Diagnostic accuracy of point-of-care ultrasound with artificial intelligence-assisted assessment of left ventricular ejection fraction
Abstract Focused cardiac ultrasound (FoCUS) is becoming standard practice in a wide spectrum of clinical settings. There is limited data evaluating the real-world use of FoCUS with artificial intelligence (AI). Our objective was to determine the accuracy of FoCUS AI-assisted left ventricular ejectio...
| Main Authors: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-10-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-023-00945-1 |
| _version_ | 1797647188832026624 |
|---|---|
| author | Pouya Motazedian Jeffrey A. Marbach Graeme Prosperi-Porta Simon Parlow Pietro Di Santo Omar Abdel-Razek Richard Jung William B. Bradford Miranda Tsang Michael Hyon Stefano Pacifici Sharanya Mohanty F. Daniel Ramirez Gordon S. Huggins Trevor Simard Stephanie Hon Benjamin Hibbert |
| author_facet | Pouya Motazedian Jeffrey A. Marbach Graeme Prosperi-Porta Simon Parlow Pietro Di Santo Omar Abdel-Razek Richard Jung William B. Bradford Miranda Tsang Michael Hyon Stefano Pacifici Sharanya Mohanty F. Daniel Ramirez Gordon S. Huggins Trevor Simard Stephanie Hon Benjamin Hibbert |
| author_sort | Pouya Motazedian |
| collection | DOAJ |
| description | Abstract Focused cardiac ultrasound (FoCUS) is becoming standard practice in a wide spectrum of clinical settings. There is limited data evaluating the real-world use of FoCUS with artificial intelligence (AI). Our objective was to determine the accuracy of FoCUS AI-assisted left ventricular ejection fraction (LVEF) assessment and compare its accuracy between novice and experienced users. In this prospective, multicentre study, participants requiring a transthoracic echocardiogram (TTE) were recruited to have a FoCUS done by a novice or experienced user. The AI-assisted device calculated LVEF at the bedside, which was subsequently compared to TTE. 449 participants were enrolled with 424 studies included in the final analysis. The overall intraclass coefficient was 0.904, and 0.921 in the novice (n = 208) and 0.845 in the experienced (n = 216) cohorts. There was a significant bias of 0.73% towards TTE (p = 0.005) with a level of agreement of 11.2%. Categorical grading of LVEF severity had excellent agreement to TTE (weighted kappa = 0.83). The area under the curve (AUC) was 0.98 for identifying an abnormal LVEF (<50%) with a sensitivity of 92.8%, specificity of 92.3%, negative predictive value (NPV) of 0.97 and a positive predictive value (PPV) of 0.83. In identifying severe dysfunction (<30%) the AUC was 0.99 with a sensitivity of 78.1%, specificity of 98.0%, NPV of 0.98 and PPV of 0.76. Here we report that FoCUS AI-assisted LVEF assessments provide highly reproducible LVEF estimations in comparison to formal TTE. This finding was consistent among senior and novice echocardiographers suggesting applicability in a variety of clinical settings. |
| first_indexed | 2024-03-11T15:12:42Z |
| format | Article |
| id | doaj.art-56473481782744538db8382c211d65a4 |
| institution | Directory Open Access Journal |
| issn | 2398-6352 |
| language | English |
| last_indexed | 2024-03-11T15:12:42Z |
| publishDate | 2023-10-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj.art-56473481782744538db8382c211d65a42023-10-29T12:37:21ZengNature Portfolionpj Digital Medicine2398-63522023-10-01611710.1038/s41746-023-00945-1Diagnostic accuracy of point-of-care ultrasound with artificial intelligence-assisted assessment of left ventricular ejection fractionPouya Motazedian0Jeffrey A. Marbach1Graeme Prosperi-Porta2Simon Parlow3Pietro Di Santo4Omar Abdel-Razek5Richard Jung6William B. Bradford7Miranda Tsang8Michael Hyon9Stefano Pacifici10Sharanya Mohanty11F. Daniel Ramirez12Gordon S. Huggins13Trevor Simard14Stephanie Hon15Benjamin Hibbert16CAPITAL Research Group, Division of Cardiology, University of Ottawa Heart Institute, OttawaDivision of Cardiology, Knight Cardiovascular Institute, Oregon Health and Sciences UniversityCAPITAL Research Group, Division of Cardiology, University of Ottawa Heart Institute, OttawaCAPITAL Research Group, Division of Cardiology, University of Ottawa Heart Institute, OttawaCAPITAL Research Group, Division of Cardiology, University of Ottawa Heart Institute, OttawaCAPITAL Research Group, Division of Cardiology, University of Ottawa Heart Institute, OttawaCAPITAL Research Group, Division of Cardiology, University of Ottawa Heart Institute, OttawaDivision of Cardiology, Tufts Medical Center and Tufts University School of MedicineDivision of Cardiology, Tufts Medical Center and Tufts University School of MedicineDivision of Cardiology, Tufts Medical Center and Tufts University School of MedicineDivision of Cardiology, Tufts Medical Center and Tufts University School of MedicineDivision of Cardiology, Tufts Medical Center and Tufts University School of MedicineDivision of Cardiology, University of Ottawa Heart Institute, OttawaDivision of Cardiology, Tufts Medical Center and Tufts University School of MedicineDepartment of Cardiovascular Medicine, Mayo ClinicDivision of Pulmonary and Critical Care Medicine, Tufts Medical Center and Tufts University School of MedicineDepartment of Cardiovascular Medicine, Mayo ClinicAbstract Focused cardiac ultrasound (FoCUS) is becoming standard practice in a wide spectrum of clinical settings. There is limited data evaluating the real-world use of FoCUS with artificial intelligence (AI). Our objective was to determine the accuracy of FoCUS AI-assisted left ventricular ejection fraction (LVEF) assessment and compare its accuracy between novice and experienced users. In this prospective, multicentre study, participants requiring a transthoracic echocardiogram (TTE) were recruited to have a FoCUS done by a novice or experienced user. The AI-assisted device calculated LVEF at the bedside, which was subsequently compared to TTE. 449 participants were enrolled with 424 studies included in the final analysis. The overall intraclass coefficient was 0.904, and 0.921 in the novice (n = 208) and 0.845 in the experienced (n = 216) cohorts. There was a significant bias of 0.73% towards TTE (p = 0.005) with a level of agreement of 11.2%. Categorical grading of LVEF severity had excellent agreement to TTE (weighted kappa = 0.83). The area under the curve (AUC) was 0.98 for identifying an abnormal LVEF (<50%) with a sensitivity of 92.8%, specificity of 92.3%, negative predictive value (NPV) of 0.97 and a positive predictive value (PPV) of 0.83. In identifying severe dysfunction (<30%) the AUC was 0.99 with a sensitivity of 78.1%, specificity of 98.0%, NPV of 0.98 and PPV of 0.76. Here we report that FoCUS AI-assisted LVEF assessments provide highly reproducible LVEF estimations in comparison to formal TTE. This finding was consistent among senior and novice echocardiographers suggesting applicability in a variety of clinical settings.https://doi.org/10.1038/s41746-023-00945-1 |
| spellingShingle | Pouya Motazedian Jeffrey A. Marbach Graeme Prosperi-Porta Simon Parlow Pietro Di Santo Omar Abdel-Razek Richard Jung William B. Bradford Miranda Tsang Michael Hyon Stefano Pacifici Sharanya Mohanty F. Daniel Ramirez Gordon S. Huggins Trevor Simard Stephanie Hon Benjamin Hibbert Diagnostic accuracy of point-of-care ultrasound with artificial intelligence-assisted assessment of left ventricular ejection fraction npj Digital Medicine |
| title | Diagnostic accuracy of point-of-care ultrasound with artificial intelligence-assisted assessment of left ventricular ejection fraction |
| title_full | Diagnostic accuracy of point-of-care ultrasound with artificial intelligence-assisted assessment of left ventricular ejection fraction |
| title_fullStr | Diagnostic accuracy of point-of-care ultrasound with artificial intelligence-assisted assessment of left ventricular ejection fraction |
| title_full_unstemmed | Diagnostic accuracy of point-of-care ultrasound with artificial intelligence-assisted assessment of left ventricular ejection fraction |
| title_short | Diagnostic accuracy of point-of-care ultrasound with artificial intelligence-assisted assessment of left ventricular ejection fraction |
| title_sort | diagnostic accuracy of point of care ultrasound with artificial intelligence assisted assessment of left ventricular ejection fraction |
| url | https://doi.org/10.1038/s41746-023-00945-1 |
| work_keys_str_mv | AT pouyamotazedian diagnosticaccuracyofpointofcareultrasoundwithartificialintelligenceassistedassessmentofleftventricularejectionfraction AT jeffreyamarbach diagnosticaccuracyofpointofcareultrasoundwithartificialintelligenceassistedassessmentofleftventricularejectionfraction AT graemeprosperiporta diagnosticaccuracyofpointofcareultrasoundwithartificialintelligenceassistedassessmentofleftventricularejectionfraction AT simonparlow diagnosticaccuracyofpointofcareultrasoundwithartificialintelligenceassistedassessmentofleftventricularejectionfraction AT pietrodisanto diagnosticaccuracyofpointofcareultrasoundwithartificialintelligenceassistedassessmentofleftventricularejectionfraction AT omarabdelrazek diagnosticaccuracyofpointofcareultrasoundwithartificialintelligenceassistedassessmentofleftventricularejectionfraction AT richardjung diagnosticaccuracyofpointofcareultrasoundwithartificialintelligenceassistedassessmentofleftventricularejectionfraction AT williambbradford diagnosticaccuracyofpointofcareultrasoundwithartificialintelligenceassistedassessmentofleftventricularejectionfraction AT mirandatsang diagnosticaccuracyofpointofcareultrasoundwithartificialintelligenceassistedassessmentofleftventricularejectionfraction AT michaelhyon diagnosticaccuracyofpointofcareultrasoundwithartificialintelligenceassistedassessmentofleftventricularejectionfraction AT stefanopacifici diagnosticaccuracyofpointofcareultrasoundwithartificialintelligenceassistedassessmentofleftventricularejectionfraction AT sharanyamohanty diagnosticaccuracyofpointofcareultrasoundwithartificialintelligenceassistedassessmentofleftventricularejectionfraction AT fdanielramirez diagnosticaccuracyofpointofcareultrasoundwithartificialintelligenceassistedassessmentofleftventricularejectionfraction AT gordonshuggins diagnosticaccuracyofpointofcareultrasoundwithartificialintelligenceassistedassessmentofleftventricularejectionfraction AT trevorsimard diagnosticaccuracyofpointofcareultrasoundwithartificialintelligenceassistedassessmentofleftventricularejectionfraction AT stephaniehon diagnosticaccuracyofpointofcareultrasoundwithartificialintelligenceassistedassessmentofleftventricularejectionfraction AT benjaminhibbert diagnosticaccuracyofpointofcareultrasoundwithartificialintelligenceassistedassessmentofleftventricularejectionfraction |