Skip to main content

Table 3 ICC between machine AI and expert, n = 611

From: B-line quantification: comparing learners novice to lung ultrasound assisted by machine artificial intelligence technology to expert review

Zone GE machine, median (Min.–Max.) Expert, median (Min.–Max.) Spearman correlation
(95% CI)
Right zone 1 5.0 (0.0–5.0) 3.0 (0.0–5.0) 0.57 (0.42–0.70)
Right zone 2 4.0 (0.0–5.0) 3.0 (0.0–5.0) 0.46 (0.27–0.62)
Right zone 3 5.0 (0.0–5.0) 2.5 (0.0–5.0) 0.65 (0.51–0.76)
Right zone 4 5.0 (0.0–5.0) 4.0 (0.0–5.0) 0.77 (0.66–0.85)
Left zone 1 4.0 (0.0–5.0) 3.0 (0.0–5.0) 0.40 (0.21–0.57)
Left zone 2 4.0 (0.0–5.0) 2.0 (0.0–5.0) 0.32 (0.05–0.55)
Left zone 3 4.0 (0.0–5.0) 2.5 (0.0–5.0) 0.60 (0.44–0.72)
Left zone 4 5.0 (0.0–5.0) 5.0 (0.0–5.0) 0.54 (0.35–0.69)
Overall ICC 0.56 (0.51–0.62)
  1. Intraclass correlation between machine AI and expert by zone and overall. Data are based off of 611 images