Skip to main content

Table 3 Participant imaging data split by type of rater

From: Validation of machine learning models for estimation of left ventricular ejection fraction on point-of-care ultrasound: insights on features that impact performance

Rater

Number of studies assigned an LVEF

Number of studies of insufficient quality for LVEF estimation

Mean estimation of LVEF ± SD

ML model

91

47

0.39 ± 0.11

Level III expert visual LVEF on randomized single videos, averaged per patient

120

18

0.40 ± 0.13

Level III expert segmentation LVEF on randomized single videos, averaged per patient

67

71

0.40 ± 0.14

Level III expert visual LVEF, accounting for all videos for a participant

124

14

0.40 ± 0.13

Level III expert segmentation LVEF, accounting for all videos for a participant

72

66

0.40 ± 0.12

Derived LVEF from echo reports

138

0

0.39 ± 0.12