Lung ultrasound for the diagnosis of pulmonary consolidation in children with community-acquired pneumonia

Introduction

According to the World Health Organization, in 2019, pneumonia caused an estimated 740,180 deaths in children under 5 years of age, accounting for 14% of all deaths in children under 5 years of age and 22% of all deaths in children aged 1 to 5 years (1). The vast majority of pneumonia cases are community-acquired pneumonia (CAP), which is a major threat to children’s health (2). CAP is an acute infection of the lung parenchyma and/or interstitial areas of the lungs, causing varying degrees of hypoxia and symptoms of infection, usually characterized by fever, cough, increased respiration, wet rales in the lungs, and abnormal changes on chest imaging (3). Severe pneumonia can lead to complications such as pulmonary consolidation, pulmonary atelectasis, and pulmonary necrosis, exacerbating the child’s symptoms. These factors can cause the illness to worsen over time, resulting in a poor reaction to treatment drugs, which can negatively impact the prognosis and outcome of pediatric patients (4,5). Research has demonstrated that pulmonary consolidation is a risk factor for necrotizing pneumonia, refractory Mycoplasma pneumoniae pneumonia infection, and other unfavorable consequences (6). Therefore, timely recognition of the development of pulmonary consolidation is crucial for the management of pneumonia in children.

The diagnosis and evaluation of pneumonia have long been conducted according to clinical manifestations, physical examination, chest radiographs, chest computed tomography (CT), and other radiologic imaging. However, the signs and symptoms of pneumonia can vary depending on the age of the child and the etiology of the infection, reducing the specificity of diagnosis (7,8). Ionizing radiation from chest radiographs and CT in young children may have potentially adverse late effects (9,10). Moreover, chest radiographs lack sensitivity for the diagnosis of pneumonia (11). Although the diagnostic accuracy of chest CT is greater than that of chest radiographs, it is often not accepted by parents due to the greater exposure to ionizing radiation, frequent need for sedation, and high cost.

Ultrasound is a frequently used imaging tool in clinical practice and is applied for the diagnosis and treatment of many diseases. However, owing to the high acoustic impedance of gas, ultrasound is unable to visualize normal lung parenchyma, and it has long been considered unsuited for lung examination. In recent years, with increased awareness of ultrasound and advances in ultrasound technology, lung ultrasound (LUS) has increasingly been used as an adjunctive test in the clinical diagnosis of pneumonia, interstitial lung disease, lung cancer, and other lung diseases (12-15). On the basis of the presence or absence of pathological abnormalities, together with A- and B-line aberrations, LUS can reflect various conditions of the lungs, including consolidation and pleural irregularities (16). However, relatively few studies have examined the use of LUS in children with CAP combined with pulmonary consolidation. The purpose of this study was thus to investigate the accuracy of LUS for detecting CAP combined with pulmonary consolidation in children. We present this article in accordance with the STARD reporting checklist (available at https://qims.amegroups.com/article/view/10.21037/qims-24-2167/rc).

Methods

Patients

Children who were diagnosed with CAP at Children’s Hospital Affiliated to Zhengzhou University between January 1, 2023, and December 31, 2023, were included. The inclusion criteria for patients were as follows: (I) age greater than 1 month and less than 18 years; (II) meeting the diagnostic criteria for pneumonia in the Diagnostic and Treatment Criteria for Community-Acquired Pneumonia in Children (2019 edition); onset of infection outside of hospital; presence of symptoms of pneumonia such as fever, cough, and wheezing; presence of signs of pneumonia such as increased respiration, wet rales, and decreased breath sounds; and (III) chest CT and chest LUS obtained within 24 hours of one another. Meanwhile, the exclusion criteria were as follows: (I) CAP combined with bronchial foreign bodies, pulmonary foreign bodies, congenital respiratory malformations, tuberculosis, lung cancer, or other diseases; (II) asthma, cystic fibrosis, congenital heart disease, immunodeficiency, or hemodynamic instability; and (III) had incomplete clinical data. This study was conducted in accordance with the Declaration of Helsinki and its subsequent amendments and was approved by the Medical Ethics Committee of Henan Children’s Hospital (No. 2023-K-080). Informed consent was obtained from all the patients’ legal guardians.

To assess the agreement between different sonographers in recognizing pulmonary consolidation and pleural effusions, we included another 30 children with CAP who underwent LUS, and the LUS results were independently assessed by two different sonographers.

CT examination

Chest CT scanning was performed via a Brilliance CT 64-row spiral CT scanner (Philips Healthcare, Best, the Netherlands) with an 8-mm scanning spacing and 2-mm-thick layers. During scanning, the child lay flat on the scanning bed, and smaller children were required to be accompanied by their parents or sedated. The position was adjusted according to the radiographer’s requirements to obtain a more satisfactory image. Chest CT image analysis was performed by a radiologist with more than 5 years of experience and a pediatric respiratory physician.

LUS

LUS was performed using a EPIQ5 color Doppler ultrasound diagnostic machine (Philips Healthcare) with a 7 to 10-MHz line array probe and if necessary, a 3.5 to 5.0-MHz convex array probe. LUS was performed by sonographers with 5 years’ experience in performing LUS according to a standardized protocol for pediatric LUS. The children were examined in a lying or sitting position in a quiet state, and both lungs were divided into 12 symmetrical zones of anterior superior, anterior inferior, lateral superior, lateral inferior, posterior superior, and posterior inferior, bounded by longitudinal parasternal, anterior axillary, posterior axillary, posteromedian, and nipple connecting lines (Figure 1). The probe was placed perpendicular to the ribs in a longitudinal sweep starting from the second intercostal space in sequence, following the order of inside-out and top-to-bottom along the intercostal space in a walking sweep. The anterior and lateral areas of the chest were examined in the supine position, and the posterior wall was examined in the prone position. Rib shadows were avoided, visualization of the pleural line was maximized, and the ultrasound image was recorded and stored. The probe was kept perpendicular to the chest wall during the sweep. The ultrasound results were discussed by two experienced pulmonary sonographers and reviewed by a more senior sonographer before a formal conclusion was reached.

Figure 1 Ultrasound partition of the lung.

The LUS signs observed include the following: (I) line A (a smooth, multiple-reflective, strong echogenic line equidistant from the pleural line, representing normal lung tissue); (II) abnormal pleural line (a rough, blurred, irregularly thickened, discontinuous, or absent pleural line); (III) B line (a parallel transversal hyperechogenic stripe not extending past a few millimeters of depth but generally extending for the entire ultrasound image); and (IV) alveolar-interstitial syndrome (increased fluid content in the alveoli and interstitium caused by the imbalance of the water-air ratio in the lungs).

Ultrasound was used to diagnose pneumonia, pulmonary consolidation, and pleural effusion: (I) a diagnosis of pneumonia included two or more lung areas bilaterally with increased B lines (≥3 B lines in a single ultrasound field of view; Figure 2); (II) a diagnosis of pulmonary consolidation included intralobar consolidations characterized by a subpleural debris sign, interlobar consolidations characterized by the presence of liver-like tissue in areas of lung tissue, and a consolidation area containing gas or liquid in a branching or parallel arrangement appearing in the solid area (i.e., bronchial insufflation sign; Figure 3); (III) a diagnosis of pleural effusion included an irregular anechoic area visible between the pleura of the splanchnic layer. In this study, detection of pleural effusion in either lung area was diagnosed as positive for pleural effusion on that side.

Figure 2 Ultrasound image of pneumonia. The arrow indicates the B lines. The red triangle indicates the anechoic area.

Figure 3 Ultrasound image of pulmonary consolidation. The arrow indicates the consolidation area of the lung.

Statistical analyses

Data were organized via Microsoft Excel (Microsoft Corp., Redmond, WA, USA) and analyzed with SPSS 26 (IBM Corp., Armonk, NY, USA). We used percentage values for measurement information and the mean and standard deviation for count information. The Cohen kappa coefficient was used to evaluate the concordance relationship between LUS and CT in the diagnosis of pneumonia and the detection of pulmonary consolidation. The Fleiss Kappa coefficient was used to quantify the sonographer’s consistency in identifying pulmonary consolidation and pleural effusion. Kappa values ≤0 indicated no concordance, 0.01–0.20 indicated none to slight, 0.21–0.40 indicated fair, 0.41–0.60 indicated moderate, 0.61–0.80 indicated comparable, and 0.81–1.00 indicated almost perfect agreement. The sensitivity, specificity, negative predictive value (NPV), and positive predictive value (PPV) of LUS were also calculated with CT as the gold standard.

Results

A total of 6,705 children with CAP were enrolled, of whom 3,485 (51.98%) were males, and a mean age of 79.38±33.91 months (range, 1–180 months). A total of 3,602 (53.72%) children were aged 0–6 years, 3,040 (45.34%) were aged 7–12 years, and 63 (0.94%) were aged 12–15 years.

Based on the results of chest CT, 3,799 (56.26%) children had pulmonary consolidation and 658 (9.81%) children had pleural effusions. The median age of children with pulmonary consolidation was 84 [interquartile range (IQR), 63, 106] months, which was significantly higher than the 75 (IQR, 47, 100) months for children without pulmonary consolidation (P<0.05).

Based on gold standard chest CT findings, LUS yielded a sensitivity of 92.10% and a specificity of 92.53% in identifying pulmonary consolidation, with a PPV of 94.16%, and an NPV of 89.96%. The consistency test suggested good agreement between LUS and CT examination (κ=0.844). The diagnosis of pulmonary consolidation by LUS examination was almost identical to that by chest CT, while LUS’s consistency with CT in diagnosing pulmonary consolidation was higher among older children (Tables 1,2).

In contrast to the results for pulmonary consolidation, LUS demonstrated only moderate consistency with chest CT in identifying pleural effusion (κ=0.457), achieving a sensitivity of 65.50%, a specificity of 90.65%, a PPV of 43.27%, and an NPV of 96.02% (Table 3).

Thirty children with CAP were included in the study to assess the consistency between different sonographers in recognizing pulmonary consolidation and pleural effusion. According to sonographer A, 14 children had pulmonary consolidation and 17 children had pleural effusion. According to sonographer B, 12 children had consolidated pulmonary consolidation and 16 children had pleural effusion. The results of the Fleiss kappa indicated that the sonographers were in agreement for the assessment of both pulmonary consolidation (κ=0.729) and pleural effusion (κ=0.798).

Discussion

CAP is one of the most common causes of hospitalization in children in developed countries and is a leading cause of death in children in developing countries (17). Severe pneumonia, in particular, can lead to a rapid decline in health, has a high morbidity and mortality rate, and can leave respiratory sequelae that require early recognition and treatment. The children hospitalized for pneumonia included in this study were mainly preschool-age children, followed by school-age children, which is consistent with a previous study (18). Most cases of the pulmonary consolidation are caused by Streptococcus pneumoniae, Mycoplasma pneumoniae, and other common pneumonia-causing pathogens. In this study, the higher prevalence of pneumonia combined with pulmonary consolidation was considered to be associated with the emergence of a large-scale peak of Mycoplasma pneumoniae infections in China in 2023 (19). Moreover, we found that older children were more likely to have accompanying pulmonary consolidation, which is consistent with previously reported findings (20).

The presence of pulmonary consolidation in a child with pneumonia can significantly aggravate the condition and may lead to poor prognosis due to conditions such as pulmonary atelectasis and pulmonary necrosis (20); therefore, early recognition of the development of pulmonary consolidation is critical to optimizing the treatment of pneumonia. Chest X-ray is commonly used to diagnosis pneumonia, but in recent years, LUS has been increasingly used for this purpose. Several studies have shown that LUS is more sensitive than is chest X-ray for detecting pneumonia in children and has the advantages of convenience and lack of radiation; consequently, some believe that LUS can be used as an alternative to X-ray in the future (18,21,22). Moreover, pulmonary ultrasound is relatively simple and can be performed in the emergency room or outpatient care department. Chest CT is the gold standard for identifying pulmonary consolidation, which mainly appear as large, homogeneous, dense shadows, with some showing signs of bronchial insufflation. In this study, the sensitivity and specificity of LUS in identifying solid lung lesions were above 90%, and LUS demonstrated a high degree of concordance with chest CT. This confirms that LUS not only performs well in identifying CAP but can also provide benefit in diagnosing pulmonary consolidation in children. We also found that LUS’s concordance with CT in diagnosing pulmonary consolidation was higher in older children, which may be related to the lower level of compliance with ultrasound in younger children. In addition, caregivers are generally more willing to accept ultrasound due to its lower cost, lack of radiation, and amenability to children. Therefore, we suggest that in children with suspected pneumonia combined with pulmonary consolidation, LUS should be favored when caregivers decline chest CT. In addition, one of the most valuable aspects of LUS is that it can track the course of pneumonia in a completely safe manner (23). Since children with pneumonia combined with atelectasis usually experience a long duration of illness, it is often necessary to evaluate the lungs several times during the course of treatment in order to adjust the treatment plan. LUS is more acceptable for multiple examinations in a short period of time than is chest CT. For children with a longer course of disease and unsatisfactory improvement of clinical symptoms, LUS can be applied to monitor subpleural consolidation attached to the pleural surface and its response to antibiotic therapy.

However, it should be noted that LUS is associated with several limitations. Riccabona et al. reported that ultrasound cannot reliably differentiate between lung atelectasis due to pneumonia and other causes of atelectasis and that caution is warranted regarding the significance of small subpleural areas of solid lung lesions and pleural line abnormalities (24). In addition, one of the main obstacles to the reproducibility of LUS examinations is the parameters of the ultrasound scan. The appearance of pulmonary consolidation under ultrasound is strongly influenced by the type and frequency of the probe used, time gain compensation, absence of tissue harmonics, and the focus of the ultrasound beam. High-frequency linear probes (8–12.5 MHz) improve spatial resolution and reduce the number of ultrasound artifacts but provide shallower penetration depths. Low-frequency convex probes (3–8 MHz) have greater depth of penetration but produce lower spatial resolution and a higher the number of artifacts. Moreover, large-scale extension of LUS application without proper training may lead to misdiagnosis (23). Therefore, LUS results should not be solely relied upon for diagnosis, and the highest diagnostic accuracy and clinical benefit can be achieved by combining the results of radiography and CT as necessary, with each providing unique clinical information, especially when clinical symptoms do not match the ultrasound results. Moreover, the clinical application of LUS requires the operation of an experienced sonographer with specialized training, and structured training and standardized imaging protocols can improve the accuracy of LUS. In order to assess the consistency of different sonographers’ assessment of LUS findings for pulmonary consolidation and pleural effusion, we included 30 children with CAP; the results indicated good consistency, suggesting that our ultrasound findings have a high degree of reliability. This was mainly due to the fact that our sonographers underwent lengthy training and were familiar with the standardized procedure for determining the results of LUS.

Pleural effusion is also a common clinical complication of CAP. A large amount of pleural effusion can cause symptoms such as dyspnea and aggravate the patient’s discomfort, necessitating prompt treatment. Several studies have reported that the diagnostic accuracy of ultrasound in detecting pleural effusion is higher than that of chest X-ray. Ultrasound is characterized by high sensitivity and accuracy in identifying and localizing pleural effusions and is now widely used to locate and quantify pleural effusions (25,26). However, in our study, LUS also exhibited moderate consistency with chest CT in identifying pleural effusion, which was lower than that reported previously (27). This may be because ultrasound results related to pleural effusion may be influenced by operator expertise and subjective judgment, and it has been suggested that a rigorous, standardized ultrasound protocol is needed for ultrasound-based diagnosis (28). However, in our study, LUS demonstrated high specificity in the recognition of pleural effusion, suggesting that ultrasound results also have a certain reference value for clinical practice. LUS may also be an option for the initial evaluation of pleural effusion when the caregivers refuse chest CT.

In recent years, research into the application of artificial intelligence (AI) in ultrasound imaging has received increased attention, as it can significantly improve the diagnostic accuracy and consistency of scans while reducing the physician’s reading time. Over the past decade, significant progress has made in the field of AI, especially deep learning, for ultrasound imaging analysis (29). Many researchers have demonstrated that AI can help clinicians interpret LUS images results faster while maintaining good accuracy (30,31). In the future, we plan to collect a larger set of dynamic LUS images of children with pneumonia as a training set and upload them to an AI tool for learning. The ultimate purpose of this is to build a LUS model for automatic evaluation. Moreover, a validation set will be included to assess the AI tool in terms of clinical validity, reliability, and consistency with experienced sonographers.

This study involved certain limitations which should be acknowledged. To begin, we did not compare the LUS results with chest X-ray results, and the analysis was fairly, basic: the results were only examined in terms of positive or negative, with no comparison of the site or extent of ultrasound detection. Moreover, we only included children with pneumonia who underwent CT scans, which might have introduced a certain selection bias toward cases of relatively severe pneumonia; however, the results remain credible. Due to data limitations, we did not perform a rigorous cost–benefit analysis or statistical evaluation to compare the clinical value of LUS and pulmonary CT. Additionally, we only compared the results of children with pneumonia in the acute phase and did not sequentially observe the changes in the ultrasound lungs images of the children. In the future, we plan to observe the changes in LUS results in children with pneumonia at different stages of disease and to test the ability of LUS to determine the regression of pneumonia when accompanied by pulmonary consolidation.

Conclusions

LUS showed high concordance with lung CT in the identification of pneumonia combined with pulmonary consolidation and moderate concordance for the identification of pleural effusion. LUS can be used as a complementary method for the preliminary evaluation of pulmonary consolidation in children with CAP, as it is simple easy to perform, and can reduce radiation exposure and costs.

Acknowledgments

None.

Footnote

Reporting Checklist: The authors have completed the STARD reporting checklist. Available at https://qims.amegroups.com/article/view/10.21037/qims-24-2167/rc

Funding: None.

Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (https://qims.amegroups.com/article/view/10.21037/qims-24-2167/coif). The authors have no conflicts of interest to declare.

Ethical Statement: The authors are accountable for all aspects of the work in ensuring that questions related to the accuracy or integrity of any part of the work are appropriately investigated and resolved. This study was conducted in accordance with the Declaration of Helsinki and its subsequent amendments and was approved by the Medical Ethics Committee of Henan Children’s Hospital (No. 2023-K-080). Informed consent was provided by all the patients’ legal guardians.

Open Access Statement: This is an Open Access article distributed in accordance with the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International License (CC BY-NC-ND 4.0), which permits the non-commercial replication and distribution of the article with the strict proviso that no changes or edits are made and the original work is properly cited (including links to both the formal publication through the relevant DOI and the license). See: https://creativecommons.org/licenses/by-nc-nd/4.0/.

References

1. World Health Organization. Pneumonia in children. Available online: https://www.who.int/news-room/fact-sheets/detail/pneumonia
2. National Health Commission of the People’s Republic of China, State Administration of Traditional Chinese Medicine. Guideline for diagnosis and treatment of community-acquired pneumonia in Children (2019 version). Chinese Journal of Clinical Infectious Diseases 2019;12:6-13.
3. Leung AKC, Wong AHC, Hon KL. Community-Acquired Pneumonia in Children. Recent Pat Inflamm Allergy Drug Discov 2018;12:136-44. [Crossref] [PubMed]
4. Li F, Zhang Y, Shi P, Cao L, Su L, Fu P, Abuduxikuer K, Wang L, Wang Y, Lu R, Tan W, Shen J. Mycoplasma pneumoniae and Adenovirus Coinfection Cause Pediatric Severe Community-Acquired Pneumonia. Microbiol Spectr 2022;10:e0002622. [Crossref] [PubMed]
5. Krutikov M, Rahman A, Tiberi S. Necrotizing pneumonia (aetiology, clinical features and management). Curr Opin Pulm Med 2019;25:225-32. [Crossref] [PubMed]
6. Zheng B, Zhao J, Cao L. The clinical characteristics and risk factors for necrotizing pneumonia caused by Mycoplasma pneumoniae in children. BMC Infect Dis 2020;20:391. [Crossref] [PubMed]
7. le Roux DM, Zar HJ. Community-acquired pneumonia in children - a changing spectrum of disease. Pediatr Radiol 2017;47:1392-8. [Crossref] [PubMed]
8. Chee E, Huang K, Haggie S, Britton PN. Systematic review of clinical practice guidelines on the management of community acquired pneumonia in children. Paediatr Respir Rev 2022;42:59-68. [Crossref] [PubMed]
9. Brenner DJ. What we know and what we don't know about cancer risks associated with radiation doses from radiological imaging. Br J Radiol 2014;87:20130629. [Crossref] [PubMed]
10. Mazrani W, McHugh K, Marsden PJ. The radiation burden of radiological investigations. Arch Dis Child 2007;92:1127-31. [Crossref] [PubMed]
11. Williams GJ, Macaskill P, Kerr M, Fitzgerald DA, Isaacs D, Codarini M, McCaskill M, Prelog K, Craig JC. Variability and accuracy in interpretation of consolidation on chest radiography for diagnosing pneumonia in children under 5 years of age. Pediatr Pulmonol 2013;48:1195-200. [Crossref] [PubMed]
12. Principi N, Esposito A, Giannitto C, Esposito S. Lung ultrasonography to diagnose community-acquired pneumonia in children. BMC Pulm Med 2017;17:212. [Crossref] [PubMed]
13. Pereda MA, Chavez MA, Hooper-Miele CC, Gilman RH, Steinhoff MC, Ellington LE, Gross M, Price C, Tielsch JM, Checkley W. Lung ultrasound for the diagnosis of pneumonia in children: a meta-analysis. Pediatrics 2015;135:714-22. [Crossref] [PubMed]
14. Zhang Y, Zhang Z, Liao H, Li M, Xu C, Liang Z, He L, Zhang S, Tang Q. Evaluation of parietal pleural adhesion and invasion in subpleural lung cancer: value of B-mode ultrasound and contrast-enhanced ultrasound. Quant Imaging Med Surg 2024;14:3302-11. [Crossref] [PubMed]
15. Zhang Y, Lian X, Huang S, Li L, Zhao Y, Lai H, Lyu G. A study of the diagnostic value of a modified transthoracic lung ultrasound scoring method in interstitial lung disease. Quant Imaging Med Surg 2023;13:946-56. [Crossref] [PubMed]
16. Sultan SR. Association Between Lung Ultrasound Patterns and Pneumonia. Ultrasound Q 2022;38:246-9. [Crossref] [PubMed]
17. Meyer Sauteur PM. Childhood community-acquired pneumonia. Eur J Pediatr 2024;183:1129-36. [Crossref] [PubMed]
18. Ciuca IM, Dediu M, Marc MS, Lukic M, Horhat DI, Pop LL. Lung Ultrasound Is More Sensitive for Hospitalized Consolidated Pneumonia Diagnosis Compared to CXR in Children. Children (Basel) 2021;8:659. [Crossref] [PubMed]
19. Xie XY, Zhou RY, Ding SA, Ma BX, Zhang X, Zhang Y. Emerging trends and concerns in Mycoplasma pneumoniae pneumonia among Chinese pediatric population. Pediatr Res 2024;95:1388-90. [Crossref] [PubMed]
20. Zhang X, Sun R, Jia W, Li P, Song C. Clinical Characteristics of Lung Consolidation with Mycoplasma pneumoniae Pneumonia and Risk Factors for Mycoplasma pneumoniae Necrotizing Pneumonia in Children. Infect Dis Ther 2024;13:329-43. [Crossref] [PubMed]
21. Talwar N, Manik L, Chugh K. Pediatric Lung Ultrasound (PLUS) in the diagnosis of Community-Acquired Pneumonia (CAP) requiring hospitalization. Lung India 2022;39:267-73. [Crossref] [PubMed]
22. Dong Z, Shen C, Tang J, Wang B, Liao H. Accuracy of Thoracic Ultrasonography for the Diagnosis of Pediatric Pneumonia: A Systematic Review and Meta-Analysis. Diagnostics (Basel) 2023;13:3457. [Crossref] [PubMed]
23. Tomà P. Lung ultrasound in pediatric radiology - cons. Pediatr Radiol 2020;50:314-20. [Crossref] [PubMed]
24. Riccabona M. Ultrasound of the chest in children (mediastinum excluded). Eur Radiol 2008;18:390-9. [Crossref] [PubMed]
25. Shao RJ, Du MJ, Xie JT. Use of lung ultrasound for the diagnosis and treatment of pleural effusion. Eur Rev Med Pharmacol Sci 2022;26:8771-6. [Crossref] [PubMed]
26. Brogi E, Gargani L, Bignami E, Barbariol F, Marra A, Forfori F, Vetrugno L. Thoracic ultrasound for pleural effusion in the intensive care unit: a narrative review from diagnosis to treatment. Crit Care 2017;21:325. [Crossref] [PubMed]
27. Hansell L, Milross M, Delaney A, Tian DH, Ntoumenopoulos G. Lung ultrasound has greater accuracy than conventional respiratory assessment tools for the diagnosis of pleural effusion, lung consolidation and collapse: a systematic review. J Physiother 2021;67:41-8. [Crossref] [PubMed]
28. Demi L, Wolfram F, Klersy C, De Silvestri A, Ferretti VV, Muller M, et al. New International Guidelines and Consensus on the Use of Lung Ultrasound. J Ultrasound Med 2023;42:309-44. [Crossref] [PubMed]
29. Nhat PTH, Van Hao N, Tho PV, Kerdegari H, Pisani L, Thu LNM, Phuong LT, Duong HTH, Thuy DB, McBride A, Xochicale M, Schultz MJ, Razavi R, King AP, Thwaites L, Van Vinh Chau N, Yacoub S, Gomez A. Clinical benefit of AI-assisted lung ultrasound in a resource-limited intensive care unit. Crit Care 2023;27:257. [Crossref] [PubMed]
30. Clausdorff Fiedler H, Prager R, Smith D, Wu D, Dave C, Tschirhart J, Wu B, Van Berlo B, Malthaner R, Arntfield R. Automated Real-Time Detection of Lung Sliding Using Artificial Intelligence: A Prospective Diagnostic Accuracy Study. Chest 2024;166:362-70. [Crossref] [PubMed]
31. Mento F, Perrone T, Fiengo A, Smargiassi A, Inchingolo R, Soldati G, Demi L. Deep learning applied to lung ultrasound videos for scoring COVID-19 patients: A multicenter study. J Acoust Soc Am 2021;149:3626. [Crossref] [PubMed]