Point-of-Care Lung Ultrasound for Differentiating COVID-19 From Influenza
Bibliographic record
Abstract
Background and objectives Patients infected with influenza and COVID-19 exhibit similar clinical presentations; thus, a point-of-care test to differentiate between the diseases is needed. Here, we sought to identify features of point-of-care lung ultrasound (LUS) that can discriminate between influenza and COVID-19. Methods In this prospective, cross-sectional study, LUS clips of patients presenting to the emergency department (ED) with viral-like symptoms were collected via a 10-zone scanning protocol. Deidentified clips were interpreted by emergency ultrasound fellows blinded to patients' clinical context and influenza or COVID-19 diagnosis. Modified Soldati scores were calculated for each lung zone. Logistic regression identified the association of pulmonary pathologies with each disease. Results Ultrasound fellows reviewed LUS clips from 165 patients, of which 30.9% (51/165) had confirmed influenza, 33.9% (56/165) had confirmed COVID-19, and 35.1% (58/165) had neither disease. Patients with COVID-19 were more likely to have irregular pleura and B-lines in all lung zones (p<0.01). The median-modified Soldati score for influenza patients was 0/20 (IQR 0-2), 9/20 (IQR 2.5-15.5) for COVID-19 patients, and 2/20 (IQR 0-8) for patients with neither disease (p<0.0001). In multivariate regression analysis adjusted for age, sex, and congestive heart failure (CHF), the presence of B-lines (OR = 1.29, 95% CI 1.09-1.53) was independently associated with COVID-19 diagnosis. The presence of pleural effusion was inversely associated with COVID-19 (OR = 0.09, 95% CI 0.01-0.65). Conclusions LUS may help providers preferentially identify the presence of influenza versus COVID-19 infection both visually and by calculating a modified Soldati score. Further studies assessing the utility of LUS in differentiating viral illnesses in patients with variable illness patterns and those with variable illness severity are warranted.
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 | 0.003 | 0.010 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
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".