AI Enhances Lung Ultrasound Interpretation Across Clinicians with Varying Expertise Levels
Bibliographic record
Abstract
Background/Objective: Lung ultrasound (LUS) is a valuable tool for detecting pulmonary conditions, but its accuracy depends on user expertise. This study evaluated whether an artificial intelligence (AI) tool could improve clinician performance in detecting pleural effusion and consolidation/atelectasis on LUS scans. Methods: In this multi-reader, multi-case study, 14 clinicians of varying experience reviewed 374 retrospectively selected LUS scans (cine clips from the PLAPS point, obtained using three different probes) from 359 patients across six centers in the U.S. and Canada. In phase one, readers scored the likelihood (0–100) of pleural effusion and consolidation/atelectasis without AI. After a 4-week washout, they re-evaluated all scans with AI-generated bounding boxes. Performance metrics included area under the curve (AUC), sensitivity, specificity, and Fleiss’ Kappa. Subgroup analyses examined effects by reader experience. Results: For pleural effusion, AUC improved from 0.917 to 0.960, sensitivity from 77.3% to 89.1%, and specificity from 91.7% to 92.9%. Fleiss’ Kappa increased from 0.612 to 0.774. For consolidation/atelectasis, AUC rose from 0.870 to 0.941, sensitivity from 70.7% to 89.2%, and specificity from 85.8% to 89.5%. Kappa improved from 0.427 to 0.756. Conclusions: AI assistance enhanced clinician detection of pleural effusion and consolidation/atelectasis in LUS scans, particularly benefiting less experienced users.
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 | 0.024 | 0.104 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".