Accuracy and Efficacy of Artificial Intelligence-Derived Automatic Measurements of Transthoracic Echocardiography in Routine Clinical Practice
<b>Background</b>: Transthoracic echocardiography (TTE) is the gold standard modality for evaluating cardiac morphology, function, and hemodynamics in clinical practice. While artificial intelligence (AI) is expected to contribute to improved accuracy and is being applied clinically, its...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-03-01
|
| Series: | Journal of Clinical Medicine |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0383/13/7/1861 |
| _version_ | 1797212463069921280 |
|---|---|
| author | Noriko Shiokawa Masaki Izumo Toshio Shimamura Yui Kurosaka Yukio Sato Takanori Okamura Yoshihiro Johnny Akashi |
| author_facet | Noriko Shiokawa Masaki Izumo Toshio Shimamura Yui Kurosaka Yukio Sato Takanori Okamura Yoshihiro Johnny Akashi |
| author_sort | Noriko Shiokawa |
| collection | DOAJ |
| description | <b>Background</b>: Transthoracic echocardiography (TTE) is the gold standard modality for evaluating cardiac morphology, function, and hemodynamics in clinical practice. While artificial intelligence (AI) is expected to contribute to improved accuracy and is being applied clinically, its impact on daily clinical practice has not been fully evaluated. <b>Methods</b>: We retrospectively examined 30 consecutive patients who underwent AI-equipped TTE at a single institution. All patients underwent manual and automatic measurements of TTE parameters using the AI-equipped TTE. Measurements were performed by three sonographers with varying experience levels: beginner, intermediate, and expert. <b>Results:</b> A comparison between the manual and automatic measurements assessed by the experts showed extremely high agreement in the left ventricular (LV) filling velocities (E wave: r = 0.998, A wave: r = 0.996; both <i>p</i> < 0.001). The automated measurements of LV end-diastolic and end-systolic diameters were slightly smaller (−2.41 mm and −1.19 mm) than the manual measurements, although without significant differences, and both methods showing high agreement (r = 0.942 and 0.977, both <i>p</i> < 0.001). However, LV wall thickness showed low agreement between the automated and manual measurements (septum: r = 0.670, posterior: r = 0.561; both <i>p</i> < 0.01), with automated measurements tending to be larger. Regarding interobserver variabilities, statistically significant agreement was observed among the measurements of expert, intermediate, and beginner sonographers for all the measurements. In terms of measurement time, automatic measurement significantly reduced measurement time compared to manual measurement (<i>p</i> < 0.001). <b>Conclusions:</b> This preliminary study confirms the accuracy and efficacy of AI-equipped TTE in routine clinical practice. A multicenter study with a larger sample size is warranted. |
| first_indexed | 2024-04-24T10:42:47Z |
| format | Article |
| id | doaj.art-e46d6e6b54974140a771394cb94861d0 |
| institution | Directory Open Access Journal |
| issn | 2077-0383 |
| language | English |
| last_indexed | 2024-04-24T10:42:47Z |
| publishDate | 2024-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Clinical Medicine |
| spelling | doaj.art-e46d6e6b54974140a771394cb94861d02024-04-12T13:20:52ZengMDPI AGJournal of Clinical Medicine2077-03832024-03-01137186110.3390/jcm13071861Accuracy and Efficacy of Artificial Intelligence-Derived Automatic Measurements of Transthoracic Echocardiography in Routine Clinical PracticeNoriko Shiokawa0Masaki Izumo1Toshio Shimamura2Yui Kurosaka3Yukio Sato4Takanori Okamura5Yoshihiro Johnny Akashi6Ultrasound Center, St. Marianna University Hospital, 2-16-1 Sugao, Miyamae-ku, Kawasaki 216-8511, JapanDepartment of Cardiology, St. Marianna University School of Medicine, 2-16-1 Sugao, Miyamae-ku, Kawasaki 216-8511, JapanUltrasound Center, St. Marianna University Hospital, 2-16-1 Sugao, Miyamae-ku, Kawasaki 216-8511, JapanUltrasound Center, St. Marianna University Hospital, 2-16-1 Sugao, Miyamae-ku, Kawasaki 216-8511, JapanDepartment of Cardiology, St. Marianna University School of Medicine, 2-16-1 Sugao, Miyamae-ku, Kawasaki 216-8511, JapanUltrasound Center, St. Marianna University Hospital, 2-16-1 Sugao, Miyamae-ku, Kawasaki 216-8511, JapanDepartment of Cardiology, St. Marianna University School of Medicine, 2-16-1 Sugao, Miyamae-ku, Kawasaki 216-8511, Japan<b>Background</b>: Transthoracic echocardiography (TTE) is the gold standard modality for evaluating cardiac morphology, function, and hemodynamics in clinical practice. While artificial intelligence (AI) is expected to contribute to improved accuracy and is being applied clinically, its impact on daily clinical practice has not been fully evaluated. <b>Methods</b>: We retrospectively examined 30 consecutive patients who underwent AI-equipped TTE at a single institution. All patients underwent manual and automatic measurements of TTE parameters using the AI-equipped TTE. Measurements were performed by three sonographers with varying experience levels: beginner, intermediate, and expert. <b>Results:</b> A comparison between the manual and automatic measurements assessed by the experts showed extremely high agreement in the left ventricular (LV) filling velocities (E wave: r = 0.998, A wave: r = 0.996; both <i>p</i> < 0.001). The automated measurements of LV end-diastolic and end-systolic diameters were slightly smaller (−2.41 mm and −1.19 mm) than the manual measurements, although without significant differences, and both methods showing high agreement (r = 0.942 and 0.977, both <i>p</i> < 0.001). However, LV wall thickness showed low agreement between the automated and manual measurements (septum: r = 0.670, posterior: r = 0.561; both <i>p</i> < 0.01), with automated measurements tending to be larger. Regarding interobserver variabilities, statistically significant agreement was observed among the measurements of expert, intermediate, and beginner sonographers for all the measurements. In terms of measurement time, automatic measurement significantly reduced measurement time compared to manual measurement (<i>p</i> < 0.001). <b>Conclusions:</b> This preliminary study confirms the accuracy and efficacy of AI-equipped TTE in routine clinical practice. A multicenter study with a larger sample size is warranted.https://www.mdpi.com/2077-0383/13/7/1861transthoracic echocardiographyartificial intelligenceautomatic measurement |
| spellingShingle | Noriko Shiokawa Masaki Izumo Toshio Shimamura Yui Kurosaka Yukio Sato Takanori Okamura Yoshihiro Johnny Akashi Accuracy and Efficacy of Artificial Intelligence-Derived Automatic Measurements of Transthoracic Echocardiography in Routine Clinical Practice Journal of Clinical Medicine transthoracic echocardiography artificial intelligence automatic measurement |
| title | Accuracy and Efficacy of Artificial Intelligence-Derived Automatic Measurements of Transthoracic Echocardiography in Routine Clinical Practice |
| title_full | Accuracy and Efficacy of Artificial Intelligence-Derived Automatic Measurements of Transthoracic Echocardiography in Routine Clinical Practice |
| title_fullStr | Accuracy and Efficacy of Artificial Intelligence-Derived Automatic Measurements of Transthoracic Echocardiography in Routine Clinical Practice |
| title_full_unstemmed | Accuracy and Efficacy of Artificial Intelligence-Derived Automatic Measurements of Transthoracic Echocardiography in Routine Clinical Practice |
| title_short | Accuracy and Efficacy of Artificial Intelligence-Derived Automatic Measurements of Transthoracic Echocardiography in Routine Clinical Practice |
| title_sort | accuracy and efficacy of artificial intelligence derived automatic measurements of transthoracic echocardiography in routine clinical practice |
| topic | transthoracic echocardiography artificial intelligence automatic measurement |
| url | https://www.mdpi.com/2077-0383/13/7/1861 |
| work_keys_str_mv | AT norikoshiokawa accuracyandefficacyofartificialintelligencederivedautomaticmeasurementsoftransthoracicechocardiographyinroutineclinicalpractice AT masakiizumo accuracyandefficacyofartificialintelligencederivedautomaticmeasurementsoftransthoracicechocardiographyinroutineclinicalpractice AT toshioshimamura accuracyandefficacyofartificialintelligencederivedautomaticmeasurementsoftransthoracicechocardiographyinroutineclinicalpractice AT yuikurosaka accuracyandefficacyofartificialintelligencederivedautomaticmeasurementsoftransthoracicechocardiographyinroutineclinicalpractice AT yukiosato accuracyandefficacyofartificialintelligencederivedautomaticmeasurementsoftransthoracicechocardiographyinroutineclinicalpractice AT takanoriokamura accuracyandefficacyofartificialintelligencederivedautomaticmeasurementsoftransthoracicechocardiographyinroutineclinicalpractice AT yoshihirojohnnyakashi accuracyandefficacyofartificialintelligencederivedautomaticmeasurementsoftransthoracicechocardiographyinroutineclinicalpractice |