Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 2, 2026Cardiovascular UltrasoundOpen Access

AI-assisted FoCUS LVEF assessments agree well with formal TTE but underperform experienced bedside visual estimates.

View Full Paper
Ask AI
Bookmark
Share

Why the study?

With the integration of AI into focused cardiac ultrasound, there is limited evidence comparing AI to bedside visual assessments by experienced users.

Does AI-based FoCUS LVEF assessment provide comparable diagnostic accuracy to bedside visual assessment by experienced users in adult patients requiring TTE?

Population

215 patients ≥ 18 years requiring a TTE

Comparison

AI-based FoCUS LVEF classification vs bedside visual assessment, with TTE reference

Design

Prospective study

Key result

AI-assisted FoCUS LVEF assessments showed good agreement with formal TTE (ICC 0.84) but were outperformed by experienced bedside users' visual estimates (ICC 0.97).

Authors

NKNikola KolobaricNBNickolas BeauregardWBWilliam Barbour

Discussion

Loading...

Member takes

Overview

AI-assisted FoCUS may support bedside LVEF assessment; leaves open superiority to expert visual estimation in routine care.

Key Points

  • To compare the diagnostic accuracy of an artificial intelligence algorithm against experienced visual estimation for assessing left ventricular ejection fraction on bedside ultrasound, using transthoracic echocardiography as the reference.
  • Prospective convenience-sample study conducted at a single US medical center between December 2020 and March 2022 among adult patients requiring a transthoracic echocardiogram (N=215; median age 63 years; 38.6% female).
  • Assessed left ventricular ejection fraction (LVEF) via AI-assisted focused cardiac ultrasound (FoCUS) using Simpson's biplane method of disks and visual estimation by experienced bedside sonographers, comparing both to reference transthoracic echocardiography (TTE).
  • AI-FoCUS demonstrated good agreement with TTE (intraclass correlation coefficient [ICC] 0.84, 95% CI: 0.80–0.88; severity kappa 0.89, 95% CI: 0.84–0.94), whereas visual assessment showed stronger concordance (ICC 0.97, 95% CI: 0.96–0.98; severity kappa 0.96, 95% CI: 0.92–0.99).
  • For detecting abnormal LVEF (<50%), AI-FoCUS achieved an AUC of 0.9779 (95% CI: 0.9591–0.9967; sensitivity 90.9%, specificity 95.6%, PPV 0.79, NPV 0.98), while visual assessment achieved an AUC of 0.9961 (95% CI: 0.9915–1.000; sensitivity 90.9%, specificity 97.8%, PPV 0.88, NPV 0.98).

Study Design

Type

Observational (n=215)

Multicenter

No

Structured PICO

Does AI-based FoCUS LVEF assessment provide comparable diagnostic accuracy to bedside visual assessment by experienced users in adult patients requiring TTE?

P
Population
215 adult patients requiring a transthoracic echocardiogram underwent bedside focused cardiac ultrasound to compare visual and AI-based left ventricular ejection fraction assessments.
E
Exposure
Artificial intelligence-based focused cardiac ultrasound (AI-FoCUS) LVEF classification using Simpson's biplane method
C
Comparator
Bedside visual global assessment of LVEF by experienced sonographer, with comprehensive TTE as the reference standard
O
Outcome
Agreement of LVEF assessment with reference TTE (measured by intraclass correlation coefficient) and diagnostic accuracy for identifying abnormal LVEF < 50% (measured by AUC)surrogate

Main Result

Effect estimate: ICC 0.84 (95% CI 0.80-0.88)

Absolute Event Rate: 0.84% vs 0.97%

AI-assisted FoCUS provides accurate estimates of LV dysfunction severity but is currently outperformed by experienced bedside sonographers.

Limitations

  • Participants were enrolled through convenience sampling, which may introduce operator bias.
  • Single-center design limits the generalizability of the findings.
  • Small number of participants with severely reduced LVEF (< 30%) limits conclusions for this subgroup.
  • Bedside visual assessments were completed by trained cardiac sonographers, which may not reflect the performance of all real-world FoCUS users.

Cite This Study

Kolobaric et al. (2026) conducted an observational in Patients requiring a transthoracic echocardiogram (n=215). AI-based focused cardiac ultrasound (FoCUS) vs. Visual bedside assessment and formal transthoracic echocardiography (TTE) was evaluated on Agreement with formal TTE for LVEF assessment (Intraclass correlation coefficient) (ICC 0.84, 95% CI 0.80-0.88). AI-assisted FoCUS LVEF assessments showed good agreement with formal TTE (ICC 0.84) but were outperformed by experienced bedside users' visual estimates (ICC 0.97).

synapsesocial.com/papers/6a97e237c562ede874ec636ahttps://doi.org/10.1186/s12947-026-00377-3
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Respect the septoapical region - deep learning enhanced estimation of left ventricular ejection fraction: application in transthoracic and point-of-care echocardiography2025
  2. 2Smarter FoCUS: AI-Guided Focused Cardiac Ultrasound Enables Novice Detection of Left Ventricular Dysfunction2026 · 1 citations
  3. 3Multicenter validation study for automated left ventricular ejection fraction assessment using a handheld ultrasound with artificial intelligence2024 · 22 citations
  4. 4Left Ventricular Ejection Fraction Assessed by a General Practitioner Using AI-Guided Point-of-Care Ultrasonography: Feasibility and Diagnostic Agreement With Conventional Echocardiography2025
  5. 5Assessment of left ventricular ejection fraction in artificial intelligence based on left ventricular opacification2024 · 1 citations