Search

Background: The incorporation of artificial intelligence (AI) into point-of-care ultrasound (POCUS) platforms has rapidly increased. The number of B-lines present on lung ultrasound (LUS) serve as a useful tool for the assessment of pulmonary congestion. Interpretation, however, requires experience and therefore AI automation has been pursued. This study aimed to test the agreement between the AI software embedded in a major vendor POCUS system and visual expert assessment. Methods: This single-center prospective study included 55 patients hospitalized for various respiratory symptoms, predominantly acutely decompensated heart failure. A 12-zone protocol was used. Two experts in LUS independently categorized B-lines into 0, 1–2, 3–4, and ≥ 5. The intraclass correlation coefficient (ICC) was used to determine agreement. Results: A total of 672 LUS zones were obtained, with 584 (87%) eligible for analysis. Compared with expert reviewers, the AI significantly overcounted number of B-lines per patient (23.5 vs. 2.8, p < 0.001). A greater proportion of zones with > 5 B-lines was found by the AI than by the reviewers (38% vs. 4%, p < 0.001). The ICC between the AI and reviewers was 0.28 for the total sum of B-lines and 0.37 for the zone-by-zone method. The interreviewer agreement was excellent, with ICCs of 0.92 and 0.91, respectively. Conclusion: This study demonstrated excellent interrater reliability of B-line counts from experts but poor agreement with the AI software embedded in a major vendor system, primarily due to overcounting. Our findings indicate that further development is needed to increase the accuracy of AI tools in LUS. [ABSTRACT FROM AUTHOR]

Aims Patients awaiting orthotopic heart transplantation (OHT) can be bridged utilizing a left ventricular assist device (LVAD) that reduces left ventricular filling pressures, decreases pulmonary artery wedge pressure, and maintains adequate cardiac output. This study set out to examine the poorly investigated area of if and how pre-treatment with LVAD impacts right ventricular (RV) function following OHT. Methods and results We prospectively evaluated 59 (LVAD n = 20) consecutive OHT patients. Transthoracic echocardiography (TTE) was performed in conjunction with right heart catheterization (RHC) at 1, 6, and 12 months after OHT. RV function TTE-parameters included tricuspid annular plane systolic excursion (TAPSE), systolic tissue velocity (S0), fractional area change, two-dimensional RV global longitudinal strain and longitudinal strain from the RV lateral wall (RVfree). At 1 month after OHT, the LVAD group had significantly better longitudinal RV function than the non-LVAD group: TAPSE (15 ± 3 mm vs. 12 ± 2 mm, P < 0.001), RV global longitudinal strain (19.8 ± 2.1% vs. 14.3 ± 2.8%, P < 0.001), and RVfree (19.8 ± 2.3% vs. 14.1 ± 2.9%, P < 0.001). At this time point, pulmonary vascular resistance (PVR) was also lower [1.2 ± 0.4 Wood Units (WU) vs. 1.6 ± 0.6 WU, P < 0.05] in the LVAD group compared with the non-LVAD group. At 6 and 12 months, no difference was detected in any of the TTE and RHC measured parameters between the two groups. Between 1 and 12 months, all parameters of RV function improved significantly in the non-LVAD group but remained unaltered in the LVAD group. Conclusions Our results indicate that pre-treatment with LVAD decreases PVR and is associated with significantly better RV function early following OHT. During the first year following transplantation, RV function progressively improved in the non-LVAD group such that at 6 and 12 months, no difference in RV function was detected between the groups. [ABSTRACT FROM AUTHOR]