0
Correspondence |

ResponseResponse FREE TO VIEW

Stein Silva, MD, PhD
Author and Funding Information

From the Critical Care Unit, CHU Purpan, INSERM U825.

CORRESPONDENCE TO: Stein Silva, MD, PhD, Critical Care Unit, CHU Purpan, INSERM U825, 31059 Toulouse Cedex 3, France; e-mail: silvastein@me.com


FINANCIAL/NONFINANCIAL DISCLOSURES: The author has reported to CHEST that no potential conflicts of interest exist with any companies/organizations whose products or services may be discussed in this article.

FUNDING/SUPPORT: The research was supported by institutional departmental funds from Centre Hospitalier Universitaire de Toulouse, Toulouse, France.

Reproduction of this article is prohibited without written permission from the American College of Chest Physicians. See online for more details.


Chest. 2015;147(6):e237. doi:10.1378/chest.15-0165
Text Size: A A A
Published online
To the Editor:

I am very grateful to Drs Trovato and Sperandeo for their comments on our article1 published in CHEST. We strongly agree that the integrative use of thoracic ultrasonography (TUS) holds the promise of improving acute respiratory failure (ARF) diagnosis and management. Nevertheless, to do so we need to first address some underpinning conceptual and methodologic issues.

First, we must explore innovative ways to usefully combine and interpret the clinical and ultrasound data recorded during ARF. A starting point is to independently assess the diagnostic value of clinical and ultrasound data1,2 before investigating an integrative analysis of the whole dataset. In the meantime, we strongly recommend that TUS be used as a complementary tool, designed to complete the physical examination and standard of care diagnosis procedures. To rely solely on TUS for the differential diagnosis of severe ARF is hazardous and could induce hasty and inappropriate therapeutic decisions. Second, we must develop fast and reliable analysis methods to interpret the high-dimensional and multimodal data recorded at the patient’s bedside. To address this issue, we proposed and validated a new supervised learning machine classifier, by combining random ensembles of predictors. Our aim is not to substitute medical reasoning with an abusive use of artificial intelligence techniques, but to demonstrate that previously described alternative binary classification methods could constitute an oversimplification.3

Unlike those of previous studies, which have suggested that an exclusive lung ultrasonography assessment could be used to estimate a patient’s respiratory and hemodynamic status,3,4 our findings highlight the pivotal place of echocardiography in the diagnosis and management of severe ARF to “disambiguate cases of hemodynamic pulmonary edema and pneumonia.” In fact, the use of supervised learning machine methods allowed us to demonstrate that left ventricular telediastolic pressure estimation has an additional value for the diagnosis of hemodynamic pulmonary edema and pneumonia (ie, high and low levels, respectively [e-Table 1, PLS Component 1, in our published article]).1 This critical point has been discussed in a study5 that explored the meaning of B-lines in a large cohort of patients with dyspnea. Interestingly, despite the fact that the authors identified a greater number of B-lines in dyspneic patients compared with control subjects, they did not find any specific feature or cutoff criterion that could allow discrimination between acute hemodynamic pulmonary edema and noncardiogenic causes of dyspnea.5

A fast-growing body of evidence suggests that TUS provides physicians with an easy, rapid, and reliable evaluation of lung and heart interactions and its variations at the bedside. However, as suggested by Trovato and Sperandeo, TUS is not a shortcut for a broader medical reasoning and can be unreliable if not used jointly with a thorough clinical assessment.

Acknowledgments

Role of sponsors: The sponsor had no role in the design of the study, the collection and analysis of the data, or the preparation of the manuscript.

Bataille B, Riu B, Ferre F, et al. Integrated use of bedside lung ultrasound and echocardiography in acute respiratory failure: a prospective observational study in ICU. Chest. 2014;146(6):1586-1593. [CrossRef] [PubMed]
 
Silva S, Biendel C, Ruiz J, et al. Usefulness of cardiothoracic chest ultrasound in the management of acute respiratory failure in critical care practice. Chest. 2013;144(3):859-865. [CrossRef] [PubMed]
 
Lichtenstein DA, Mezière GA. Relevance of lung ultrasound in the diagnosis of acute respiratory failure: the BLUE protocol. Chest. 2008;134(1):117-125. [CrossRef] [PubMed]
 
Lichtenstein DA, Mezière GA, Lagoueyte JF, Biderman P, Goldstein I, Gepner A. A-lines and B-lines: lung ultrasound as a bedside tool for predicting pulmonary artery occlusion pressure in the critically ill. Chest. 2009;136(4):1014-1020. [CrossRef] [PubMed]
 
Trovato GM, Sperandeo M. Sounds, ultrasounds, and artifacts: which clinical role for lung imaging? Am J Respir Crit Care Med. 2013;187(7):780-781. [CrossRef] [PubMed]
 

Figures

Tables

References

Bataille B, Riu B, Ferre F, et al. Integrated use of bedside lung ultrasound and echocardiography in acute respiratory failure: a prospective observational study in ICU. Chest. 2014;146(6):1586-1593. [CrossRef] [PubMed]
 
Silva S, Biendel C, Ruiz J, et al. Usefulness of cardiothoracic chest ultrasound in the management of acute respiratory failure in critical care practice. Chest. 2013;144(3):859-865. [CrossRef] [PubMed]
 
Lichtenstein DA, Mezière GA. Relevance of lung ultrasound in the diagnosis of acute respiratory failure: the BLUE protocol. Chest. 2008;134(1):117-125. [CrossRef] [PubMed]
 
Lichtenstein DA, Mezière GA, Lagoueyte JF, Biderman P, Goldstein I, Gepner A. A-lines and B-lines: lung ultrasound as a bedside tool for predicting pulmonary artery occlusion pressure in the critically ill. Chest. 2009;136(4):1014-1020. [CrossRef] [PubMed]
 
Trovato GM, Sperandeo M. Sounds, ultrasounds, and artifacts: which clinical role for lung imaging? Am J Respir Crit Care Med. 2013;187(7):780-781. [CrossRef] [PubMed]
 
NOTE:
Citing articles are presented as examples only. In non-demo SCM6 implementation, integration with CrossRef’s "Cited By" API will populate this tab (http://www.crossref.org/citedby.html).

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging & repositioning the boxes below.

Find Similar Articles
  • CHEST Journal
    Print ISSN: 0012-3692
    Online ISSN: 1931-3543