Lung ultrasound for the diagnosis of pneumonia in adults: a systematic review and meta-analysis

Abstract

Background: Guidelines do not currently recommend the use of lung ultrasound (LUS) as an alternative to chest X-ray (CXR) or chest computerized tomography (CT) scan for the diagnosis of pneumonia. We conducted a meta-analysis to summarize existing evidence of the diagnostic accuracy of LUS for pneumonia in adults.

Methods: We conducted a systematic search of published studies comparing the diagnostic accuracy of LUS against a referent CXR or chest CT scan and/or clinical criteria for pneumonia in adults aged ≥18 years. Eligible studies were required to have a CXR and/or chest CT scan at the time of evaluation. We manually extracted descriptive and quantitative information from eligible studies, and calculated pooled sensitivity and specificity using the Mantel-Haenszel method and pooled positive and negative likelihood ratios (LR) using the DerSimonian-Laird method. We assessed for heterogeneity using the Q and I2 statistics.

Results: Our initial search strategy yielded 2726 articles, of which 45 (1.7%) were manually selected for review and 10 (0.4%) were eligible for analyses. These 10 studies provided a combined sample size of 1172 participants. Six studies enrolled adult patients who were either hospitalized or admitted to Emergency Departments with suspicion of pneumonia and 4 studies enrolled critically-ill adult patients. LUS was performed by highly-skilled sonographers in seven studies, by trained physicians in two, and one did not mention level of training. All studies were conducted in high-income settings. LUS took a maximum of 13 minutes to conduct. Nine studies used a 3.5-5 MHz micro-convex transducer and one used a 5-9 MHz convex probe. Pooled sensitivity and specificity for the diagnosis of pneumonia using LUS were 94% (95% CI, 92%-96%) and 96% (94%-97%), respectively; pooled positive and negative LRs were 16.8 (7.7-37.0) and 0.07 (0.05-0.10), respectively; and, the area-under-the-ROC curve was 0.99 (0.98-0.99).

Conclusions: Our meta-analysis supports that LUS, when conducted by highly-skilled sonographers, performs well for the diagnosis of pneumonia. General practitioners and Emergency Medicine physicians should be encouraged to learn LUS since it appears to be an established diagnostic tool in the hands of experienced physicians.

Figure 1

Flowchart of articles retrieved from search of databases and reasons of exclusions.

Figure 2

Forest plots for diagnostic accuracy of lung ultrasound for the diagnosis of pneumonia. Sensitivity (Panel A), Specificity (Panel B), negative likelihood ratio (Panel C) and positive likelihood ratio (Panel D). Inconsistency (I²) describes the percentage of total variation across studies due to heterogeneity.

Figure 3

Summary receiver operating characteristics of lung ultrasound for pneumonia. The values sensitivity and 1-specificity for each study are represented with a square. 95% confidence intervals for sensitivity (vertical lines) and 1-specificity (horizontal lines) are also shown. Each study is represented by a separate color.