Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 May 24;2(3):453-462.
doi: 10.1016/j.mcpdig.2024.03.009. eCollection 2024 Sep.

Electrocardiogram Signal Analysis With a Machine Learning Model Predicts the Presence of Pulmonary Embolism With Accuracy Dependent on Embolism Burden

Waldemar E Wysokinski  1 , Ryan A Meverden  1 , Francisco Lopez-Jimenez  1 , David M Harmon  1 , Betsy J Medina Inojosa  1 , Abraham Baez Suarez  1 , Kan Liu  1 , Jose R Medina Inojosa  1 , Ana I Casanegra  1 , Robert D McBane  1 , Damon E Houghton  1
Affiliations

Electrocardiogram Signal Analysis With a Machine Learning Model Predicts the Presence of Pulmonary Embolism With Accuracy Dependent on Embolism Burden

Waldemar E Wysokinski et al. Mayo Clin Proc Digit Health. .

Abstract

Objective: To develop an artificial intelligence deep neural network (AI-DNN) algorithm to analyze 12-lead electrocardiogram (ECG) for detection of acute pulmonary embolism (PE) and PE categories.

Patients and methods: A cohort of patients seen between January 1, 1999, and December 31, 2020, from across the Mayo Clinic Enterprise with computed tomography pulmonary angiogram (CTPA) and ECG performed ±6 hours was identified. Natural language processing algorithms were applied to radiology reports to determine the diagnosis of acute PE, acute right ventricular strain pulmonary embolism (RVSPE), saddle pulmonary embolism (SADPE), or no PE. Diagnostic performance parameters of the AI-DNN reported were area under the receiver operating characteristics curve (AUROC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV).

Results: A cohort of patients with CTPA report and ECG consisted of 79,894 patients including 7423 (9.3%) with acute PE, among whom 1138 patients had RVSPE or SADPE. Artificial intelligence deep neural network predicted acute PE with a modest accuracy of AUROC of 0.69 (95% CI, 0.68-0.71), sensitivity of 63.5%, specificity of 64.7%, PPV of 15.6%, and NPV of 94.5%. The AI-DNN prediction using the same algorithm for RVSPE or SADPE was higher (AUROC, 0.84; 95% CI, 0.81-0.86) with a sensitivity of 80.8%, specificity of 64.7.8%, PPV of 3.5%, and NPV of 99.5%.

Conclusion: An AI-based analysis of 12-lead ECG shows modest detection power for acute PE in patients who underwent CTPA, with higher accuracy for high-risk PE. Moreover, with the high NPV, it has the clinical potential to exclude high-risk PE quickly and correctly.

PubMed Disclaimer

Conflict of interest statement

Given his role as Editor-in-Chief, Dr Francisco Lopez-Jimenez had no involvement in the peer-review of this article and had no access to information regarding its peer-review. Full responsibility for the editorial process for this article was delegated to an unaffiliated Editor. Dr Harmon reports grants from NIH StARR R38 grant (NHLBI): NIH 5R38HL150086-02. Dr Houghton reports grants from Gordan & Betty Moore Foundation, American Society of Hematology, Bayer, Hemostasis & Thrombosis Research Society, Noaber Foundation, Veralox to the institution. The other authors report no competing interests.

Figures

Figure
Figure
Receiver operating characteristics curve and resulting area under the curve for patients with any acute pulmonary embolism (red line) and subgroup of patients with severe pulmonary embolism with right ventricle strain and/or with saddle pulmonary embolism (blue line).
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Heit J.A., Ashrani A., Crusan D.J., McBane R.D., Petterson T.M., Bailey K.R. Reasons for the persistent incidence of venous thromboembolism. Thromb Haemost. 2017;117(2):390–400. doi: 10.1160/TH16-07-0509. - DOI - PMC - PubMed
    1. Sista A.K., Kuo W.T., Schiebler M., Madoff D.C. Stratification, imaging, and management of acute massive and submassive pulmonary embolism. Radiology. 2017;284(1):5–24. doi: 10.1148/radiol.2017151978. - DOI - PubMed
    1. Feng L.B., Pines J.M., Yusuf H.R., Grosse S.D. U.S. trends in computed tomography use and diagnoses in emergency department visits by patients with symptoms suggestive of pulmonary embolism, 2001-2009. Acad Emerg Med. 2013;20(10):1033–1040. doi: 10.1111/acem.12221. - DOI - PMC - PubMed
    1. Kline J.A., Garrett J.S., Sarmiento E.J., Strachan C.C., Courtney D.M. Over-testing for suspected pulmonary embolism in American emergency departments: the continuing epidemic. Circ Cardiovasc Qual Outcomes. 2020;13(1) doi: 10.1161/CIRCOUTCOMES.119.005753. - DOI - PubMed
    1. Jaff M.R., McMurtry M.S., Archer S.L., et al. Management of massive and submassive pulmonary embolism, iliofemoral deep vein thrombosis, and chronic thromboembolic pulmonary hypertension: a scientific statement from the American Heart Association. Circulation. 2011;123(16):1788–1830. doi: 10.1161/CIR.0b013e318214914f. - DOI - PubMed

LinkOut - more resources