Lung ultrasound early detection and monitoring in COVID-19 pneumonia: fact and fiction

Sperandeo, Marco; Trovato, Guglielmo M.

doi:10.1093/qjmed/hcaa165

Cited by 7 publications

(5 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, LUS is not suitable for formulating diagnostic hypotheses based on conjecturally speci c clues that are, actually, not reproducible, di cult to demonstrate, confusing in case of pre-existing comorbidities and have never received unanimous consensus or solid support 24,25 . Moreover, one must ask how a method like US, which only visualizes a small part of the pulmonary parenchyma could ever enable a reliable assessment of diseases extent and severity 16,26 . With these consideration in mind, if the role of CT in COVID-19 is still debated, that of LUS is not unexpectedly even more uncertain.…”

Section: Discussionmentioning

confidence: 99%

Sensitivity of Lung US compared to Chest CT for the screening of COVID-19: preliminary report of our experience

Quarato

Mirijello

Lacedonia

et al. 2020

Preprint

View full text Add to dashboard Cite

As lung ultrasound (LUS) is a noninvasive, radiation-free, repeatable and portable imaging tool suitable for a point-of-care use, several recent literature reports have emphasized its role as the ideal screening tool for SARS-CoV2 pneumonia. To evaluate the actual diagnostic accuracy of LUS for this purpose, we performed a systematic comparative study between LUS and CT scan findings in a population of 82 patients hospitalized because of COVID-19. LUS and Chest CT have been performed in all patients within 6-12 hours from the admission. The sensitivity of LUS in assessing typical CT findings was 60%. Despite LUS detected consolidations adherent to pleural surface in all cases, it was not able to detect all the consolidations assessed at CT scan (p=0.002), showing a risk to underestimate the actual disease’s extent. Moreover, only 70% of pleural surface is visible by LUS. Considering that the specificity and the positive predictive value of the same LUS signs may be lowered in a normal setting of non epidemic COVID-19 and in case of pre-existing cardio-pulmonary diseases, LUS use should not be indicated for diagnosis of COVID-19. However, it may be very useful for the assessment of pleural effusion and to guide safer fluid drainage.

show abstract

Section: Discussionmentioning

confidence: 99%

Sensitivity of Lung US compared to Chest CT for the screening of COVID-19: preliminary report of our experience

Quarato

Mirijello

Lacedonia

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Lung ultrasound is a diagnostic method greatly operator-dependent, in which the human expertise component must be accompanied by the most suitable quality of the equipment and its appropriate setting ( 2 ). As a consequence, this strictly clinical and qualitative interpretation reading of lung images is an element of weakness when health professionals with different levels of knowledge and expertise in performing the procedure are operating ( 3 ). Patients, particularly in limited resource subsets at home, in ambulances, and in emergency room facilities, are very difficult subjects for a full-contact procedure such as the chest ultrasound.…”

Section: Overviewmentioning

confidence: 99%

Artificial Intelligence (AI) and Lung Ultrasound in Infectious Pulmonary Disease

Trovato¹,

Russo²

2021

Front. Med.

View full text Add to dashboard Cite

Deep Learning algorithms are ready for use and can aid in the interpretation of radiological findings monitoring change during follow-up. However, the translational approach to ultrasound is difficult and currently subject to major limitations. Great help can derive from computer-assisted report procedures, which, in appropriate contexts of expert machine learning, can structure a future context of diagnostic orientation.Lung ultrasound is a diagnostic method that relies heavily on the operator's abilities, in which the human expertise component must be accompanied by the most suitable quality of the equipment and of its appropriate setting. However, this strictly clinical and qualitative interpretation when reading lung images is an element of weakness since we have health professionals with different levels of knowledge and expertise in performing the procedure. There are also particular difficulties linked to the conditions of the patients and to the methods of assistance and caution due to the need to prevent contagion in the fight against coronavirus 2019 disease (COVID-19).Patients, particularly in limited resource subsets at home, in ambulances, and in emergency room facilities, are very difficult subjects even for expert operators, and this is also because chest ultrasounds are full-contact procedures.Quantitative analysis makes radiology reporting much more comprehensive. Actually, several research groups have begun looking to artificial intelligence (AI) as a tool for reading and analyzing X-rays and computed tomography (CT) scans and helping to diagnose and monitor COVID-19 by several deep-learning approaches. This is carried out with the hope of overcoming the intrinsic limits of the diagnostic procedure and the context of intervention.Unfortunately, with US procedures, the proposal to use inappropriate methods, based on the automatic reading of the artifacts, in particular of the b-lines, has been addressed: this is what has been unexpectedly, and for no good reason, suggested by many. In this regard, it must be strongly reiterated that quantifying erratic and unreliable artifacts, measuring them by machine counting methods, is only a mystifying and misleading approach without advantages and is de facto dangerous in patient management.Currently, it is unlikely that the algorithms proposed may directly replace the medical doctors, and, namely, the radiologists' judgments as well as personal responsibility during ultrasound diagnosis. This is due to the limited or even absent specificity of these approaches for categorizing definite findings and to the medico-legal implications of such diagnoses.

show abstract

“…Furthermore, algorithms were passed off as innovative and sustainable medicine, optimal for directives, recommendations, or statistics ( 8 , 9 ). Ethical responsibilities and democratic accountability of researchers in their role as experts and policy advisors are great.…”

mentioning

confidence: 99%

Editorial: Lung Ultrasound in the Diagnosis of Infective Lung Diseases

Trovato

Sperandeo

2022

Front. Med.

View full text Add to dashboard Cite

Lung ultrasound early detection and monitoring in COVID-19 pneumonia: fact and fiction

Cited by 7 publications

References 6 publications

Sensitivity of Lung US compared to Chest CT for the screening of COVID-19: preliminary report of our experience

Sensitivity of Lung US compared to Chest CT for the screening of COVID-19: preliminary report of our experience

Artificial Intelligence (AI) and Lung Ultrasound in Infectious Pulmonary Disease

Editorial: Lung Ultrasound in the Diagnosis of Infective Lung Diseases

Contact Info

Product

Resources

About