Abstract
Background
Stress-only myocardial perfusion imaging (MPI) markedly reduces radiation dose, scanning time, and cost. We developed an automated clinical algorithm to safely cancel unnecessary rest imaging with high sensitivity for obstructive coronary artery disease (CAD).
Methods and Results
Patients without known CAD undergoing both MPI and invasive coronary angiography from REFINE SPECT were studied. A machine learning score (MLS) for prediction of obstructive CAD was generated using stress-only MPI and pre-test clinical variables. An MLS threshold with a pre-defined sensitivity of 95% was applied to the automated patient selection algorithm. Obstructive CAD was present in 1309/2079 (63%) patients. MLS had higher area under the receiver operator characteristic curve (AUC) for prediction of CAD than reader diagnosis and TPD (0.84 vs 0.70 vs 0.78, P < .01). An MLS threshold of 0.29 had superior sensitivity than reader diagnosis and TPD for obstructive CAD (95% vs 87% vs 87%, P < .01) and high-risk CAD, defined as stenosis of the left main, proximal left anterior descending, or triple-vessel CAD (sensitivity 96% vs 89% vs 90%, P < .01).
Conclusions
The MLS is highly sensitive for prediction of both obstructive and high-risk CAD from stress-only MPI and can be applied to a stress-first protocol for automatic cancellation of unnecessary rest imaging.
Similar content being viewed by others
Abbreviations
- CAD:
-
Coronary artery disease
- ICA:
-
Invasive coronary angiography
- LAD:
-
Left anterior descending
- LCx:
-
Left circumflex artery
- LMCA:
-
Left main coronary artery
- MLS:
-
Machine learning score
- MPI:
-
Myocardial perfusion imaging
- SPECT:
-
Single-photon emission computed tomography
- SSS:
-
Summed stress score
- TPD:
-
Total perfusion deficit
References
Wolk MJ, Bailey SR, Doherty JU, Douglas PS, Hendel RC, Kramer CM, et al. ACCF/AHA/ASE/ASNC/HFSA/HRS/SCAI/SCCT/SCMR/STS 2013 multimodality appropriate use criteria for the detection and risk assessment of stable ischemic heart disease. J Card Fail 2014;20:65-90.
Einstein AJ, Pascual TN, Mercuri M, Karthikeyan G, Vitola JV, Mahmarian JJ, et al. Current worldwide nuclear cardiology practices and radiation exposure: Results from the 65 country IAEA Nuclear Cardiology Protocols Cross-Sectional Study (INCAPS). Eur Heart J 2015;36:1689-96.
Mercuri M, Pascual TN, Mahmarian JJ, Shaw LJ, Dondi M, Paez D, et al. Estimating the reduction in the radiation burden from nuclear cardiology through use of stress-only imaging in the united states and worldwide. JAMA Intern Med 2016;176:269-73.
Jerome SD, Tilkemeier PL, Farrell MB, Shaw LJ. Nationwide laboratory adherence to myocardial perfusion imaging radiation dose reduction practices: A report from the intersocietal accreditation commission data repository. JACC Cardiovasc Imaging 2015;8:1170-6.
Gowd BM, Heller GV, Parker MW. Stress-only SPECT myocardial perfusion imaging: A review. J Nucl Cardiol 2014;21:1200-12.
Bhalodkar NC, Blum S. Normal stress-only versus standard stress/rest myocardial perfusion imaging: Similar patient mortality with reduced radiation exposure. J Am Coll Cardiol 2010;55:2611-2.
Ueyama T, Takehana K, Maeba H, Iwasaka T. Prognostic value of normal stress-only technetium-99m myocardial perfusion imaging protocol. Comparison with standard stress-rest protocol. Circ J 2012;76:2386-91.
Chang SM, Nabi F, Xu J, Raza U, Mahmarian JJ. Normal stress-only versus standard stress/rest myocardial perfusion imaging: Similar patient mortality with reduced radiation exposure. J Am Coll Cardiol 2010;55:221-30.
Gowdar S, Chaudhry W, Ahlberg AW, Henzlova MJ, Duvall WL. Triage of patients for attenuation-corrected stress-first Tc-99m SPECT MPI using a simplified clinical pre-test scoring model. J Nucl Cardiol 2018;25:1178-87.
Betancur J, Otaki Y, Motwani M, Fish MB, Lemley M, Dey D, et al. Prognostic value of combined clinical and myocardial perfusion imaging data using machine learning. JACC Cardiovasc Imaging 2018;11:1000-9.
Hu LH, Betancur J, Sharir T, Einstein AJ, Bokhari S, Fish MB, et al. Machine learning predicts per-vessel early coronary revascularization after fast myocardial perfusion SPECT: results from multicentre REFINE SPECT registry. Eur Heart J Cardiovasc Imaging 2020;21:549-59.
Hu LH, Miller RJH, Sharir T, Commandeur F, Rios R, Einstein AJ et al. Prognostically safe stress-only SPECT myocardial perfusion imaging guided by machine learning: Report from REFINE SPECT. Eur Heart J Cardiovasc Imaging 2020.
Slomka PJ, Betancur J, Liang JX, Otaki Y, Hu LH, Sharir T, et al. Rationale and design of the REgistry of Fast Myocardial Perfusion Imaging with NExt generation SPECT (REFINE SPECT). J Nucl Cardiol 2020;27:1010-21.
Miller RJH, Klein E, Gransar H, Slomka PJ, Friedman JD, Hayes S, et al. Prognostic significance of previous myocardial infarction and previous revascularization in patients undergoing SPECT MPI. Int J Cardiol 2020;313:9-15.
Molinaro AM, Simon R, Pfeiffer RM. Prediction error estimation: A comparison of resampling methods. Bioinformatics 2005;21:3301-7.
Motwani M, Dey D, Berman DS, Germano G, Achenbach S, Al-Mallah MH, et al. Machine learning for prediction of all-cause mortality in patients with suspected coronary artery disease: A 5-year multicentre prospective registry analysis. Eur Heart J 2017;38:500-7.
DeLong ER, DeLong DM, Clarke-Pearson DL. Comparing the areas under two or more correlated receiver operating characteristic curves: A nonparametric approach. Biometrics 1988;44:837-45.
Duvall WL, Hiensch RJ, Levine EJ, Croft LB, Henzlova MJ. The prognosis of a normal Tl-201 stress-only SPECT MPI study. J Nucl Cardiol 2012;19:914-21.
Duvall WL, Baber U, Levine EJ, Croft LB, Henzlova MJ. A model for the prediction of a successful stress-first Tc-99m SPECT MPI. J Nucl Cardiol 2012;19:1124-34.
Budoff MJ, Li D, Kazerooni EA, Thomas GS, Mieres JH, Shaw LJ. Diagnostic accuracy of noninvasive 64-row Computed Tomographic Coronary Angiography (CCTA) compared with Myocardial Perfusion Imaging (MPI): The PICTURE Study. A prospective multicenter trial. Acad Radiol 2017;24:22-9.
George RT, Mehra VC, Chen MY, Kitagawa K, Arbab-Zadeh A, Miller JM, et al. Myocardial CT perfusion imaging and SPECT for the diagnosis of coronary artery disease: A head-to-head comparison from the CORE320 multicenter diagnostic performance study. Radiology 2015;274:626.
Berman DS, Shaw LJ, Min JK, Hachamovitch R, Abidov A, Germano G, et al. SPECT/PET myocardial perfusion imaging versus coronary CT angiography in patients with known or suspected CAD. Q J Nucl Med Mol Imaging 2010;54:177-200.
Nakanishi R, Gransar H, Slomka P, Arsanjani R, Shalev A, Otaki Y, et al. Predictors of high-risk coronary artery disease in subjects with normal SPECT myocardial perfusion imaging. J Nucl Cardiol 2016;23:530-41.
Cosmai EM, Heller GV. The clinical importance of electrocardiographic changes during pharmacologic stress testing with radionuclide myocardial perfusion imaging. J Nucl Cardiol 2005;12:466-72.
Emmett L, Iwanochko RM, Freeman MR, Barolet A, Lee DS, Husain M. Reversible regional wall motion abnormalities on exercise technetium-99m-gated cardiac single photon emission computed tomography predict high-grade angiographic stenoses. J Am Coll Cardiol 2002;39:991-8.
Otaki Y, Betancur J, Sharir T, Hu L-H, Gransar H, Liang JX, et al. 5-year prognostic value of quantitative versus visual mpi in subtle perfusion defects. JACC Cardiovasc Imaging 2020;13:774-85.
Fiechter M, Ghadri JR, Kuest SM, Pazhenkottil AP, Wolfrum M, Nkoulou RN, et al. Nuclear myocardial perfusion imaging with a novel cadmium-zinc-telluride detector SPECT/CT device: First validation versus invasive coronary angiography. Eur J Nucl Med Mol Imaging 2011;38:2025-30.
Disclosures
This research was supported in part by Grant R01HL089765 from the National Heart, Lung, and Blood Institute/ National Institutes of Health (NHLBI/NIH) (PI: Piotr Slomka). The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health. The work was supported in part by the Dr. Miriam and Sheldon Adelson Medical Research Foundation. D.S.B., and P.J.S. participate in software royalties for QPS software at Cedars-Sinai Medical Center. P.J.S. has received research Grant support from Siemens Medical Systems. D.S.B., A.J.E., and E.J.M. have served as consultants for GE Healthcare. M.D.C. has received research Grant support from Spectrum-Dynamics and consulting honoraria from Sanofi and GE Healthcare. T.D.R. has received research Grant support from GE Healthcare and Advanced Accelerator Applications. A.J.E. and his institution have received research support from GE Healthcare, Philips Healthcare, and Toshiba America Medical Systems. E.J.M. has served as a consultant for Bracco Inc, and he and his institution have received Grant support from Bracco Inc. All other authors have reported that they have no relationships relevant to the contents of this paper to disclose.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This article includes a PowerPoint file that should be made available as ESM on SpringerLink.
The authors of this article have provided a PowerPoint file, available for download at SpringerLink, which summarizes the contents of the paper and is free for re-use at meetings and presentations. Search for the article DOI on SpringerLink.com.
Funding
This research was supported in part by Grant R01HL089765 from the National Heart, Lung, and Blood Institute/ National Institutes of Health (NHLBI/NIH) (PI: Piotr Slomka). The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health. The work was supported in part by the Dr. Miriam and Sheldon Adelson Medical Research Foundation.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Eisenberg, E., Miller, R.J.H., Hu, LH. et al. Diagnostic safety of a machine learning-based automatic patient selection algorithm for stress-only myocardial perfusion SPECT. J. Nucl. Cardiol. 29, 2295–2307 (2022). https://doi.org/10.1007/s12350-021-02698-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12350-021-02698-4