Abstract 15710: Point-of-Care Ultrasonography: Artificial Intelligence in the Assessment of Left Ventricular Function
Bibliographic record
Abstract
Introduction: Point-of-care ultrasonography (PoCUS) has become routine for the bedside assessment of patients. Current evidence shows that image acquisition and interpretation of left ventricular function can be achieved reliably by trained users, but evidence is lacking for interpretation by artificial intelligence. We sought to evaluate the accuracy of PoCUS devices with integrated artificial intelligence in comparison to transthoracic echocardiograms for assessment of left ventricular ejection fraction (LVEF). Methods: This is a prospective, multicenter cohort study using the KOSMOS portable ultrasound device (EchoNous, Redmon, WA). PoCUS studies included an apical four and two chamber views and were obtained by either novice trainees or experienced ultrasonographers. A real-time, automated LVEF was calculated by the device using a modified Simpson’s method. These patients also underwent a formal transthoracic echocardiogram, with image acquisition and interpretation completed by blinded ultrasonographers and level-3 trained echocardiographers, respectively. Results: A total of 449 patients were enrolled in the study with 227 and 222 studies completed by novice and experienced scanners, respectively. Images of suitable quality were obtained in 208 of the novice cohort (91.6%) and 216 of the experienced cohort (97.3%). In comparison to formal echocardiography, linear regression shows a R 2 value of 0.82 for the total cohort, and 0.85 for the novice and 0.72 in experienced scanner subgroups. Incorporating an intra-observer variability of ± 5%, the sensitivity and specificity for an abnormal (≤50%) and severely reduced (≤30%) LVEF was 99.2% and 97.7%, and 86.8% and 99%, respectively. Conclusions: Our study is one first to assess the accuracy of PoCUS devices with integrated artificial intelligence. Based on our study, a real-time, automated LVEF can be acquired by PoCUS with strong correlation to formal echocardiography. This study also highlights that diagnostic quality studies can be acquired by novice scanners with comparable accuracy to experienced scanners. This provides evidence for an immediate and inexpensive method for accurate LVEF assessment in emergent and resource-limited environments.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.006 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".