Clinical utility of automated assessment of left ventricular ejection fraction using artificial intelligence-assisted border detection

Hind Rahmouni, Bonnie Ky, Ted Plappert, Kevin Duffy, Susan E. Wiegers, Victor A. Ferrari, Martin G. Keane, James N. Kirkpatrick, Frank E. Silvestry, Martin St. John Sutton

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

Background: Ejection fraction (EF) calculated from 2-dimensional echocardiography provides important prognostic and therapeutic information in patients with heart disease. However, quantification of EF requires planimetry and is time-consuming. As a result, visual assessment is frequently used but is subjective and requires extensive experience. New computer software to assess EF automatically is now available and could be used routinely in busy digital laboratories (>15 000 studies per year) and in core laboratories running large clinical trials. We tested Siemens AutoEF software (Siemens Medical Solutions, Erlangen, Germany) to determine whether it correlated with visual estimates of EF, manual planimetry, and cardiac magnetic resonance (CMR). Methods: Siemens AutoEF is based on learned patterns and artificial intelligence. An expert and a novice reader assessed EF visually by reviewing transthoracic echocardiograms from consecutive patients. An experienced sonographer quantified EF in all studies using Simpson's method of disks. AutoEF results were compared to CMR. Results: Ninety-two echocardiograms were analyzed. Visual assessment by the expert (R = 0.86) and the novice reader (R = 0.80) correlated more closely with manual planimetry using Simpson's method than did AutoEF (R = 0.64). The correlation between AutoEF and CMR was 0.63, 0.28, and 0.51 for EF, end-diastolic and end-systolic volumes, respectively. Conclusion: The discrepancies in EF estimates between AutoEF and manual tracing using Simpson's method and between AutoEF and CMR preclude routine clinical use of AutoEF until it has been validated in a number of large, busy echocardiographic laboratories. Visual assessment of EF, with its strong correlation with quantitative EF, underscores its continued clinical utility.

Original languageEnglish (US)
Pages (from-to)562-570
Number of pages9
JournalAmerican Heart Journal
Volume155
Issue number3
DOIs
StatePublished - Mar 2008
Externally publishedYes

Fingerprint

Artificial Intelligence
Stroke Volume
Magnetic Resonance Spectroscopy
Software
Germany
Echocardiography
Heart Diseases
Clinical Trials
Therapeutics

ASJC Scopus subject areas

  • Cardiology and Cardiovascular Medicine

Cite this

Clinical utility of automated assessment of left ventricular ejection fraction using artificial intelligence-assisted border detection. / Rahmouni, Hind; Ky, Bonnie; Plappert, Ted; Duffy, Kevin; Wiegers, Susan E.; Ferrari, Victor A.; Keane, Martin G.; Kirkpatrick, James N.; Silvestry, Frank E.; St. John Sutton, Martin.

In: American Heart Journal, Vol. 155, No. 3, 03.2008, p. 562-570.

Research output: Contribution to journalArticle

Rahmouni, H, Ky, B, Plappert, T, Duffy, K, Wiegers, SE, Ferrari, VA, Keane, MG, Kirkpatrick, JN, Silvestry, FE & St. John Sutton, M 2008, 'Clinical utility of automated assessment of left ventricular ejection fraction using artificial intelligence-assisted border detection', American Heart Journal, vol. 155, no. 3, pp. 562-570. https://doi.org/10.1016/j.ahj.2007.11.002
Rahmouni, Hind ; Ky, Bonnie ; Plappert, Ted ; Duffy, Kevin ; Wiegers, Susan E. ; Ferrari, Victor A. ; Keane, Martin G. ; Kirkpatrick, James N. ; Silvestry, Frank E. ; St. John Sutton, Martin. / Clinical utility of automated assessment of left ventricular ejection fraction using artificial intelligence-assisted border detection. In: American Heart Journal. 2008 ; Vol. 155, No. 3. pp. 562-570.
@article{ad91c3adad974ad496eddc3daff0e94a,
title = "Clinical utility of automated assessment of left ventricular ejection fraction using artificial intelligence-assisted border detection",
abstract = "Background: Ejection fraction (EF) calculated from 2-dimensional echocardiography provides important prognostic and therapeutic information in patients with heart disease. However, quantification of EF requires planimetry and is time-consuming. As a result, visual assessment is frequently used but is subjective and requires extensive experience. New computer software to assess EF automatically is now available and could be used routinely in busy digital laboratories (>15 000 studies per year) and in core laboratories running large clinical trials. We tested Siemens AutoEF software (Siemens Medical Solutions, Erlangen, Germany) to determine whether it correlated with visual estimates of EF, manual planimetry, and cardiac magnetic resonance (CMR). Methods: Siemens AutoEF is based on learned patterns and artificial intelligence. An expert and a novice reader assessed EF visually by reviewing transthoracic echocardiograms from consecutive patients. An experienced sonographer quantified EF in all studies using Simpson's method of disks. AutoEF results were compared to CMR. Results: Ninety-two echocardiograms were analyzed. Visual assessment by the expert (R = 0.86) and the novice reader (R = 0.80) correlated more closely with manual planimetry using Simpson's method than did AutoEF (R = 0.64). The correlation between AutoEF and CMR was 0.63, 0.28, and 0.51 for EF, end-diastolic and end-systolic volumes, respectively. Conclusion: The discrepancies in EF estimates between AutoEF and manual tracing using Simpson's method and between AutoEF and CMR preclude routine clinical use of AutoEF until it has been validated in a number of large, busy echocardiographic laboratories. Visual assessment of EF, with its strong correlation with quantitative EF, underscores its continued clinical utility.",
author = "Hind Rahmouni and Bonnie Ky and Ted Plappert and Kevin Duffy and Wiegers, {Susan E.} and Ferrari, {Victor A.} and Keane, {Martin G.} and Kirkpatrick, {James N.} and Silvestry, {Frank E.} and {St. John Sutton}, Martin",
year = "2008",
month = "3",
doi = "10.1016/j.ahj.2007.11.002",
language = "English (US)",
volume = "155",
pages = "562--570",
journal = "American Heart Journal",
issn = "0002-8703",
publisher = "Mosby Inc.",
number = "3",

}

TY - JOUR

T1 - Clinical utility of automated assessment of left ventricular ejection fraction using artificial intelligence-assisted border detection

AU - Rahmouni, Hind

AU - Ky, Bonnie

AU - Plappert, Ted

AU - Duffy, Kevin

AU - Wiegers, Susan E.

AU - Ferrari, Victor A.

AU - Keane, Martin G.

AU - Kirkpatrick, James N.

AU - Silvestry, Frank E.

AU - St. John Sutton, Martin

PY - 2008/3

Y1 - 2008/3

N2 - Background: Ejection fraction (EF) calculated from 2-dimensional echocardiography provides important prognostic and therapeutic information in patients with heart disease. However, quantification of EF requires planimetry and is time-consuming. As a result, visual assessment is frequently used but is subjective and requires extensive experience. New computer software to assess EF automatically is now available and could be used routinely in busy digital laboratories (>15 000 studies per year) and in core laboratories running large clinical trials. We tested Siemens AutoEF software (Siemens Medical Solutions, Erlangen, Germany) to determine whether it correlated with visual estimates of EF, manual planimetry, and cardiac magnetic resonance (CMR). Methods: Siemens AutoEF is based on learned patterns and artificial intelligence. An expert and a novice reader assessed EF visually by reviewing transthoracic echocardiograms from consecutive patients. An experienced sonographer quantified EF in all studies using Simpson's method of disks. AutoEF results were compared to CMR. Results: Ninety-two echocardiograms were analyzed. Visual assessment by the expert (R = 0.86) and the novice reader (R = 0.80) correlated more closely with manual planimetry using Simpson's method than did AutoEF (R = 0.64). The correlation between AutoEF and CMR was 0.63, 0.28, and 0.51 for EF, end-diastolic and end-systolic volumes, respectively. Conclusion: The discrepancies in EF estimates between AutoEF and manual tracing using Simpson's method and between AutoEF and CMR preclude routine clinical use of AutoEF until it has been validated in a number of large, busy echocardiographic laboratories. Visual assessment of EF, with its strong correlation with quantitative EF, underscores its continued clinical utility.

AB - Background: Ejection fraction (EF) calculated from 2-dimensional echocardiography provides important prognostic and therapeutic information in patients with heart disease. However, quantification of EF requires planimetry and is time-consuming. As a result, visual assessment is frequently used but is subjective and requires extensive experience. New computer software to assess EF automatically is now available and could be used routinely in busy digital laboratories (>15 000 studies per year) and in core laboratories running large clinical trials. We tested Siemens AutoEF software (Siemens Medical Solutions, Erlangen, Germany) to determine whether it correlated with visual estimates of EF, manual planimetry, and cardiac magnetic resonance (CMR). Methods: Siemens AutoEF is based on learned patterns and artificial intelligence. An expert and a novice reader assessed EF visually by reviewing transthoracic echocardiograms from consecutive patients. An experienced sonographer quantified EF in all studies using Simpson's method of disks. AutoEF results were compared to CMR. Results: Ninety-two echocardiograms were analyzed. Visual assessment by the expert (R = 0.86) and the novice reader (R = 0.80) correlated more closely with manual planimetry using Simpson's method than did AutoEF (R = 0.64). The correlation between AutoEF and CMR was 0.63, 0.28, and 0.51 for EF, end-diastolic and end-systolic volumes, respectively. Conclusion: The discrepancies in EF estimates between AutoEF and manual tracing using Simpson's method and between AutoEF and CMR preclude routine clinical use of AutoEF until it has been validated in a number of large, busy echocardiographic laboratories. Visual assessment of EF, with its strong correlation with quantitative EF, underscores its continued clinical utility.

UR - http://www.scopus.com/inward/record.url?scp=39149130340&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=39149130340&partnerID=8YFLogxK

U2 - 10.1016/j.ahj.2007.11.002

DO - 10.1016/j.ahj.2007.11.002

M3 - Article

VL - 155

SP - 562

EP - 570

JO - American Heart Journal

JF - American Heart Journal

SN - 0002-8703

IS - 3

ER -