCLUSION: ML, using clinical and stress imaging data, can be used to automatically recommend cancellation of rest SPECT MPI scans, while ensuring higher prognostic safety than current clinical approaches. Published on behalf of the European Society of Cardiology. All rights reserved.
AIMS: Single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) stress-only protocols reduce radiation exposure and cost but require clinicians to make immediate decisions regarding rest scan cancellation. We developed a machine learning (ML) approach for automatic rest scan cancellation and evaluated its prognostic safety. METHODS AND RESULTS: In total, 20 414 patients from a solid-state SPECT MPI international multicentre registry with clinical data and follow-up for major adverse cardiac events (MACE) were used to train ML for MACE prediction as a continuous probability (ML score), using 10-fold repeated hold-out testing to separate test from training data. Three ML score thresholds (ML1, ML2, and ML3) were derived by matching the cancellation rates achieved by physician interpretation and two clinical selection rules. Annual MACE rates were compared in patients selected for rest scan cancellation between approaches. Patients selected for rest scan cancellation with ML had lower annualized MACE rates than those selected by physician interpretation or clinical selection rules (ML1 vs. physician interpretation: 1.4 ± 0.1% vs. 2.1 ± 0.1%; ML2 vs. clinical selection: 1.5 ± 0.1% vs. 2.0 ± 0.1%; ML3 vs. stringent clinical selection: 0.6 ± 0.1% vs. 1.7 ± 0.1%, all P < 0.0001) at matched cancellation rates (60 ± 0.7, 64 ± 0.7, and 30 ± 0.6%). Annualized all-cause mortality rates in populations recommended for rest cancellation by physician interpretation, clinical selection approaches were higher (1.3%, 1.2%, and 1.0%, respectively) compared with corresponding ML thresholds (0.6%, 0.6%, and 0.2%). CONCLUSION: ML, using clinical and stress imaging data, can be used to automatically recommend cancellation of rest SPECT MPI scans, while ensuring higher prognostic safety than current clinical approaches. Published on behalf of the European Society of Cardiology. All rights reserved.
Authors: Andrew Lin; Márton Kolossváry; Manish Motwani; Ivana Išgum; Pál Maurovich-Horvat; Piotr J Slomka; Damini Dey Journal: Radiol Cardiothorac Imaging Date: 2021-02-25
Authors: Richard Rios; Robert J H Miller; Nipun Manral; Tali Sharir; Andrew J Einstein; Mathews B Fish; Terrence D Ruddy; Philipp A Kaufmann; Albert J Sinusas; Edward J Miller; Timothy M Bateman; Sharmila Dorbala; Marcelo Di Carli; Serge D Van Kriekinge; Paul B Kavanagh; Tejas Parekh; Joanna X Liang; Damini Dey; Daniel S Berman; Piotr J Slomka Journal: Comput Biol Med Date: 2022-03-25 Impact factor: 6.698
Authors: Waseem Hijazi; Willam Leslie; Neil Filipchuk; Ryan Choo; Stephen Wilton; Matthew James; Piotr J Slomka; Robert J H Miller Journal: J Nucl Cardiol Date: 2022-04-13 Impact factor: 3.872
Authors: Piotr J Slomka; Jonathan B Moody; Robert J H Miller; Jennifer M Renaud; Edward P Ficaro; Ernest V Garcia Journal: J Nucl Cardiol Date: 2020-10-16 Impact factor: 5.952
Authors: Robert J H Miller; Tali Sharir; Yuka Otaki; Heidi Gransar; Joanna X Liang; Andrew J Einstein; Mathews B Fish; Terrence D Ruddy; Philipp A Kaufmann; Albert J Sinusas; Edward J Miller; Timothy M Bateman; Sharmila Dorbala; Marcelo Di Carli; Balaji K Tamarappoo; Damini Dey; Daniel S Berman; Piotr J Slomka Journal: J Nucl Med Date: 2021-03-12 Impact factor: 11.082
Authors: Richard Rios; Robert J H Miller; Lien Hsin Hu; Yuka Otaki; Ananya Singh; Marcio Diniz; Tali Sharir; Andrew J Einstein; Mathews B Fish; Terrence D Ruddy; Philipp A Kaufmann; Albert J Sinusas; Edward J Miller; Timothy M Bateman; Sharmila Dorbala; Marcelo DiCarli; Serge Van Kriekinge; Paul Kavanagh; Tejas Parekh; Joanna X Liang; Damini Dey; Daniel S Berman; Piotr Slomka Journal: Cardiovasc Res Date: 2022-07-20 Impact factor: 13.081
Authors: Yuka Otaki; Ananya Singh; Paul Kavanagh; Robert J H Miller; Tejas Parekh; Balaji K Tamarappoo; Tali Sharir; Andrew J Einstein; Mathews B Fish; Terrence D Ruddy; Philipp A Kaufmann; Albert J Sinusas; Edward J Miller; Timothy M Bateman; Sharmila Dorbala; Marcelo Di Carli; Sebastien Cadet; Joanna X Liang; Damini Dey; Daniel S Berman; Piotr J Slomka Journal: JACC Cardiovasc Imaging Date: 2021-07-14