Skip to main content

Advertisement

SpringerLink
Log in

Automated abstraction of myocardial perfusion imaging reports using natural language processing

  • ORIGINAL ARTICLE
  • Published:
Journal of Nuclear Cardiology Aims and scope

Abstract

Background

Findings and interpretations of myocardial perfusion imaging (MPI) studies are documented in free-text MPI reports. MPI results are essential for research, but manual review is prohibitively time consuming. This study aimed to develop and validate an automated method to abstract MPI reports.

Methods

We developed a natural language processing (NLP) algorithm to abstract MPI reports. Randomly selected reports were double-blindly reviewed by two cardiologists to validate the NLP algorithm. Secondary analyses were performed to describe patient outcomes based on abstracted-MPI results on 16,957 MPI tests from adult patients evaluated for suspected ACS.

Results

The NLP algorithm achieved high sensitivity (96.7%) and specificity (98.9%) on the MPI categorical results and had a similar degree of agreement compared to the physician reviewers. Patients with abnormal MPI results had higher rates of 30-day acute myocardial infarction or death compared to patients with normal results. We identified issues related to the quality of the reports that not only affect communication with referring physicians but also challenges for automated abstraction.

Conclusion

NLP is an accurate and efficient strategy to abstract results from the free-text MPI reports. Our findings will facilitate future research to understand the benefits of MPI studies but requires validation in other settings.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Figure 1

Similar content being viewed by others

Abbreviations

ACS:

Acute coronary syndrome

AMI:

Acute myocardial infarction

EHR:

Electronic health record

ETT:

Exercise treadmill test

ED:

Emergency department

EF:

Ejection fraction

HEART:

History, Electrocardiogram, Age, Risk factors, Troponin

MACE:

Major adverse cardiac events

MPI:

Myocardial perfusion imaging

NLP:

Natural language processing

References

  1. Ladapo JA, Blecker S, Douglas PS. Physician decision making and trends in the use of cardiac stress testing in the United States: An analysis of repeated cross-sectional data. Ann Intern Med. 2014;161:482–90.

    Article  Google Scholar 

  2. Hachamovitch R, Berman DS, Shaw LJ, et al. Incremental prognostic value of myocardial perfusion single photon emission computed tomography for the prediction of cardiac death: Differential stratification for risk of cardiac death and myocardial infarction. Circulation. 1998;97:535–43.

    Article  CAS  Google Scholar 

  3. Metz LD, Beattie M, Hom R, Redberg RF, Grady D, Fleischmann KE. The prognostic value of normal exercise myocardial perfusion imaging and exercise echocardiography: A meta-analysis. J Am Coll Cardiol. 2007;49:227–37.

    Article  Google Scholar 

  4. Redberg RF. Stress testing in the emergency department: Not which test but whether any test should be done. JAMA Intern Med. 2015;175:436.

    Article  Google Scholar 

  5. Foy AJ, Liu G, Davidson WR Jr, Sciamanna C, Leslie DL. Comparative effectiveness of diagnostic testing strategies in emergency department patients with chest pain: An analysis of downstream testing, interventions, and outcomes. JAMA Intern Med. 2015;175:428–36.

    Article  Google Scholar 

  6. Prasad V, Cheung M, Cifu A. Chest pain in the emergency department: The case against our current practice of routine noninvasive testing. Arch Intern Med. 2012;172:1506–9.

    Article  Google Scholar 

  7. Donaldson MS, Corrigan JM, Kohn LT. To err is human: building a safer health system. Vol 6: National Academies Press; 2000.

  8. Weiskopf NG, Weng C. Methods and dimensions of electronic health record data quality assessment: Enabling reuse for clinical research. J Am Med Inform Assoc. 2013;20:144–51.

    Article  Google Scholar 

  9. Zheng C, Rashid N, Wu YL, et al. Using natural language processing and machine learning to identify gout flares from electronic clinical notes. Arthritis Care Res (Hoboken). 2014;66:1740–8.

    Article  Google Scholar 

  10. Zheng C, Rashid N, Koblick R, An J. Medication extraction from electronic clinical notes in an integrated health system: A study on aspirin use in patients with nonvalvular atrial fibrillation. Clin Ther. 2015;37:2048–2058.e2042.

    Article  Google Scholar 

  11. Xie F, Zheng C, Yuh-Jer Shen A, Chen W. Extracting and analyzing ejection fraction values from electronic echocardiography reports in a large health maintenance organization. Health Inform J. 2017;23:319–28.

    Article  Google Scholar 

  12. An J, Niu F, Zheng C, et al. Warfarin management and outcomes in patients with nonvalvular atrial fibrillation within an integrated health care system. J Manag Care Spec Pharm. 2017;23:700–12.

    PubMed  Google Scholar 

  13. Zheng C, Sun BC, Wu YL, et al. Automated identification and extraction of exercise treadmill test results. J Am Heart Assoc. 2020;9:e014940.

    Article  Google Scholar 

  14. Levy AE, Shah NR, Matheny ME, Reeves RM, Gobbel GT, Bradley SM. Determining post-test risk in a national sample of stress nuclear myocardial perfusion imaging reports: Implications for natural language processing tools. J Nucl Cardiol. 2018;26:1878–85.

    Article  Google Scholar 

  15. Sharp AL, Wu YL, Shen E, et al. The HEART score for suspected acute coronary syndrome in U.S. emergency departments. J Am Coll Cardiol. 2018;72:1875–7.

    Article  Google Scholar 

  16. Naing L, Winn T, Rusli B. Practical issues in calculating the sample size for prevalence studies. Arch Orofac Sci. 2006;1:9–14.

    Google Scholar 

  17. Hermann LK, Newman DH, Pleasant WA, et al. Yield of routine provocative cardiac testing among patients in an emergency department-based chest pain unit. JAMA Intern Med. 2013;173:1128–33.

    Article  Google Scholar 

  18. Duvall WL, Wijetunga MN, Klein TM, et al. Stress-only Tc-99m myocardial perfusion imaging in an emergency department chest pain unit. J Emerg Med. 2012;42:642–50.

    Article  Google Scholar 

  19. Cremer PC, Khalaf S, Agarwal S, et al. Myocardial perfusion imaging in emergency department patients with negative cardiac biomarkers: Yield for detecting ischemia, short-term events, and impact of downstream revascularization on mortality. Circ Cardiovasc Imaging. 2014;7:912–9.

    Article  Google Scholar 

  20. McHugh ML. Interrater reliability: The kappa statistic. Biochem Med (Zagreb). 2012;22:276–82.

    Article  Google Scholar 

  21. Shrout PE, Fleiss JL. Intraclass correlations: Uses in assessing rater reliability. Psychol Bull. 1979;86:420–8.

    Article  CAS  Google Scholar 

  22. Tilkemeier PL, Bourque J, Doukky R, Sanghani R, Weinberg RL. ASNC imaging guidelines for nuclear cardiology procedures: Standardized reporting of nuclear cardiology procedures. J Nucl Cardiol. 2017;24:2064–128.

    Article  Google Scholar 

  23. Kontos MC, Diercks DB, Kirk JD. Emergency department and office-based evaluation of patients with chest pain. Mayo Clin Proc. 2010;85:284–99.

    Article  Google Scholar 

  24. Sokolova M, Lapalme G. A systematic analysis of performance measures for classification tasks. Inf Process Manag. 2009;45:427–37.

    Article  Google Scholar 

  25. Sharp AL, Baecker AS, Shen E, et al. Effect of a HEART care pathway on chest pain management within an integrated health system. Ann Emerg Med. 2019;74:171–80.

    Article  Google Scholar 

  26. Dey D, Slomka PJ, Leeson P, et al. Artificial intelligence in cardiovascular imaging: JACC state-of-the-art review. J Am Coll Cardiol. 2019;73:1317–35.

    Article  Google Scholar 

  27. Al’Aref SJ, Anchouche K, Singh G, et al. Clinical applications of machine learning in cardiovascular disease and its relevance to cardiac imaging. Eur Heart J. 2019;40:1975–86.

    Article  Google Scholar 

  28. Udelson JE, Beshansky JR, Ballin DS, et al. Myocardial perfusion imaging for evaluation and triage of patients with suspected acute cardiac ischemia: A randomized controlled trial. JAMA. 2002;288:2693–700.

    Article  Google Scholar 

  29. Lim SH, Anantharaman V, Sundram F, et al. Stress myocardial perfusion imaging for the evaluation and triage of chest pain in the emergency department: A randomized controlled trial. J Nucl Cardiol. 2013;20:1002–12.

    Article  Google Scholar 

  30. Nabi F, Chang SM, Xu J, Gigliotti E, Mahmarian JJ. Assessing risk in acute chest pain: The value of stress myocardial perfusion imaging in patients admitted through the emergency department. J Nucl Cardiol. 2012;19:233–43.

    Article  Google Scholar 

  31. Berman DS, Kang X, Hayes SW, et al. Adenosine myocardial perfusion single-photon emission computed tomography in women compared with men. Impact of diabetes mellitus on incremental prognostic value and effect on patient management. J Am Coll Cardiol. 2003;41:1125–33.

    Article  Google Scholar 

  32. Navare SM, Mather JF, Shaw LJ, Fowler MS, Heller GV. Comparison of risk stratification with pharmacologic and exercise stress myocardial perfusion imaging: A meta-analysis. J Nucl Cardiol. 2004;11:551–61.

    Article  Google Scholar 

  33. 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.

    Article  Google Scholar 

  34. Bhuiya FA, Pitts SR, McCaig LF. Emergency department visits for chest pain and abdominal pain: United States, 1999–2008. NCHS Data Brief. 2010;43:1–8.

    Google Scholar 

  35. Douglas PS, Hendel RC, Cummings JE, et al. ACCF/ACR/AHA/ASE/ASNC/HRS/NASCI/RSNA/SAIP/SCAI/SCCT/SCMR 2008 health policy statement on structured reporting in cardiovascular imaging. J Am Coll Cardiol. 2009;53:76–90.

    Article  Google Scholar 

  36. Nobel JM, Kok EM, Robben SGF. Redefining the structure of structured reporting in radiology. Insights Imaging. 2020;11:10.

    Article  Google Scholar 

  37. Wu E, Holly TA. Nuclear cardiology reporting: Leaving an impression. J Nucl Cardiol. 2019;26:1886–7.

    Article  Google Scholar 

  38. Maddux PT, Farrell MB, Ewing JA, Tilkemeier PL. Improved compliance with reporting standards: A retrospective analysis of Intersocietal Accreditation Commission Nuclear Cardiology Laboratories. J Nucl Cardiol. 2018;25:986–94.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Research and Evaluation Department, Kaiser Permanente Southern California, 100 S Los Robles Ave, 2nd Floor, Pasadena, CA, 91101, USA

    Chengyi Zheng PhD MS, Yi-Lin Wu MS, Aniket A. Kawatkar PhD MS, Visanee V. Musigdilok MPH & Adam L. Sharp MD MS

  2. Department of Emergency Medicine and Leonard Davis Institute, University of Pennsylvania, Philadelphia, PA, USA

    Benjamin C. Sun MD MPP

  3. Knight Cardiovascular Institute, Oregon Health and Science University, Portland, OR, USA

    Maros Ferencik MD PhD MCR

  4. Division of Cardiology, Kaiser Permanente Southern California, Los Angeles Medical Center, Los Angeles, CA, USA

    Ming-Sum Lee MD PhD

  5. Division of Cardiology, University of California, San Francisco, San Francisco, CA, USA

    Rita F. Redberg MD MSc

Authors
  1. Chengyi Zheng PhD MS
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Benjamin C. Sun MD MPP
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yi-Lin Wu MS
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Maros Ferencik MD PhD MCR
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Ming-Sum Lee MD PhD
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Rita F. Redberg MD MSc
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Aniket A. Kawatkar PhD MS
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Visanee V. Musigdilok MPH
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Adam L. Sharp MD MS
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Chengyi Zheng PhD MS.

Ethics declarations

Disclosures

This work was supported by the National Heart, Lung, and Blood Institute of the National Institutes of Health under Award Number R01HL134647. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health. Author, B.C.S., was a consultant for Medtronic. The remaining authors have no conflicts of interest to report.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Funding

This work was supported by the National Heart, Lung, and Blood Institute of the National Institutes of Health under Award Number R01HL134647.

The authors have also provided an audio summary of the article, which is available to download as ESM, or to listen to via the JNC/ASNC Podcast.

Electronic supplementary material

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zheng, C., Sun, B.C., Wu, YL. et al. Automated abstraction of myocardial perfusion imaging reports using natural language processing. J. Nucl. Cardiol. 29, 1178–1187 (2022). https://doi.org/10.1007/s12350-020-02401-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12350-020-02401-z

Keywords

Search

Navigation