Leveraging Comprehensive Echo Data to Power Artificial Intelligence Models for Handheld Cardiac Ultrasound
Objective: To develop a fully end-to-end deep learning framework capable of estimating left ventricular ejection fraction (LVEF), estimating patient age, and classifying patient sex from echocardiographic videos, including videos collected using handheld cardiac ultrasound (HCU). Patients and Method...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Mayo Clinic Proceedings: Digital Health |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S294976122500001X |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823864251389837312 |
|---|---|
| author | D.M. Anisuzzaman, PhD Jeffrey G. Malins, PhD John I. Jackson, PhD Eunjung Lee, PhD Jwan A. Naser, MBBS Behrouz Rostami, PhD Grace Greason, BA Jared G. Bird, MD Paul A. Friedman, MD Jae K. Oh, MD Patricia A. Pellikka, MD Jeremy J. Thaden, MD Francisco Lopez-Jimenez, MD, MSc, MBA Zachi I. Attia, PhD Sorin V. Pislaru, MD, PhD Garvan C. Kane, MD, PhD |
| author_facet | D.M. Anisuzzaman, PhD Jeffrey G. Malins, PhD John I. Jackson, PhD Eunjung Lee, PhD Jwan A. Naser, MBBS Behrouz Rostami, PhD Grace Greason, BA Jared G. Bird, MD Paul A. Friedman, MD Jae K. Oh, MD Patricia A. Pellikka, MD Jeremy J. Thaden, MD Francisco Lopez-Jimenez, MD, MSc, MBA Zachi I. Attia, PhD Sorin V. Pislaru, MD, PhD Garvan C. Kane, MD, PhD |
| author_sort | D.M. Anisuzzaman, PhD |
| collection | DOAJ |
| description | Objective: To develop a fully end-to-end deep learning framework capable of estimating left ventricular ejection fraction (LVEF), estimating patient age, and classifying patient sex from echocardiographic videos, including videos collected using handheld cardiac ultrasound (HCU). Patients and Methods: Deep learning models were trained using retrospective transthoracic echocardiography (TTE) data collected in Mayo Clinic Rochester and surrounding Mayo Clinic Health System sites (training: 6432 studies and internal validation: 1369 studies). Models were then evaluated using retrospective TTE data from the 3 Mayo Clinic sites (Rochester, n=1970; Arizona, n=1367; Florida, n=1562) before being applied to a prospective dataset of handheld ultrasound and TTE videos collected from 625 patients. Study data were collected between January 1, 2018 and February 29, 2024. Results: Models showed strong performance on the retrospective TTE datasets (LVEF regression: root mean squared error (RMSE)=6.83%, 6.53%, and 6.95% for Rochester, Arizona, and Florida cohorts, respectively; classification of LVEF ≤40% versus LVEF > 40%: area under curve (AUC)=0.962, 0.967, and 0.980 for Rochester, Arizona, and Florida, respectively; age: RMSE=9.44% for Rochester; sex: AUC=0.882 for Rochester), and performed comparably for prospective HCU versus TTE data (LVEF regression: RMSE=6.37% for HCU vs 5.57% for TTE; LVEF classification: AUC=0.974 vs 0.981; age: RMSE=10.35% vs 9.32%; sex: AUC=0.896 vs 0.933). Conclusion: Robust TTE datasets can be used to effectively power HCU deep learning models, which in turn demonstrates focused diagnostic images can be obtained with handheld devices. |
| format | Article |
| id | doaj-art-84e08b1479764eda80534ce7fe8c6ec7 |
| institution | Kabale University |
| issn | 2949-7612 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Mayo Clinic Proceedings: Digital Health |
| spelling | doaj-art-84e08b1479764eda80534ce7fe8c6ec72025-02-09T05:01:50ZengElsevierMayo Clinic Proceedings: Digital Health2949-76122025-03-0131100194Leveraging Comprehensive Echo Data to Power Artificial Intelligence Models for Handheld Cardiac UltrasoundD.M. Anisuzzaman, PhD0Jeffrey G. Malins, PhD1John I. Jackson, PhD2Eunjung Lee, PhD3Jwan A. Naser, MBBS4Behrouz Rostami, PhD5Grace Greason, BA6Jared G. Bird, MD7Paul A. Friedman, MD8Jae K. Oh, MD9Patricia A. Pellikka, MD10Jeremy J. Thaden, MD11Francisco Lopez-Jimenez, MD, MSc, MBA12Zachi I. Attia, PhD13Sorin V. Pislaru, MD, PhD14Garvan C. Kane, MD, PhD15Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MNDepartment of Cardiovascular Medicine, Mayo Clinic, Rochester, MNDepartment of Cardiovascular Medicine, Mayo Clinic, Rochester, MNDepartment of Cardiovascular Medicine, Mayo Clinic, Rochester, MNDepartment of Cardiovascular Medicine, Mayo Clinic, Rochester, MNDepartment of Cardiovascular Medicine, Mayo Clinic, Rochester, MNDepartment of Cardiovascular Medicine, Mayo Clinic, Rochester, MNDepartment of Cardiovascular Medicine, Mayo Clinic, Rochester, MNDepartment of Cardiovascular Medicine, Mayo Clinic, Rochester, MNDepartment of Cardiovascular Medicine, Mayo Clinic, Rochester, MNDepartment of Cardiovascular Medicine, Mayo Clinic, Rochester, MNDepartment of Cardiovascular Medicine, Mayo Clinic, Rochester, MNDepartment of Cardiovascular Medicine, Mayo Clinic, Rochester, MNDepartment of Cardiovascular Medicine, Mayo Clinic, Rochester, MNDepartment of Cardiovascular Medicine, Mayo Clinic, Rochester, MNCorrespondence: Address to Garvan C. Kane, MD, PhD, Chair, Division of Cardiovascular Ultrasound, Department of Cardiovascular Medicine, Gonda 6, Mayo Clinic, 200 First Street SW, Rochester, MN 55905.; Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MNObjective: To develop a fully end-to-end deep learning framework capable of estimating left ventricular ejection fraction (LVEF), estimating patient age, and classifying patient sex from echocardiographic videos, including videos collected using handheld cardiac ultrasound (HCU). Patients and Methods: Deep learning models were trained using retrospective transthoracic echocardiography (TTE) data collected in Mayo Clinic Rochester and surrounding Mayo Clinic Health System sites (training: 6432 studies and internal validation: 1369 studies). Models were then evaluated using retrospective TTE data from the 3 Mayo Clinic sites (Rochester, n=1970; Arizona, n=1367; Florida, n=1562) before being applied to a prospective dataset of handheld ultrasound and TTE videos collected from 625 patients. Study data were collected between January 1, 2018 and February 29, 2024. Results: Models showed strong performance on the retrospective TTE datasets (LVEF regression: root mean squared error (RMSE)=6.83%, 6.53%, and 6.95% for Rochester, Arizona, and Florida cohorts, respectively; classification of LVEF ≤40% versus LVEF > 40%: area under curve (AUC)=0.962, 0.967, and 0.980 for Rochester, Arizona, and Florida, respectively; age: RMSE=9.44% for Rochester; sex: AUC=0.882 for Rochester), and performed comparably for prospective HCU versus TTE data (LVEF regression: RMSE=6.37% for HCU vs 5.57% for TTE; LVEF classification: AUC=0.974 vs 0.981; age: RMSE=10.35% vs 9.32%; sex: AUC=0.896 vs 0.933). Conclusion: Robust TTE datasets can be used to effectively power HCU deep learning models, which in turn demonstrates focused diagnostic images can be obtained with handheld devices.http://www.sciencedirect.com/science/article/pii/S294976122500001X |
| spellingShingle | D.M. Anisuzzaman, PhD Jeffrey G. Malins, PhD John I. Jackson, PhD Eunjung Lee, PhD Jwan A. Naser, MBBS Behrouz Rostami, PhD Grace Greason, BA Jared G. Bird, MD Paul A. Friedman, MD Jae K. Oh, MD Patricia A. Pellikka, MD Jeremy J. Thaden, MD Francisco Lopez-Jimenez, MD, MSc, MBA Zachi I. Attia, PhD Sorin V. Pislaru, MD, PhD Garvan C. Kane, MD, PhD Leveraging Comprehensive Echo Data to Power Artificial Intelligence Models for Handheld Cardiac Ultrasound Mayo Clinic Proceedings: Digital Health |
| title | Leveraging Comprehensive Echo Data to Power Artificial Intelligence Models for Handheld Cardiac Ultrasound |
| title_full | Leveraging Comprehensive Echo Data to Power Artificial Intelligence Models for Handheld Cardiac Ultrasound |
| title_fullStr | Leveraging Comprehensive Echo Data to Power Artificial Intelligence Models for Handheld Cardiac Ultrasound |
| title_full_unstemmed | Leveraging Comprehensive Echo Data to Power Artificial Intelligence Models for Handheld Cardiac Ultrasound |
| title_short | Leveraging Comprehensive Echo Data to Power Artificial Intelligence Models for Handheld Cardiac Ultrasound |
| title_sort | leveraging comprehensive echo data to power artificial intelligence models for handheld cardiac ultrasound |
| url | http://www.sciencedirect.com/science/article/pii/S294976122500001X |
| work_keys_str_mv | AT dmanisuzzamanphd leveragingcomprehensiveechodatatopowerartificialintelligencemodelsforhandheldcardiacultrasound AT jeffreygmalinsphd leveragingcomprehensiveechodatatopowerartificialintelligencemodelsforhandheldcardiacultrasound AT johnijacksonphd leveragingcomprehensiveechodatatopowerartificialintelligencemodelsforhandheldcardiacultrasound AT eunjungleephd leveragingcomprehensiveechodatatopowerartificialintelligencemodelsforhandheldcardiacultrasound AT jwananasermbbs leveragingcomprehensiveechodatatopowerartificialintelligencemodelsforhandheldcardiacultrasound AT behrouzrostamiphd leveragingcomprehensiveechodatatopowerartificialintelligencemodelsforhandheldcardiacultrasound AT gracegreasonba leveragingcomprehensiveechodatatopowerartificialintelligencemodelsforhandheldcardiacultrasound AT jaredgbirdmd leveragingcomprehensiveechodatatopowerartificialintelligencemodelsforhandheldcardiacultrasound AT paulafriedmanmd leveragingcomprehensiveechodatatopowerartificialintelligencemodelsforhandheldcardiacultrasound AT jaekohmd leveragingcomprehensiveechodatatopowerartificialintelligencemodelsforhandheldcardiacultrasound AT patriciaapellikkamd leveragingcomprehensiveechodatatopowerartificialintelligencemodelsforhandheldcardiacultrasound AT jeremyjthadenmd leveragingcomprehensiveechodatatopowerartificialintelligencemodelsforhandheldcardiacultrasound AT franciscolopezjimenezmdmscmba leveragingcomprehensiveechodatatopowerartificialintelligencemodelsforhandheldcardiacultrasound AT zachiiattiaphd leveragingcomprehensiveechodatatopowerartificialintelligencemodelsforhandheldcardiacultrasound AT sorinvpislarumdphd leveragingcomprehensiveechodatatopowerartificialintelligencemodelsforhandheldcardiacultrasound AT garvanckanemdphd leveragingcomprehensiveechodatatopowerartificialintelligencemodelsforhandheldcardiacultrasound |